[go: up one dir, main page]

WO2018166525A1 - 人脸防伪检测方法和系统、电子设备、程序和介质 - Google Patents

人脸防伪检测方法和系统、电子设备、程序和介质 Download PDF

Info

Publication number
WO2018166525A1
WO2018166525A1 PCT/CN2018/079273 CN2018079273W WO2018166525A1 WO 2018166525 A1 WO2018166525 A1 WO 2018166525A1 CN 2018079273 W CN2018079273 W CN 2018079273W WO 2018166525 A1 WO2018166525 A1 WO 2018166525A1
Authority
WO
WIPO (PCT)
Prior art keywords
face
image
detected
camera
neural network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/079273
Other languages
English (en)
French (fr)
Inventor
杨凯
吴立威
赵晨旭
程郑鑫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sensetime Technology Development Co Ltd
Original Assignee
Beijing Sensetime Technology Development Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Sensetime Technology Development Co Ltd filed Critical Beijing Sensetime Technology Development Co Ltd
Publication of WO2018166525A1 publication Critical patent/WO2018166525A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/19—Recognition using electronic means
    • G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G06V30/19173—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/40—Spoof detection, e.g. liveness detection
    • G06V40/45—Detection of the body part being alive
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face

Definitions

  • the present application relates to computer vision technology, and in particular to a face detection method and system, an electronic device, a program and a medium.
  • In vivo detection refers to the use of computer vision technology to determine whether the face image in front of the camera is from a real person.
  • the face anti-counterfeiting focuses on detecting whether the face is authentic; the activity detection focuses on detecting whether the face is active.
  • An active face is not necessarily a non-forgery face.
  • a non-forged face is not necessarily active.
  • the embodiment of the present application provides a technical solution for performing face anti-counterfeiting detection.
  • a method for detecting a face security includes:
  • the multi-view camera comprises: one or more visible light cameras, and/or one or more designated cameras;
  • the designated camera includes any one or more of the following: a near infrared camera, an infrared camera, a low illumination visible light camera, and a wide dynamic camera.
  • the method when the multi-view camera includes a designated camera, the method further includes: performing a face anti-counterfeiting detection based on the to-be-detected image collected by the specified camera;
  • Determining, according to the result of the consistency comparison, whether the face passes the anti-counterfeiting detection comprising: responding to the image to be detected collected based on the specified camera by the face anti-counterfeiting detection, and the consistency comparison result satisfies a predetermined requirement, It is determined that the face passes the anti-counterfeiting detection.
  • the multi-view camera includes an infrared camera or a near-infrared camera
  • performing face anti-counterfeiting detection based on the to-be-detected image collected by the specified camera including:
  • the specified camera collects The detected image did not pass the face security detection.
  • the multi-view camera further includes a visible light camera
  • Performing the face anti-counterfeiting detection based on the to-be-detected image collected by the specified camera further includes:
  • the state of the pupil in the face to be detected in the image to be detected collected by the visible light camera is in a preset state, and the image to be detected collected by the specified camera does not pass the anti-counterfeiting detection.
  • the multi-view camera includes a wide dynamic camera
  • performing face anti-counterfeiting detection based on the to-be-detected image collected by the specified camera including:
  • the image to be detected collected by the specified camera does not pass the face security detection in response to the moiré included in the image to be detected collected by the wide dynamic camera.
  • the method further includes:
  • Determining, according to the result of the consistency comparison, whether the face passes the anti-counterfeiting detection including:
  • the face passes the anti-counterfeiting detection in response to the image to be detected acquired based on the specified camera passing the face anti-counterfeiting detection, and the conformity comparison result satisfies a predetermined requirement, and the extracted feature does not include the fake face cue information.
  • the image to be detected collected by the specified camera passes the face anti-counterfeiting detection, and the consistency comparison result satisfies a predetermined requirement, and the extracting is performed to be detected.
  • the feature of the image, and detecting whether the extracted feature includes an operation of forging face cue information.
  • the extracted features include one or more of the following: a local binary pattern feature, a sparsely encoded histogram feature, a panorama feature, and a face map feature. , face detail map features.
  • the forged face cue information has human eye observability under visible light conditions.
  • the forged face cue information includes any one or more of the following: forged clue information of the imaging medium, forged clue information of the imaging medium, and a real fake person The clue information of the face.
  • the forged clue information of the imaging medium includes: edge information, reflective information, and/or material information of the imaging medium; and/or,
  • the forged clue information of the imaging medium includes: a screen edge of the display device, a screen reflection, and/or a screen moiré; and/or,
  • the clue information of the real fake face includes: the characteristics of the masked face, the characteristics of the model face, and the characteristics of the sculpture face.
  • the extracting the feature of the image to be detected and detecting whether the extracted feature includes forged face cue information comprises:
  • the training image set includes: a plurality of face images that can be used as positive samples for training and a plurality of images that can be used as negative samples for training;
  • the method for acquiring a training image set including forged face cue information includes:
  • Image processing for simulating forged face cue information is performed on at least a portion of the acquired at least one face image to generate at least one image that can be used as a negative sample for training.
  • the neural network includes: a first neural network located in the electronic device.
  • the neural network includes: a second neural network located in the server.
  • the method further includes:
  • the server sends a detection result of whether the extracted feature includes forged face cue information to the electronic device.
  • the neural network further includes: a first neural network located in the electronic device; the size of the first neural network is smaller than a size of the second neural network;
  • the method further includes:
  • the electronic device in response to the detection result of the to-be-detected image including the forged face cue information, determining, according to the consistency comparison result, whether the face passes the anti-counterfeiting detection The electronic device determines that the face does not pass the anti-counterfeiting detection according to the detection result of the output of the first neural network.
  • the method further includes: the server returning the detection result output by the second neural network to the electronic device;
  • Determining whether the face passes the anti-counterfeiting detection according to the result of the consistency comparison comprising: whether the electronic device passes the face anti-counterfeiting detection according to the image to be detected collected based on the specified camera, and whether the consistency comparison result is The detection result satisfying the predetermined requirement and the output of the second neural network determines whether the face to be passed the anti-counterfeiting detection.
  • a human face anti-counterfeiting detection system includes:
  • a multi-view camera for collecting a plurality of images to be detected including a human face
  • a first acquiring module configured to acquire, by using a multi-view camera, a plurality of to-be-detected images including a human face, and acquire depth information of a face in the image to be detected;
  • a comparison module configured to compare the obtained depth information of the face with the preset face depth information
  • a determining module configured to determine, according to the consistency comparison result, whether the face passes the anti-counterfeiting detection.
  • the multi-view camera comprises: one or more visible light cameras, and/or one or more designated cameras;
  • the designated camera includes any one or more of the following: a near infrared camera, an infrared camera, a low illumination visible light camera, and a wide dynamic camera.
  • the system when the multi-view camera includes a designated camera, the system further includes:
  • a first face anti-counterfeiting detection module configured to perform face anti-counterfeiting detection based on the to-be-detected image collected by the specified camera
  • the determining module is configured to: determine that the face passes the anti-counterfeiting detection in response to the image to be detected collected by the specified camera passes the face anti-counterfeiting detection, and the consistency comparison result satisfies a predetermined requirement.
  • the first face anti-counterfeiting detection module is configured to:
  • the specified camera collects The detected image did not pass the face security detection.
  • the multi-view camera further includes a visible light camera
  • the first face anti-counterfeiting detection module is further configured to:
  • the image to be detected collected by the specified camera does not pass the anti-counterfeiting detection in response to the state of the pupil in the face of the image to be detected collected by the visible light camera being in a preset state.
  • the first face anti-counterfeiting detection module is configured to:
  • the image to be detected collected by the specified camera does not pass the face security detection in response to the moiré included in the image to be detected collected by the wide dynamic camera.
  • the method further includes:
  • a second face anti-counterfeiting detection module configured to extract a feature of the image to be detected, and detect whether the extracted feature includes forged face cue information
  • the determining module is used to:
  • the second face anti-counterfeiting detection module is configured to pass the face anti-counterfeiting detection based on the to-be-detected image collected by the specified camera, and the consistency comparison result Satisfying the predetermined requirement, starting to perform the operation of extracting the feature of the image to be detected and detecting whether the extracted feature includes forged face cue information.
  • the extracted features include one or more of the following: a local binary pattern feature, a sparsely encoded histogram feature, a panorama feature, and a face map feature. , face detail map features.
  • the forged face cue information has human eye observability under visible light conditions.
  • the forged face cue information includes any one or more of the following: forged clue information of the imaging medium, forged clue information of the imaging medium, and a real fake person The clue information of the face.
  • the forged clue information of the imaging medium includes: edge information, reflective information, and/or material information of the imaging medium; and/or,
  • the forged clue information of the imaging medium includes: a screen edge of the display device, a screen reflection, and/or a screen moiré; and/or,
  • the clue information of the real fake face includes: the characteristics of the masked face, the characteristics of the model face, and the characteristics of the sculpture face.
  • the second face anti-counterfeiting detection module includes: a neural network, configured to receive the image to be detected, and outputted to indicate whether the image to be detected includes At least one detection result of the forged face cue information, wherein the neural network is pre-trained based on the training image set including the forged face cue information.
  • the training image set includes: a plurality of face images that can be used as positive samples for training and a plurality of images that can be used as negative samples for training;
  • the system further includes:
  • a second acquiring module configured to acquire a plurality of face images that can be used as positive samples for training; and perform image processing for simulating forged face cue information on at least part of the acquired at least one face image to generate at least An image that can be used as a negative sample for training.
  • the neural network includes: a first neural network located in the electronic device.
  • the neural network includes: a second neural network located in the server;
  • the system also includes:
  • a first sending module located in the electronic device, configured to send the image to be detected to a server;
  • a second sending module configured to send, by the second neural network, a detection result of whether the extracted feature includes forged face cue information output by the second neural network to the electronic device.
  • the neural network further includes: a first neural network located in the electronic device, configured to receive the image to be detected and output the image to be detected Whether the detection result of at least one forged face cue information is included; the size of the first neural network is smaller than the size of the second neural network;
  • the first sending module is configured to send the image to be detected to the server in response to the detection result that the image to be detected does not include the forged face cue information output by the first neural network.
  • an electronic device including the face anti-counterfeiting detection system of any of the above embodiments of the present application.
  • another electronic device including:
  • a memory for storing executable instructions
  • a processor configured to communicate with the memory to execute the executable instruction to complete an operation of the face anti-counterfeiting detection method according to any one of the embodiments of the present application.
  • a computer program comprising computer readable code, when the computer readable code is run on a device, the processor in the device performs the implementation of the present application.
  • a computer readable storage medium for storing computer readable instructions, wherein when the instructions are executed, performing the method of any one of the embodiments of the present application The operation of each step in the process.
  • the face anti-counterfeiting detection method and system, the electronic device, the program and the medium provided by the above-mentioned embodiments of the present application acquire the depth information of the face image in the image to be detected through the plurality of to-be-detected images of the human face collected by the multi-view camera. And comparing the obtained depth information of the face with the preset face depth information; determining whether the face passes the anti-counterfeiting detection according to the result of the comparison, the depth information in the image collected by the multi-view camera in the embodiment of the present application, Effective face detection of anti-counterfeiting is achieved.
  • FIG. 1 is a flow chart of an embodiment of an applicant's face anti-counterfeiting detection method.
  • FIG. 2 is a schematic diagram of a binocular camera in the embodiment of the present application.
  • FIG. 3 is a flow chart of another embodiment of the applicant's face anti-counterfeiting detection method.
  • FIG. 4 is a flow chart of still another embodiment of the applicant's face anti-counterfeiting detection method.
  • FIG. 5 is a schematic structural diagram of an embodiment of an applicant's face anti-counterfeiting detection system.
  • FIG. 6 is a schematic structural view of another embodiment of the applicant's face anti-counterfeiting detection system.
  • FIG. 7 is a schematic structural view of still another embodiment of the applicant's face anti-counterfeiting detection system.
  • FIG. 8 is a schematic structural diagram of an application embodiment of an electronic device according to the present application.
  • terminal devices such as terminal devices, computer systems, servers, etc.
  • terminal devices can operate with numerous other general purpose or special purpose computing system environments or configurations.
  • Examples of well-known terminal devices, computing systems, environments, and/or configurations suitable for use with terminal devices, computer systems, servers, etc. include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients Machines, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, networked personal computers, small computer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above, and the like.
  • Terminal devices such as terminal devices, computer systems, servers, etc.
  • program modules may include routines, programs, target programs, components, logic, data structures, and the like that perform the specified tasks or implement the specified abstract data types.
  • the computer system/server can be implemented in a distributed cloud computing environment where tasks are performed by remote processing devices that are linked through a communication network.
  • program modules may be located on a local or remote computing system storage medium including storage devices.
  • FIG. 1 is a flow chart of an embodiment of an applicant's face anti-counterfeiting detection method. As shown in FIG. 1, the face anti-counterfeiting detection method of this embodiment includes:
  • the multi-view camera in each embodiment of the present application may be, for example, a binocular camera, a trinocular camera, a four-eye camera, etc., which respectively indicate that there are several cameras.
  • the multi-view camera can include, for example, but is not limited to, one or more visible light cameras, and/or one or more designated cameras.
  • the designated camera may include, but is not limited to, any one or more of the following: a near infrared camera, an infrared camera, a low illumination visible light camera, and a wide dynamic camera.
  • a binocular camera including a near-infrared camera plus a low-illumination visible light camera, or a binocular camera including a near-infrared camera widened dynamic visible light camera may be used.
  • FIG. 2 it is a schematic diagram of a binocular camera in the embodiment of the present application.
  • the depth information refers to the distance between the photographer (ie, the face) and the lens of the multi-view camera, and can be calculated by calibrating any two or more camera parameters in the multi-view camera.
  • the distance between the photographed face and the lens that is, the depth information of the face in the image to be detected.
  • the camera parameters may include, for example, internal parameters (focal length, image center, distortion coefficient, etc.) of the camera and external parameters (R (rotation) matrix, T (translation) matrix).
  • the operation 102 may be performed by a processor invoking a corresponding instruction stored in a memory, or may be performed by a first acquisition module executed by the processor.
  • Forged faces generally do not contain depth information.
  • the depth information of each facial feature to the camera in a normal human face is different and should be different.
  • the depth information of the face is counted, and a certain range of deviation is allowed, and the preset face depth information is obtained; but if the face is forged on paper or on the device, the depth information of the facial features to the camera is almost the same, according to the acquired person.
  • the difference condition satisfies the preset face depth information
  • the operation 104 may be performed by a processor invoking a corresponding instruction stored in a memory or by a comparison module executed by the processor.
  • the depth information of the acquired facial features of the face to the camera is different, and the difference condition satisfies the preset face depth information, it is determined that the face in the image to be detected passes the anti-counterfeiting detection. Otherwise, if there is no difference in the depth information of the facial features of the obtained face to the camera, and/or the difference situation does not satisfy the preset face depth information, it is determined that the face in the image to be detected does not pass the anti-counterfeiting detection.
  • the operation 106 may be performed by a processor invoking a corresponding instruction stored in a memory, or may be performed by a determination module executed by the processor.
  • the face anti-counterfeiting detection method obtaineds the depth information of the face in the image to be detected by the plurality of to-be-detected images of the face collected by the multi-view camera; and the depth information of the obtained face is The preset face depth information is compared and compared. According to the consistency comparison result, it is determined whether the face passes the anti-counterfeiting detection.
  • the depth information in the image acquired by the multi-view camera is used to implement effective face anti-counterfeiting detection.
  • the 2D-type forged face refers to the face image printed by the paper-like material.
  • the 2D-type forged face generally does not contain depth information (for example, the depth information of each facial feature to the camera in a normal human face is different) But if the fake face is on paper or on the device, the depth information of the facial features to the camera is almost the same), and also contains the fake face of the paper face, paper material, paper reflection, paper edge, etc. Clue information.
  • the 2.5D-type forged face refers to a face image carried by a carrier device such as a video remake device.
  • the 2.5D-type forged face generally does not include depth information, and also includes a screen moiré of a carrier device such as a video remake device, and a screen reflection. Forged face cue information, such as the edge of the screen.
  • 3D fake faces refer to real fake faces, such as masks, models, sculptures, 3D printing, etc.
  • the 3D fake faces cannot absorb some of the light sources emitted by the specified camera, and also have corresponding fake face clues.
  • Information such as stitching of the mask, abstraction of the model, or too smooth skin, etc.
  • the method further includes: performing face anti-counterfeiting detection based on the image to be detected collected by the specified camera.
  • determining whether the face passes the anti-counterfeiting detection according to the consistency comparison result may include: determining, by the face anti-counterfeiting detection, that the image to be detected collected based on the specified camera passes the face anti-counterfeiting detection, and the consistency comparison result satisfies the predetermined requirement, determining The face in the image to be detected passes the anti-counterfeiting detection.
  • the face anti-counterfeiting detection based on the image to be detected collected by the specified camera may include:
  • the normal normal human pupil will be in a bright and transparent state, and the paper-printed face, model and sculpture, etc., will not appear in the pupil of the forged face;
  • the fake face will not be imaged in front of the near-infrared camera (ie, the screen is dark), and the person in the image to be detected collected by the infrared camera and the near-infrared camera can be distinguished by distinguishing the state of the pupil and whether the face image is detected. Whether the face is a fake face.
  • the multi-view camera may further include a visible light camera.
  • performing the face anti-counterfeiting detection based on the to-be-detected image collected by the specified camera may further include:
  • the state of the pupil in the image to be detected in the image to be detected collected by the visible light camera is in a preset state, and it is determined that the face in the image to be detected does not pass the anti-counterfeiting detection, or the image to be detected collected by the camera is not passed the face anti-counterfeiting detection.
  • the binocular camera composed of the infrared camera plus the visible light camera is used for the face anti-counterfeiting detection
  • the near-infrared photo of a real person can be collected and printed using the paper to attack, because the printed face pupil is Near-infrared camera shooting will show a bright and transparent state; this situation can be judged by the visible light camera, because the pupil of the visible light camera should be in a normal state, but the face of the near-infrared shooting and printing is bright and transparent.
  • the two cameras complement each other to achieve the face anti-counterfeiting detection effect.
  • the face anti-counterfeiting detection based on the image to be detected collected by the specified camera may include:
  • Wide dynamic cameras generally have multiple exposures, which can reduce the influence of light in applications where backlighting is more serious, thus improving the robustness of face recognition and face security detection.
  • the 2D class and the 2.5D class forged face cue information which may exist in the image to be detected can be identified, thereby realizing the detection of the 2D class and the 2.5D class forged face; the general multi-view camera
  • the specified camera can more effectively identify fake faces from 3D classes and some 2.5D fake faces.
  • the living body detection fails; or the large-scale moiré in the wide-motion camera in the multi-view camera fails the living body detection; in the dark light application Scenes, when a multi-light camera includes a low-illumination camera, it can reduce the influence of light and improve the robustness of face recognition and face anti-counterfeiting detection.
  • the method further includes: extracting features of the image to be detected, and detecting whether the extracted features include forged face cue information.
  • the forged face cue information described above has human eye observability under visible light conditions.
  • determining whether the face passes the anti-counterfeiting detection according to the comparison result may include: determining whether the image to be detected based on the specified camera passes the face anti-counterfeiting detection, the consistency comparison result satisfies the predetermined requirement, and Whether the extracted features include forged face cue information, and the face passes the anti-counterfeiting detection.
  • the face is determined to pass the anti-counterfeiting detection in response to the image to be detected collected by the specified camera passing the face anti-counterfeiting detection, and the matching comparison result satisfies the predetermined requirement, and the extracted feature does not include the fake face cue information. Otherwise, if the image to be detected collected by the specified camera does not pass the face anti-counterfeiting detection, and/or the consistency comparison result satisfies the predetermined requirement, and/or the extracted feature does not include the fake face cue information, as long as the three situations occur In either case, it is determined that the face has not passed the anti-counterfeiting detection.
  • FIG. 3 is a flow chart of an embodiment of an applicant's face anti-counterfeiting detection method. As shown in FIG. 3, the face anti-counterfeiting detection method of this embodiment includes:
  • the operation 202 may be performed by a processor invoking a corresponding instruction stored in a memory, or may be performed by a first acquisition module executed by the processor.
  • the operation of detecting the face anti-counterfeiting based on the image to be detected collected by the specified camera may be implemented by using, but not limited to, the foregoing embodiments of the present application.
  • the operation 204 may be performed by a processor invoking a corresponding instruction stored in a memory, or may be performed by a comparison module executed by the processor and a first face anti-counterfeiting detection module.
  • the subsequent process of the embodiment is not performed, or the image to be detected may be further outputted.
  • the face does not pass the security detection prompt message.
  • the operation 206 may be performed by a processor invoking a corresponding instruction stored in a memory, or may be performed by a second face anti-counterfeiting detection module executed by the processor.
  • the operation 208 may be performed by a processor invoking a corresponding instruction stored in a memory, or may be performed by a determination module executed by the processor.
  • the features extracted in the embodiments of the present application may include, but are not limited to, any of the following: a local binary pattern (LBP) feature, a sparsely encoded histogram (HSC) Feature, panorama (LARGE) feature, face map (SMALL) feature, face detail map (TINY) feature.
  • LBP local binary pattern
  • HSC sparsely encoded histogram
  • LARGE panorama
  • SMALL face map
  • TINY face detail map
  • the feature items included in the extracted feature may be updated according to the fake face cue information that may appear.
  • the edge information in the image can be highlighted by the LBP feature; the reflection and fuzzy information in the image can be more clearly reflected by the HSC feature; the LARGE feature is a full-image feature, which can be extracted to the most obvious image based on the LARGE feature.
  • a forged hack; a face map (SMALL) is a region cut of a size of a face frame (for example, 1.5 times the size) in an image, which includes a face, a face, and a background, which are based on the SMALL feature.
  • Extracting the forged clues such as reflection, remake device screen moiré and the edge of the model or mask; face detail map (TINY) is the area cut image of the size of the face frame, including the face, based on the TINY feature, can be extracted to the image PS (based on image editing software photoshop editing), remake screen moiré and the texture of the model or mask and other forged clues.
  • TINY face detail map
  • the forged face cue information in the embodiment of the present application has human eye observability under visible light conditions, that is, the human eye can observe these forgeries under visible light conditions. Face clue information. Based on this feature of the fake face cue information, it is possible to realize anti-counterfeiting detection by using a still image or a dynamic video captured by a visible light camera (such as an RGB camera), avoiding the introduction of a specific camera and reducing the hardware cost.
  • the forged face cue information may include, for example but not limited to, any one or more of the following: forged clue information of the imaging medium, forged clue information of the imaging medium, and clue information of the fake face that is actually present.
  • the forged clue information of the imaging medium is also referred to as 2D-type forged face cue information, and the forged clue information of the imaging medium may be referred to as 2.5D-type forged face cue information, and the cue information of the real fake face may be referred to as 3D.
  • the fake face cue information that needs to be detected may be updated correspondingly according to a possible fake face manner.
  • the electronic device can "discover" the boundaries between various real faces and fake faces, and realize various types of anti-counterfeiting detection under the condition of general hardware devices such as visible light cameras. Resist the "hack" attack and improve security.
  • the forged clue information of the imaging medium may include, but is not limited to, edge information, reflective information, and/or material information of the imaging medium.
  • the forged clue information of the imaging medium may include, for example but is not limited to, a screen edge of the display device, a screen reflection, and/or a screen moiré.
  • the clue information of the real fake face may include, but is not limited to, the characteristics of the masked face, the characteristics of the model face, and the characteristics of the sculpture face.
  • the forged face cue information in the above embodiment can be divided into 2D class, 2.5D class and 3D class forged face in dimension.
  • the 2D-type forged face refers to a face image printed by a paper-like material
  • the 2D-type forged face cue information may include, for example, a paper face edge, a paper material, a paper reflective, a paper edge, and the like.
  • the 2.5D-type forged face refers to a face image carried by a carrier device such as a video remake device
  • the 2.5D-type forged face cues information may include, for example, a screen moiré of a carrier device such as a video remake device, a screen reflection, a screen edge, and the like. Forging clue information.
  • 3D fake faces refer to real fake faces, such as masks, models, sculptures, 3D printing, etc.
  • the 3D fake faces also have corresponding forged clue information, such as the stitching of the mask and the abstraction of the model. Or forged clue information such as too smooth skin.
  • the anti-counterfeiting detection of the face in the detected image is further performed by extracting the feature of the image to be detected or the image, and detecting whether the extracted feature includes forged face cue information, and determining the to-be-detected according to the detection result.
  • the image or video passes the face anti-counterfeiting detection and the face anti-counterfeiting detection by multiple means, further improves the robustness and accuracy of the face anti-counterfeiting detection result, and can realize the visible light without relying on special multi-spectral equipment Effective face anti-counterfeiting detection under the condition, without the need of special hardware equipment, reduces the hardware cost caused by this, and can be conveniently applied to various face detection scenarios.
  • extracting features of each image to be detected and detecting whether the extracted features include forged face cue information may be implemented as follows: And inputting, by the neural network, a detection result indicating whether the image to be detected includes at least one forged face cue information, wherein the neural network is pre-trained based on the training image set including the forged face cue information carry out.
  • a training image set including forged face cue information may be obtained by:
  • Image processing for simulating forged face cue information is performed on at least a portion of the acquired at least one face image to generate at least one image that can be used as a negative sample for training.
  • the neural network may include: a first neural network located in the electronic device, that is, performing the foregoing implementation by the first neural network located in the electronic device.
  • a first neural network located in the electronic device that is, performing the foregoing implementation by the first neural network located in the electronic device.
  • an operation of extracting features of each image to be detected and detecting whether the extracted features include forged face cue information is respectively detected.
  • the electronic device transmits the image to be detected to the server.
  • the neural network may include: a second neural network located in the server, that is, performing, by using a second neural network located in the server, performing, respectively, extracting features of each image to be detected in each of the foregoing embodiments, and An operation of detecting whether the extracted face cue information is included in the extracted feature is detected.
  • the face anti-counterfeiting detection method of this embodiment further includes: the server transmitting, to the electronic device, a detection result of whether the extracted feature includes the forged face cue information.
  • the neural network may include: a first neural network located in the electronic device and a second neural network located in the server, wherein the first neural network The size of the network is smaller than the size of the second neural network.
  • the first neural network may be smaller than the second neural network in the number of network layers and/or parameters.
  • the first neural network and the second neural network may each be a multi-layer neural network (ie, a deep neural network), such as a multi-layer convolutional neural network, such as LeNet, AlexNet, or the like. Any neural network model such as GoogLeNet, VGG, ResNet.
  • the first neural network and the second neural network may employ a neural network of the same type and structure, or a neural network of different types and structures.
  • the face anti-counterfeiting detection method of this embodiment includes:
  • the electronic device acquires, by using a multi-view camera, a plurality of to-be-detected images including a human face, and acquires depth information of a face in the image to be detected.
  • the operation 302 may be performed by a processor invoking a corresponding instruction stored in a memory, or may be performed by a first acquisition module executed by the processor.
  • the electronic device compares the obtained depth information of the face with the preset face depth information, and performs the face security detection based on the to-be-detected image collected by the specified camera.
  • the operation of detecting the face anti-counterfeiting based on the image to be detected collected by the specified camera may be implemented by using, but not limited to, the foregoing embodiments of the present application.
  • the operation 304 may be performed by a processor invoking a corresponding instruction stored in a memory, or may be performed by a comparison module executed by the processor and a first face anti-counterfeiting detection module.
  • the electronic device In response to the image to be detected collected by the specified camera passes the face anti-counterfeiting detection, and the consistency comparison result satisfies the predetermined requirement, the electronic device inputs the image to be detected into the first neural network, and outputs the image to be expressed by the first neural network.
  • the detection image includes a detection result of at least one forged face cue information.
  • the subsequent process of the embodiment is not performed, or the image to be detected may be further outputted.
  • the face does not pass the security detection prompt message.
  • the forged face cue information therein has human eye observability under visible light conditions.
  • the first neural network is pre-trained based on a training image set including forged face cue information.
  • the forged face cues contained in the features extracted in the embodiments of the present application may be learned by the first neural network by training the first neural network in advance, and then any information including the forged face cues After the image is input into the first neural network, it will be detected, and it can be judged as a fake face image, otherwise it is a real face image.
  • the operation 306 may be performed by a processor invoking a corresponding instruction stored in a memory, or may be performed by a first neural network that is executed by the processor.
  • the electronic device sends the to-be-detected image to the server, in response to the first neural network outputting the detection result that the image to be detected does not include the forged face cue information.
  • the first neural network outputs the detection result of the to-be-detected image including the forged face cue information, and the electronic device may output a prompt message that the face in the to-be-detected image does not pass the anti-counterfeiting detection, and does not perform the follow-up of the embodiment. Process.
  • the operation 308 may be performed by a processor invoking a corresponding instruction stored in a memory, or may be performed by a first transmitting module executed by the processor.
  • the server inputs the image to be detected into the second neural network, and outputs, by using the second neural network, a detection result indicating whether the image to be detected includes at least one forged face cue information, and returns the detection result to the electronic device.
  • the forged face cue information therein has human eye observability under visible light conditions.
  • the second neural network is pre-trained based on a training image set including forged face cue information.
  • the forged face cues contained in the features extracted in the embodiments of the present application may be learned by the second neural network in advance by training the second neural network, and then any information including the forged face cues is included. After the image is input into the second neural network, it will be detected, and it can be judged as a fake face image, otherwise it is a real face image.
  • the operation 310 may be performed by a processor invoking a corresponding instruction stored in a memory, or may be performed by a second neural network and a second transmitting module that are executed by the processor.
  • the electronic device determines, according to the detection result of the second neural network output returned by the server, whether the face in the image to be detected passes the anti-counterfeiting detection.
  • the detection result of the output of the second neural network is that the image to be detected does not include any detection result of the forged face cue information, it is determined that the face in the image to be detected passes the anti-counterfeiting detection. Otherwise, if the detection result of the output of the second neural network is that the image to be detected does not include any detection result of the forged face cue information, it is determined that the face in the image to be detected does not pass the anti-counterfeiting detection.
  • the operation 312 may be performed by a processor invoking a corresponding instruction stored in a memory or by a determining module executed by the processor.
  • the electronic device in the foregoing embodiments of the present application may be, for example, a mobile phone terminal or a tablet computer. Since the hardware performance of the terminal device is usually limited, the neural network that performs more feature extraction and detection will require more computing and storage resources, while the computing and storage resources of the terminal device are relatively limited compared to the cloud server, in order to save the terminal device side nerve The calculation and storage resources occupied by the network can ensure the effective detection of the face security.
  • the first neural network with a small network (lower network and/or less network parameters) is set in the terminal device.
  • the second neural network with more network parameters and the comprehensive anti-counterfeiting clue feature make the second neural network more robust and better in detection performance, in addition to extracting the LBP feature and the face SMALL feature from the image to be detected, Extracting HSC features, LARGE features, TINY features, and other features that may include forged face cue information, in the first neural network
  • the second neural network is used to perform more accurate and comprehensive face anti-counterfeiting detection, which improves the accuracy of the detection result; in the video collected by the first neural network When the face does not pass the face anti-counterfeiting detection, it is not necessary to perform the face anti-counterfeiting detection through the second neural network, which improves the efficiency
  • any of the methods for detecting the face security provided by the embodiments of the present application may be performed by any suitable device having data processing capabilities, including but not limited to: an electronic device, a server, and the like.
  • any method for detecting the face anti-counterfeiting detection provided by the embodiment of the present application may be executed by a processor, such as the processor executing any one of the face anti-counterfeiting detection methods mentioned in the embodiments of the present application by calling corresponding instructions stored in the memory. This will not be repeated below.
  • the foregoing program may be stored in a computer readable storage medium, and the program is executed when executed.
  • the foregoing steps include the steps of the foregoing method embodiments; and the foregoing storage medium includes: a medium that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.
  • FIG. 5 is a schematic structural diagram of an embodiment of an applicant's face anti-counterfeiting detection system.
  • the face anti-counterfeiting system of the embodiment can be used to implement the foregoing embodiments of the face anti-counterfeiting method of the present application.
  • the face anti-counterfeiting detection system of this embodiment includes: a multi-view camera, a first acquisition module, a comparison module, and a determination module. among them:
  • a multi-view camera for collecting a plurality of images to be detected including a human face may be, for example, a binocular camera, a trinocular camera, a quad target camera, or the like.
  • the multi-view camera can include, for example, but is not limited to, one or more visible light cameras, and/or one or more designated cameras.
  • the designated camera may include, but is not limited to, any one or more of the following: a near infrared camera, an infrared camera, a low illumination visible light camera, and a wide dynamic camera.
  • the first acquiring module is configured to acquire, by using a multi-view camera, a plurality of to-be-detected images including a human face, and acquire depth information of a face in the image to be detected.
  • the comparison module is configured to compare the obtained depth information of the face with the preset face depth information.
  • the determining module is configured to determine whether the face passes the anti-counterfeiting detection according to the comparison result.
  • the face anti-counterfeiting detection system acquires the depth information of the face in the image to be detected by using the plurality of to-be-detected images of the face collected by the multi-view camera; and the depth information of the obtained face is The preset face depth information is compared and compared. According to the consistency comparison result, it is determined whether the face passes the anti-counterfeiting detection.
  • the depth information in the image acquired by the multi-view camera is used to implement effective face anti-counterfeiting detection.
  • FIG. 6 is a schematic structural view of another embodiment of the applicant's face anti-counterfeiting detection system.
  • the face anti-counterfeiting detection system of the embodiment may further include: a first face anti-counterfeiting detecting module, configured to detect an image to be detected based on the specified camera. Perform face security detection.
  • the determining module is configured to determine that the face in the image to be detected passes the anti-counterfeiting detection in response to the image to be detected collected by the specified camera passes the face anti-counterfeiting detection, and the consistency comparison result satisfies the predetermined requirement.
  • the first face anti-counterfeiting detection module can be used to: detect whether a face is detected according to an image to be detected collected from an infrared camera or a near-infrared camera. Perform face anti-counterfeiting detection; and/or perform face anti-counterfeiting detection according to the state of the pupil in the face.
  • the multi-view camera also includes a visible light camera.
  • the first face anti-counterfeiting detection module is further configured to: identify whether the state of the pupil in the image to be detected collected by the visible light camera is in a preset state. The state of the pupil in the image to be detected collected by the visible light camera is in a preset state, and it is determined that the face in the image to be detected does not pass the anti-counterfeiting detection, or the image to be detected collected by the specified camera does not pass the anti-counterfeiting detection.
  • the first face anti-counterfeiting detection module is configured to: detect whether a moiré is included in the image to be detected collected by the wide dynamic camera, and perform face anti-counterfeiting detection. In response to the moiré pattern being detected by the wide dynamic camera, the image to be detected collected by the specified camera does not pass the face anti-counterfeiting detection.
  • the face anti-counterfeiting detection system of each of the above embodiments may further include: a second face anti-counterfeiting detection module, configured to extract features of the image to be detected, and detect whether the extracted features include forgery Face clue information.
  • the determining module is configured to pass the face anti-counterfeiting detection according to the image to be detected collected by the specified camera, and the consistency comparison result satisfies the predetermined requirement, and the extracted feature does not include the fake face cue information. It is determined that the face in the image to be detected passes the anti-counterfeiting detection.
  • the second face anti-counterfeiting detection module is configured to perform the function of extracting the image to be detected, and the image to be detected collected by the specified camera passes the face anti-counterfeiting detection, and the matching result meets the predetermined requirement, and starts to perform the feature of extracting the image to be detected. And detecting whether the extracted feature includes the operation of forging face cue information.
  • the features extracted in the embodiments of the present application may include, but are not limited to, any of the following: an LBP feature, an HSC feature, a LARGE feature, a SMALL feature, and a TINY feature.
  • the feature items included in the extracted features may be updated based on the fake face cue information that may appear.
  • the forged face cue information in various embodiments of the present application has human eye observability under visible light conditions.
  • the forged face cue information may include, for example but not limited to, any one or more of the following: forged clue information of the imaging medium, forged clue information of the imaging medium, and clue information of the fake face that is actually present.
  • the forged clue information of the imaging medium may include, but is not limited to, edge information, reflective information, and/or material information of the imaging medium.
  • the forged clue information of the imaging medium may include, for example but is not limited to, a screen edge of the display device, a screen reflection, and/or a screen moiré.
  • the clue information of the real fake face may include, but is not limited to, the characteristics of the masked face, the characteristics of the model face, and the characteristics of the sculpture face.
  • the second face anti-counterfeiting detection module includes: a neural network, configured to receive an image to be detected, and output a message indicating whether the image to be detected includes at least one forged face cue information.
  • the detection result wherein the neural network is pre-trained based on the training image set including the forged face cue information.
  • the training image set may include: a plurality of face images that can be used as positive samples for training and a plurality of images that can be used as negative samples for training;
  • the face anti-counterfeiting detection system of each of the above embodiments may further include: a second acquiring module, configured to acquire a plurality of face images that can be used as positive samples for training; and at least one face image obtained Image processing for simulating forged face cue information is performed at least partially to generate at least one image that can be used as a negative sample for training.
  • a second acquiring module configured to acquire a plurality of face images that can be used as positive samples for training
  • at least one face image obtained Image processing for simulating forged face cue information is performed at least partially to generate at least one image that can be used as a negative sample for training.
  • the neural network described above includes a first neural network located in the electronic device.
  • the neural network described above includes a second neural network located in the server.
  • the face anti-counterfeiting detection system of this embodiment may further include: a first sending module and/or a second sending module. among them:
  • a first sending module located in the electronic device, configured to send the image to be detected to the server
  • the second sending module is located in the server, and is configured to send, to the electronic device, the detection result of whether the extracted feature included in the second neural network includes the forged face cue information.
  • FIG. 7 is a schematic structural diagram of the applicant's face anti-counterfeiting detection system in the other embodiment.
  • the neural network further includes: a first neural network located in the electronic device, configured to receive the image to be detected and output to indicate whether the image to be detected includes at least A false detection result of the face clue information.
  • the size of the first neural network is smaller than the size of the second neural network.
  • the first sending module is configured to send the image to be detected to the server in response to the detection result that the image to be detected does not include the forged face cue information output by the first neural network.
  • the embodiment of the present application further provides an electronic device, which may include the face anti-counterfeiting detection system of any of the above embodiments.
  • the electronic device can be, for example, an electronic device or a server or the like.
  • another electronic device provided by the embodiment of the present application includes:
  • a memory for storing executable instructions
  • a processor configured to communicate with the memory to execute the executable instruction to complete the operation of the face anti-counterfeiting detection method of any of the above embodiments of the present application.
  • FIG. 8 is a schematic structural diagram of an application embodiment of an electronic device according to the present application.
  • the electronic device includes one or more processors, a communication unit, etc., such as one or more central processing units (CPUs), and/or one or more images.
  • processors such as one or more central processing units (CPUs), and/or one or more images.
  • a processor GPU or the like, the processor can perform various appropriate actions and processes according to executable instructions stored in a read only memory (ROM) or executable instructions loaded from a storage portion into a random access memory (RAM) .
  • ROM read only memory
  • RAM random access memory
  • the communication portion may include, but is not limited to, a network card, which may include, but is not limited to, an IB (Infiniband) network card, and the processor may communicate with the read only memory and/or the random access memory to execute executable instructions, and connect to the communication portion through the bus. And communicating with the other target device by the communication unit, so as to complete the operation corresponding to any method provided by the embodiment of the present application, for example, acquiring a plurality of to-be-detected images including a human face collected by the multi-view camera, and acquiring the to-be-detected image. Depth information of the face image; comparing the obtained depth information of the face with the preset face depth information; determining whether the face passes the anti-counterfeiting detection according to the consistency comparison result.
  • a network card which may include, but is not limited to, an IB (Infiniband) network card
  • the processor may communicate with the read only memory and/or the random access memory to execute executable instructions, and connect to the communication portion through the bus.
  • the CPU, ROM, and RAM are connected to each other through a bus.
  • the ROM is an optional module.
  • the RAM stores executable instructions, or writes executable instructions to the ROM at runtime, the executable instructions causing the processor to perform operations corresponding to any of the methods described above.
  • An input/output (I/O) interface is also connected to the bus.
  • the communication unit can be integrated or set up with multiple sub-modules (eg multiple IB network cards) and on the bus link.
  • the following components are connected to the I/O interface: an input portion including a keyboard, a mouse, and the like; an output portion including a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker; a storage portion including a hard disk or the like; The communication part of the network interface card of the LAN card, modem, etc.
  • the communication section performs communication processing via a network such as the Internet.
  • the drive is also connected to the I/O interface as needed.
  • a removable medium such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like is mounted on the drive as needed so that a computer program read therefrom is installed into the storage portion as needed.
  • FIG. 8 is only an optional implementation manner. In some practices, the number and types of components in FIG. 8 may be selected, deleted, added, or replaced according to actual needs; Different function components can also be implemented in separate settings or integrated settings, such as GPU and CPU detachable settings or GPU can be integrated on the CPU, the communication part can be separated, or integrated on the CPU or GPU. and many more. These alternative embodiments are all within the scope of protection disclosed herein.
  • an embodiment of the present disclosure includes a computer program product comprising a computer program tangibly embodied on a machine readable medium, the computer program comprising program code for executing the method illustrated in the flowchart, the program code comprising The instructions corresponding to the steps of the face anti-counterfeiting detection method provided by the embodiment of the present application are executed.
  • the computer program can be downloaded and installed from the network via a communication portion, and/or installed from a removable medium.
  • the embodiment of the present application further provides a computer program, including computer readable code, when the computer readable code is run on a device, the processor in the device executes to implement any of the embodiments of the present application. Instructions for each step in the method.
  • the embodiment of the present application further provides a computer readable storage medium for storing computer readable instructions, when the instructions are executed, performing the operations of the steps in the method of any embodiment of the present application.
  • the methods and systems of the present application may be implemented in a number of ways.
  • the methods and systems of the present application can be implemented in software, hardware, firmware, or any combination of software, hardware, and firmware.
  • the above-described sequence of steps for the method is for illustrative purposes only, and the steps of the method of the present application are not limited to the order described above unless otherwise specifically stated.
  • the present application may also be embodied as a program recorded in a recording medium, the program comprising machine readable instructions for implementing the method according to the present application.
  • the present application also covers a recording medium storing a program for executing the method according to the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Image Analysis (AREA)
  • Collating Specific Patterns (AREA)
  • Image Processing (AREA)

Abstract

本申请实施例公开了一种人脸防伪检测方法和系统、程序和介质，其中，方法包括：通过多目摄像头采集的包括人脸的多个待检测图像，获取所述待检测图像中人脸的深度信息；将获取的人脸的深度信息与预设人脸深度信息进行相符性比较；根据所述相符性比较结果确定所述人脸是否通过防伪检测。本申请实施例使用多目摄像头采集的图像中的深度信息，实现了有效的人脸防伪检测。

Description

人脸防伪检测方法和系统、电子设备、程序和介质
本申请要求在2017年03月16日提交中国专利局、申请号为CN 201710157715.1、发明名称为“人脸防伪检测方法和装置、系统、电子设备”的中国专利申请的优先权，以及在2017年12月07日提交中国专利局、申请号为CN201711289396.6、发明名称为“人脸防伪检测方法和系统、电子设备、程序和介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及计算机视觉技术，尤其是一种人脸防伪检测方法和系统、电子设备、程序和介质。
背景技术
活体检测是指使用计算机视觉的技术，判定在摄像头前的人脸图像是否来自真实的人。活体检测通常有两种实现思路：一是人脸活性检测，二是人脸防伪检测，这两种思路各有侧重。其中，人脸防伪侧重检测人脸是否具有真实性；活性检测侧重检测人脸是否具备活性。具备活性的人脸并不一定是非伪造人脸，同样，非伪造人脸不一定具备活性。
发明内容
本申请实施例提供一种用于进行人脸防伪检测的技术方案。
根据本申请实施例的一个方面，提供的一种人脸防伪检测方法，包括：
通过多目摄像头采集的包括人脸的多个待检测图像，获取所述待检测图像中人脸的深度信息；
将获取的人脸的深度信息与预设人脸深度信息进行相符性比较；
根据所述相符性比较结果确定所述人脸是否通过防伪检测。
可选地，在本申请上述各实施例的方法中，所述多目摄像头包括：一个或多个可见光摄像头，和/或，一个或多个指定摄像头；
所述指定摄像头包括以下任意一种或多种：近红外摄像头，红外摄像头，低照度可见光摄像头，宽动态摄像头。
可选地，在本申请上述各实施例的方法中，所述多目摄像头包括指定摄像头时，所述方法还包括：基于所述指定摄像头采集的待检测图像进行人脸防伪检测；
所述根据所述相符性比较结果确定所述人脸是否通过防伪检测，包括：响应于基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，确定所述人脸通过防伪检测。
可选地，在本申请上述各实施例的方法中，所述多目摄像头包括红外摄像头或近红外摄像头时，基于所述指定摄像头采集的待检测图像进行人脸防伪检测，包括：
根据从所述红外摄像头或所述近红外摄像头采集的待检测图像中是否检测到人脸，进行人脸防伪检测；和/或，根据所述人脸中瞳孔的状态进行人脸防伪检测；
响应于从所述红外摄像头或所述近红外摄像头采集的待检测图像中未检测到人脸、和/或检测到的人脸中瞳孔的状态未呈预设状态，所述指定摄像头采集的待检测图像未通过人脸防伪检测。
可选地，在本申请上述各实施例的方法中，所述多目摄像头中还包括可见光摄像头；
基于所述指定摄像头采集的待检测图像进行人脸防伪检测，还包括：
识别所述可见光摄像头采集的待检测图像中人脸中瞳孔的状态是否呈预设状态；
响应于所述可见光摄像头采集的待检测图像中人脸中瞳孔的状态呈预设状态，所述指定摄像头采集的待检测图像未通过防伪检测。
可选地，在本申请上述各实施例的方法中，所述多目摄像头包括宽动态摄像头时，基于所述指定摄像头采集的待检测图像进行人脸防伪检测，包括：
检测所述宽动态摄像头采集的待检测图像中是否包括摩尔纹，进行人脸防伪检测；
响应于所述宽动态摄像头采集的待检测图像中包括摩尔纹，所述指定摄像头采集的待检测图像未通过人脸防伪检测。
可选地，在本申请上述各实施例的方法中，还包括：
提取所述待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息；
所述根据所述相符性比较结果确定所述人脸是否通过防伪检测，包括：
响应于基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，且提取的特征中未包含伪造人脸线索信息，所述人脸通过防伪检测。
可选地，在本申请上述各实施例的方法中，基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，执行所述提取所述待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息的操作。
可选地，在本申请上述各实施例的方法中，提取的所述特征包括以下一项或任意多项：局部二值模式特征、稀疏编码的柱状图特征、全景图特征、人脸图特征、人脸细节图特征。
可选地，在本申请上述各实施例的方法中，所述伪造人脸线索信息具有可见光条件下的人眼可观测性。
可选地，在本申请上述各实施例的方法中，所述伪造人脸线索信息包括以下任意一项或多项：成像介质的伪造线索信息、成像媒介的伪造线索信息、真实存在的伪造人脸的线索信息。
可选地，在本申请上述各实施例的方法中，所述成像介质的伪造线索信息包括：成像介质的边缘信息、反光信息和/或材质信息；和/或，
所述成像媒介的伪造线索信息包括：显示设备的屏幕边缘、屏幕反光和/或屏幕摩尔纹；和/或，
所述真实存在的伪造人脸的线索信息包括：带面具人脸的特性、模特类人脸的特性、雕塑类人脸的特性。
可选地，在本申请上述各实施例的方法中，所述提取所述待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息，包括：
将所述待检测图像输入神经网络，并经所述神经网络输出用于表示所述待检测图像是否包含至少一伪造人脸线索信息的检测结果，其中，所述神经网络基于包括有伪造人脸线索信息的训练用图像集预先训练完成。
可选地，在本申请上述各实施例的方法中，所述训练用图像集包括：可作为训练用正样本的多张人脸图像和可作为训练用负样本的多张图像；
所述包括有伪造人脸线索信息的训练用图像集的获取方法，包括：
获取可作为训练用正样本的多张人脸图像；
对获取的至少一张人脸图像的至少局部进行用于模拟伪造人脸线索信息的图像处理，以生成至少一张可作为训练用负样本的图像。
可选地，在本申请上述各实施例的方法中，所述神经网络包括：位于所述电子设备中的第一神经网络。
可选地，在本申请上述各实施例的方法中，所述神经网络包括：位于所述服务器中的第二神经网络。
所述方法还包括：
所述电子设备将所述待检测图像发送给服务器；
所述服务器将提取的特征中是否包含伪造人脸线索信息的检测结果发送给所述电子设备。
可选地，在本申请上述各实施例的方法中，所述神经网络还包括：位于电子设备中的第一神经网络；所述第一神经网络的大小小于所述第二神经网络的大小；
所述方法还包括：
将所述待检测图像输入第一神经网络，并经所述第一神经网络输出用于表示所述待检测图像是否包含至少一伪造人脸线索信息的检测结果；
响应于所述待检测图像未包含伪造人脸线索信息的检测结果，执行所述电子设备将所述待检测图像发送给所述服务器的操作。
可选地，在本申请上述各实施例的方法中，响应于所述待检测图像包含伪造人脸线索信息的检测结果，所述根据所述相符性比较结果确定所述人脸是否通过防伪检测，包括：所述电子设备根据所述第一神经网络输出的检测结果确定所述人脸未通过防伪检测。
可选地，在本申请上述各实施例的方法中，还包括：所述服务器将所述第二神经网络输出的检测结果返回给所述电子设备；
所述根据所述相符性比较结果确定所述人脸是否通过防伪检测，包括：所述电子设备根据基于所述指定摄像头采集的待检测图像是否通过人脸防伪检测、所述相符性比较结果是否满足预定要求、以及所述第二神经网络输出的检测结果确定所述待人脸是否通过防伪检测。
根据本申请实施例的另一个方面，提供的一种人脸防伪检测系统，包括：
多目摄像头，用于采集包括人脸的多个待检测图像；
第一获取模块，用于通过多目摄像头采集的包括人脸的多个待检测图像，获取所述待检测图像中人脸的深度信息；
比较模块，用于将获取的人脸的深度信息与预设人脸深度信息进行相符性比较；
确定模块，用于根据所述相符性比较结果确定所述人脸是否通过防伪检测。
可选地，在本申请上述各实施例的系统中，所述多目摄像头包括：一个或多个可见光摄像头，和/或，一个或多个指定摄像头；
所述指定摄像头包括以下任意一种或多种：近红外摄像头，红外摄像头，低照度可见光摄像头，宽动态摄像头。
可选地，在本申请上述各实施例的系统中，所述多目摄像头包括指定摄像头时，所述系统还包括：
第一人脸防伪检测模块，用于基于所述指定摄像头采集的待检测图像进行人脸防伪检测；
所述确定模块用于：响应于基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，确定所述人脸通过防伪检测。
可选地，在本申请上述各实施例的系统中，所述多目摄像头包括红外摄像头或近红外摄像头时，第一人脸防伪检测模块用于：
根据从所述红外摄像头或所述近红外摄像头采集的待检测图像中是否检测到人脸进行人脸防伪检测；和/或，根据所述人脸中瞳孔的状态进行人脸防伪检测；
响应于从所述红外摄像头或所述近红外摄像头采集的待检测图像中未检测到人脸、和/或检测到的人脸中瞳孔的状态未呈预设状态，所述指定摄像头采集的待检测图像未通过人脸防伪检测。
可选地，在本申请上述各实施例的系统中，所述多目摄像头中还包括可见光摄像头；
所述第一人脸防伪检测模块还用于：
识别所述可见光摄像头采集的待检测图像中人脸中瞳孔的状态是否呈预设状态；
响应于所述可见光摄像头采集的待检测图像人脸中瞳孔的状态呈预设状态，所述指定 摄像头采集的待检测图像未通过防伪检测。
可选地，在本申请上述各实施例的系统中，所述多目摄像头包括宽动态摄像头时，所述第一人脸防伪检测模块用于：
检测所述宽动态摄像头采集的待检测图像中是否包括摩尔纹，进行人脸防伪检测；
响应于所述宽动态摄像头采集的待检测图像中包括摩尔纹，所述指定摄像头采集的待检测图像未通过人脸防伪检测。
可选地，在本申请上述各实施例的系统中，还包括：
第二人脸防伪检测模块，用于提取所述待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息；
所述确定模块用于：
响应于基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，且提取的特征中未包含伪造人脸线索信息，确定所述人脸通过防伪检测。
可选地，在本申请上述各实施例的系统中，所述第二人脸防伪检测模块，用于基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，开始执行所述提取所述待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息的操作。
可选地，在本申请上述各实施例的系统中，提取的所述特征包括以下一项或任意多项：局部二值模式特征、稀疏编码的柱状图特征、全景图特征、人脸图特征、人脸细节图特征。
可选地，在本申请上述各实施例的系统中，所述伪造人脸线索信息具有可见光条件下的人眼可观测性。
可选地，在本申请上述各实施例的系统中，所述伪造人脸线索信息包括以下任意一项或多项：成像介质的伪造线索信息、成像媒介的伪造线索信息、真实存在的伪造人脸的线索信息。
可选地，在本申请上述各实施例的系统中，所述成像介质的伪造线索信息包括：成像介质的边缘信息、反光信息和/或材质信息；和/或，
所述成像媒介的伪造线索信息包括：显示设备的屏幕边缘、屏幕反光和/或屏幕摩尔纹；和/或，
所述真实存在的伪造人脸的线索信息包括：带面具人脸的特性、模特类人脸的特性、雕塑类人脸的特性。
可选地，在本申请上述各实施例的系统中，所述第二人脸防伪检测模块包括：神经网络，用于接收所述待检测图像，并输出用于表示所述待检测图像是否包含至少一伪造人脸线索信息的检测结果，其中，所述神经网络基于包括有伪造人脸线索信息的训练用图像集预先训练完成。
可选地，在本申请上述各实施例的系统中，所述训练用图像集包括：可作为训练用正样本的多张人脸图像和可作为训练用负样本的多张图像；
所述系统，还包括：
第二获取模块，用于获取可作为训练用正样本的多张人脸图像；以及对获取的至少一张人脸图像的至少局部进行用于模拟伪造人脸线索信息的图像处理，以生成至少一张可作为训练用负样本的图像。
可选地，在本申请上述各实施例的系统中，所述神经网络包括：位于所述电子设备中的第一神经网络。
可选地，在本申请上述各实施例的系统中，所述神经网络包括：位于所述服务器中的第二神经网络；
所述系统还包括：
第一发送模块，位于所述电子设备中，用于将所述待检测图像发送给服务器；和/或，
第二发送模块，位于所述服务器中，用于将所述第二神经网络输出的、所述提取的特征中是否包含伪造人脸线索信息的检测结果发送给所述电子设备。
可选地，在本申请上述各实施例的系统中，所述神经网络还包括：位于电子设备中的第一神经网络，用于接收所述待检测图像并输出用于表示所述待检测图像是否包含至少一伪造人脸线索信息的检测结果；所述第一神经网络的大小小于所述第二神经网络的大小；
所述第一发送模块，用于响应于所述第一神经网络输出的、所述待检测图像未包含伪造人脸线索信息的检测结果，将所述待检测图像发送给所述服务器。
根据本申请实施例的又一个方面，提供的一种电子设备，包括本申请上述任一实施例的人脸防伪检测系统。
根据本申请实施例的又一个方面，提供的另一种电子设备，包括：
存储器，用于存储可执行指令；以及
处理器，用于与所述存储器通信以执行所述可执行指令从而完成本申请任一实施例所述人脸防伪检测方法的操作。
根据本申请实施例的再一个方面，提供的一种计算机程序，包括计算机可读代码，当所述计算机可读代码在设备上运行时，所述设备中的处理器执行用于实现本申请任一实施例所述方法中各步骤的指令。
根据本申请实施例的再一个方面，提供的一种计算机可读存储介质，用于存储计算机可读取的指令，其特征在于，所述指令被执行时执行本申请任一实施例所述方法中各步骤的操作。
基于本申请上述实施例提供的人脸防伪检测方法和系统、电子设备、程序和介质，通过多目摄像头采集的包括人脸的多个待检测图像，获取待检测图像中人脸图像的深度信息；将获取的人脸的深度信息与预设人脸深度信息进行相符性比较；根据相符性比较结果确定人脸是否通过防伪检测，本申请实施例使用多目摄像头采集的图像中的深度信息，实现了有效的人脸防伪检测。
下面通过附图和实施例，对本申请的技术方案做进一步的详细描述。
附图说明
构成说明书的一部分的附图描述了本申请的实施例，并且连同描述一起用于解释本申请的原理。
参照附图，根据下面的详细描述，可以更加清楚地理解本申请，其中：
图1为本申请人脸防伪检测方法一个实施例的流程图。
图2为本申请实施例中双目摄像头的一个示意图。
图3为本申请人脸防伪检测方法另一个实施例的流程图。
图4为本申请人脸防伪检测方法又一个实施例的流程图。
图5为本申请人脸防伪检测系统一个实施例的结构示意图。
图6为本申请人脸防伪检测系统另一个实施例的结构示意图。
图7为本申请人脸防伪检测系统又一个实施例的结构示意图。
图8为本申请电子设备一个应用实施例的结构示意图。
具体实施方式
现在将参照附图来详细描述本申请的各种示例性实施例。应注意到：除非另外说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本申请的范围。
同时，应当明白，为了便于描述，附图中所示出的各个部分的尺寸并不是按照实际的比例关系绘制的。
以下对至少一个示例性实施例的描述实际上仅仅是说明性的，决不作为对本申请及其应用或使用的任何限制。
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论，但在适当情况下，所述技术、方法和设备应当被视为说明书的一部分。
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步讨论。
本申请实施例可以应用于终端设备、计算机系统、服务器等终端设备，其可与众多其它通用或专用计算系统环境或配置一起操作。适于与终端设备、计算机系统、服务器等终端设备一起使用的众所周知的终端设备、计算系统、环境和/或配置的例子包括但不限于：个人计算机系统、服务器计算机系统、瘦客户机、厚客户机、手持或膝上设备、基于微处理器的系统、机顶盒、可编程消费电子产品、网络个人电脑、小型计算机系统﹑大型计算机系统和包括上述任何系统的分布式云计算技术环境，等等。
终端设备、计算机系统、服务器等终端设备可以在由计算机系统执行的计算机系统可执行指令(诸如程序模块)的一般语境下描述。通常，程序模块可以包括例程、程序、目标程序、组件、逻辑、数据结构等等，它们执行指定的任务或者实现指定的抽象数据类型。计算机系统/服务器可以在分布式云计算环境中实施，分布式云计算环境中，任务是由通过通信网络链接的远程处理设备执行的。在分布式云计算环境中，程序模块可以位于包括存储设备的本地或远程计算系统存储介质上。
图1为本申请人脸防伪检测方法一个实施例的流程图。如图1所示，该实施例的人脸防伪检测方法包括：
102，通过多目摄像头采集的包括人脸的多个待检测图像，获取该待检测图像中人脸的深度信息。
本申请各实施例中的多目摄像头例如可以是双目摄像头、三目摄像头、四目摄像头等，分别表示有几个摄像头。在其中一个可选示例中，多目摄像头例如可以包括但不限于：一个或多个可见光摄像头，和/或，一个或多个指定摄像头。其中的指定摄像头例如可以包括但不限于以下任意一种或多种：近红外摄像头，红外摄像头，低照度可见光摄像头，宽动态摄像头。在本申请实施例的一个应用实例中，可以采用包含近红外摄像头加低照度可见光摄像头的双目摄像头、或者包含近红外摄像头加宽动态可见光摄像头的双目摄像头。如图2所示，为本申请实施例中双目摄像头的一个示意图。
本申请各实施例中，深度信息是指被拍摄者(即：人脸)与多目摄像头的镜头之间的距离，可以通过对多目摄像头中任意两个或以上摄像头参数的标定，可以计算出被拍摄的人脸与镜头之间的距离，即：该待检测图像中人脸的深度信息。其中，摄像头参数例如可以包括：摄像头的内参(焦距，图像中心，畸变系数等)和外参(R(旋转)矩阵，T(平移)矩阵)。
在一个可选示例中，该操作102可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第一获取模块执行。
104，将获取的人脸的深度信息与预设人脸深度信息进行相符性比较。
伪造人脸一般不包含深度信息，例如一般真人的人脸中每个五官到摄像头的深度信息都是不一样的、应该有所差异，可以根据经验设置预设人脸深度信息，例如对大量人脸的深度信息进行统计、并允许一定的偏差范围，获得预设人脸深度信息；但是如果是纸上或者是设备上伪造人脸，五官到摄像头的深度信息几乎是一样的，根据获取的人脸的五官到摄像头的深度信息中是否有差异、以及差异情况是否满足预设人脸深度信息，来判断获取的人脸的深度信息与预设人脸深度信息是否相符。
在一个可选示例中，该操作104可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的比较模块执行。
106，根据相符性比较结果确定上述待检测图像中的人脸是否通过防伪检测。
如果获取的人脸的五官到摄像头的深度信息有差异、且差异情况满足预设人脸深度信息，则确定上述待检测图像中的人脸通过防伪检测。否则，若获取的人脸的五官到摄像头的深度信息无差异、和/或差异情况不满足预设人脸深度信息，确定上述待检测图像中的人脸未通过防伪检测。
在一个可选示例中，该操作106可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的确定模块执行。
基于本申请上述实施例提供的人脸防伪检测方法，通过多目摄像头采集的包括人脸的多个待检测图像，获取待检测图像中人脸的深度信息；将获取的人脸的深度信息与预设人脸深度信息进行相符性比较；根据相符性比较结果确定人脸是否通过防伪检测，本申请实施例使用多目摄像头采集的图像中的深度信息，实现了有效的人脸防伪检测。
本申请人通过研究发现：伪造人脸从维度上可以划分为2D类、2.5D类和3D类伪造人脸。其中：
2D类伪造人脸指的是纸质类材料打印出的人脸图像，该2D类伪造人脸一般不包含深度信息(例如一般真人的人脸中每个五官到摄像头的深度信息都是不一样的，但是如果是纸上或者是设备上伪造人脸，五官到摄像头的深度信息几乎是一样的)，并且还含有纸质人脸的边缘、纸张材质、纸面反光、纸张边缘等伪造人脸线索信息。
2.5D类伪造人脸指的是视频翻拍设备等载体设备承载的人脸图像，该2.5D类伪造人脸一般不包含深度信息、并且还包含视频翻拍设备等载体设备的屏幕摩尔纹、屏幕反光、屏幕边缘等伪造人脸线索信息。
3D类伪造人脸指的是真实存在的伪造人脸，例如面具、模特、雕塑、3D打印等，该3D类伪造人脸无法吸收一些指定摄像头发射的光源、并且同样具备相应的伪造人脸线索信息，例如面具的缝合处、模特的较为抽象或过于光滑的皮肤等伪造线索信息。
在多目摄像头包括指定摄像头时，在本申请人脸防伪检测方法的另一个实施例中，还可以包括：基于指定摄像头采集的待检测图像进行人脸防伪检测。相应地，该实施例中，根据相符性比较结果确定人脸是否通过防伪检测，可以包括：响应于基于指定摄像头采集的待检测图像通过人脸防伪检测、且相符性比较结果满足预定要求，确定待检测图像中的人脸通过防伪检测。
在多目摄像头包括红外摄像头或近红外摄像头时，在本申请各实施例的一个实施方式中，基于指定摄像头采集的待检测图像进行人脸防伪检测，可以包括：
根据从红外摄像头或近红外摄像头采集的待检测图像中是否检测到人脸，进行人脸防伪检测；和/或，根据检测到的人脸中瞳孔的状态进行人脸防伪检测；
响应于从红外摄像头或近红外摄像头采集的待检测图像中未检测到人脸、和/或检测到的人脸中瞳孔的状态未呈预设状态，确定指定摄像头采集的待检测图像未通过人脸防伪检测。
在红外摄像头、近红外摄像头前，一般正常真人的瞳孔会呈现高亮透明的状态，纸质打印人脸、模特和雕塑等伪造人脸的瞳孔均不会出现这种状态；而通过电子设备承载的伪造人脸在近红外摄像头前不会成像(即：屏幕一片黑暗)，可以通过区分瞳孔的状态、以及是否检测到人脸图像来区分红外摄像头、近红外摄像头采集的待检测图像中的人脸是否为伪造人脸。
另外，在本申请各实施例的另一个实施方式中，多目摄像头中还可以包括可见光摄像头。相应地，基于指定摄像头采集的待检测图像进行人脸防伪检测，还可以包括：
识别可见光摄像头采集的待检测图像中人脸中瞳孔的状态是否呈预设状态；
响应于可见光摄像头采集的待检测图像中人脸中瞳孔的状态呈预设状态，确定该待检测图像中的人脸未通过防伪检测，或者指定摄像头采集的待检测图像未通过人脸防伪检测。
基于上述实施例，采用红外摄像头加可见光摄像头组成的双目摄像头进行人脸防伪检测时，可以通过采集到一个真人的近红外照片并使用纸张打印出来进行攻击，因为打印出来的人脸瞳孔是被近红外摄像头拍摄所以会呈现高亮透明状态；这种情况可以通过可见光摄像头辅助进行判断，因为在可见光摄像头前人的瞳孔应呈现正常状态，但是近红外拍摄并打印的人脸瞳孔高亮透明，两个摄像头相辅相成从而达到人脸防伪检测效果。
在本申请上述各实施例的又一个实施方式中，多目摄像头包括宽动态摄像头时，基于指定摄像头采集的待检测图像进行人脸防伪检测，可以包括：
检测宽动态摄像头采集的待检测图像中是否包括摩尔纹，进行人脸防伪检测；
响应于宽动态摄像头采集的待检测图像中包括摩尔纹，确定指定摄像头采集的待检测图像未通过人脸防伪检测。
宽动态摄像头一般会多次曝光，在逆光比较严重的应用场景会有减少光线的影响，从而提高人脸识别与人脸防伪检测的鲁棒性。
基于获取的人脸的深度信息，便可以识别对待检测图像中可能存在的2D类和2.5D类伪造人脸线索信息，从而实现对2D类和2.5D类伪造人脸的检测；通用多目摄像头中的指定摄像头，可以更加有效的甄别来自3D类的伪造人脸和一些2.5D类伪造人脸。例如，多目摄像头中的近红外摄像头拍摄图像中无法检测到人脸则活体检测失败；或者多目摄像头中的宽动态摄像头拍摄图像中出现大量摩尔纹则活体检测失败；在光线较暗的应用场景，多目摄像头中包括低照度摄像头时，可以减少光线的影响从而提高人脸识别与人脸防伪检测的鲁棒性。
在本申请人脸防伪检测方法的又一个实施例中，还可以包括：提取待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息。在其中一个可选示例中，上述伪造人脸线索信息具有可见光条件下的人眼可观测性。相应地，该实施例中，根据相符性比较结果确定人脸是否通过防伪检测，可以包括：根据基于指定摄像头采集的待检测图像是否通过人脸防伪检测、相符性比较结果是否满足预定要求、以及提取的特征中是否包含伪造人脸线索信息，人脸通过防伪检测。响应于基于指定摄像头采集的待检测图像通过人脸防伪检测、且相符性比较结果满足预定要求，且提取的特征中未包含伪造人脸线索信息，确定人脸通过防伪检测。否则，若基于指定摄像头采集的待检测图像未通过人脸防伪检测、和/或相符性比较结果满足预定要求、和/或提取的特征中未包含伪造人脸线索信息，只要出现这三种情况中的任一情况，确定人脸未通过防伪检测。
图3为本申请人脸防伪检测方法一个实施例的流程图。如图3所示，该实施例的人脸防伪检测方法包括：
202，通过多目摄像头采集的包括人脸的多个待检测图像，获取该待检测图像中人脸的深度信息。
在一个可选示例中，该操作202可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第一获取模块执行。
204，将获取的人脸的深度信息与预设人脸深度信息进行相符性比较；以及基于指定摄像头采集的待检测图像进行人脸防伪检测。
其中，可以采用但不限于本申请上述各实施例的方式，实现基于指定摄像头采集的待检测图像进行人脸防伪检测的操作。
在一个可选示例中，该操作204可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的比较模块和第一人脸防伪检测模块执行。
206，响应于基于指定摄像头采集的待检测图像通过人脸防伪检测、且相符性比较结果满足预定要求，提取待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息。
若操作204中，基于指定摄像头采集的待检测图像通过人脸防伪检测、和/或相符性比 较结果不满足预定要求，不执行本实施例的后续流程，或者还可以进一步输出上述待检测图像中人脸未通过防伪检测提示消息。
在一个可选示例中，该操作206可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第二人脸防伪检测模块执行。
208，根据提取的特征中是否包含伪造人脸线索信息的检测结果，确定上述待检测图像中的人脸是否通过防伪检测。
在一个可选示例中，该操作208可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的确定模块执行。
在本申请各实施例的一个可选示例中，本申请各实施例中提取的特征，例如可以包括但不限于以下任意多项：局部二值模式(LBP)特征、稀疏编码的柱状图(HSC)特征、全景图(LARGE)特征、人脸图(SMALL)特征、人脸细节图(TINY)特征。应用中，可以根据可能出现的伪造人脸线索信息对该提取的特征包括的特征项进行更新。
其中，通过LBP特征，可以突出图像中的边缘信息；通过HSC特征，可以更明显的反映图像中的反光与模糊信息；LARGE特征是全图特征，基于LARGE特征，可以提取到图像中最明显的伪造线索(hack)；人脸图(SMALL)是图像中人脸框若干倍大小(例如1.5倍大小)的区域切图，其包含人脸、人脸与背景切合的部分，基于SMALL特征，可以提取到反光、翻拍设备屏幕摩尔纹与模特或者面具的边缘等伪造线索；人脸细节图(TINY)是取人脸框大小的区域切图，包含人脸，基于TINY特征，可以提取到图像PS(基于图像编辑软件photoshop编辑)、翻拍屏幕摩尔纹与模特或者面具的纹理等伪造线索。
在本申请各实施例的一个可选示例中，本申请实施例中的伪造人脸线索信息具有可见光条件下的人眼可观测性，也即，人眼在可见光条件下是可以观测到这些伪造人脸线索信息的。基于伪造人脸线索信息具有的该特性，使得在采用可见光摄像头(如RGB摄像头)采集的静态图像或动态视频实现防伪检测成为可能，避免额外引入指定摄像头，降低硬件成本。伪造人脸线索信息例如可以包括但不限于以下任意一项或多项：成像介质的伪造线索信息、成像媒介的伪造线索信息、真实存在的伪造人脸的线索信息。其中，成像介质的伪造线索信息也称为2D类伪造人脸线索信息，成像媒介的伪造线索信息可以称为2.5D类伪造人脸线索信息，真实存在的伪造人脸的线索信息可以称为3D类伪造人脸线索信息，可以根据可能出现的伪造人脸方式对需要检测的伪造人脸线索信息进行相应更新。通过对这些线索信息的检测，使得电子设备可以“发现”各式各样的真实人脸和伪造人脸之间的边界，在可见光摄像头这样通用的硬件设备条件下实现各种不同类型的防伪检测，抵御“hack”攻击，提高安全性。
其中，成像介质的伪造线索信息例如可以包括但不限于：成像介质的边缘信息、反光信息和/或材质信息。成像媒介的伪造线索信息例如可以包括但不限于：显示设备的屏幕边缘、屏幕反光和/或屏幕摩尔纹。真实存在的伪造人脸的线索信息例如可以包括但不限于：带面具人脸的特性、模特类人脸的特性、雕塑类人脸的特性。
上述实施例中的伪造人脸线索信息从维度上可以划分为2D类、2.5D类和3D类伪造人脸。其中，2D类伪造人脸指的是纸质类材料打印出的人脸图像，该2D类伪造人脸线索信息例如可以包含纸质人脸的边缘、纸张材质、纸面反光、纸张边缘等伪造线索信息。2.5D类伪造人脸指的是视频翻拍设备等载体设备承载的人脸图像，该2.5D类伪造人脸线索信息例如可以包含视频翻拍设备等载体设备的屏幕摩尔纹、屏幕反光、屏幕边缘等伪造线索信息。3D类伪造人脸指的是真实存在的伪造人脸，例如面具、模特、雕塑、3D打印等，该3D类伪造人脸同样具备相应的伪造线索信息，例如面具的缝合处、模特的较为抽象或过于光滑的皮肤等伪造线索信息。
基于该实施例，还通过提取该待检测图像或视频的特征、并检测提取的特征中是否包含伪造人脸线索信息，进一步对待检测图像中的人脸进行防伪检测，根据检测结果确定该 待检测图像或视频是否通过人脸防伪检测，通过多重手段进行人脸防伪检测，进一步提升了人脸防伪检测结果的鲁棒性和准确性，且无需依赖于特殊的多光谱设备，便可以实现在可见光条件下的有效人脸防伪检测，且无需借助于特殊的硬件设备，降低了由此导致的硬件成本，可方便应用于各种人脸检测场景。
在本申请各人脸防伪检测方法实施例的一个可选示例中，分别提取各待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息，可以通过如下方式实现：将待检测图像输入神经网络，并经该神经网络输出用于表示待检测图像是否包含至少一伪造人脸线索信息的检测结果，其中，该神经网络基于包括有伪造人脸线索信息的训练用图像集预先训练完成。
在一个可选示例中，可以通过如下方法获取包括有伪造人脸线索信息的训练用图像集：
获取可作为训练用正样本的多张人脸图像；
对获取的至少一张人脸图像的至少局部进行用于模拟伪造人脸线索信息的图像处理，以生成至少一张可作为训练用负样本的图像。
在本申请各人脸防伪检测方法实施例的一个可选示例中，上述神经网络可以包括：位于电子设备中的第一神经网络，即：由位于电子设备中的第一神经网络执行上述各实施例中分别提取各待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息的操作。
在本申请各人脸防伪检测方法实施例的另一个可选示例中，电子设备将待检测图像发送给服务器。相应地，该实施例中，神经网络可以包括：位于该服务器中的第二神经网络，即：由位于服务器中的第二神经网络执行上述各实施例中分别提取各待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息的操作。该实施例的人脸防伪检测方法还包括：服务器将提取的特征中是否包含伪造人脸线索信息的检测结果发送给电子设备。
另外，在本申请各人脸防伪检测方法实施例的再一个可选示例中，神经网络可以包括：位于电子设备中的第一神经网络和位于服务器中的第二神经网络，其中，第一神经网络的大小小于第二神经网络的大小，例如，可以是第一神经网络在网络层和/或参数数量上小于第二神经网络。
在本申请各实施例中，第一神经网络、第二神经网络，分别可以是一个多层神经网络(即：深度神经网络)，例如多层的卷积神经网络，例如可以是LeNet、AlexNet、GoogLeNet、VGG、ResNet等任意神经网络模型。第一神经网络和第二神经网络可以采用相同类型和结构的神经网络，也可以采用不同类型和结构的神经网络。
图4为本申请人脸防伪检测方法一个实施例的流程图。如图4所示，该实施例的人脸防伪检测方法包括：
302，电子设备通过多目摄像头采集的包括人脸的多个待检测图像，获取该待检测图像中人脸的深度信息。
在一个可选示例中，该操作302可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第一获取模块执行。
304，电子设备将获取的人脸的深度信息与预设人脸深度信息进行相符性比较；以及基于指定摄像头采集的待检测图像进行人脸防伪检测。
其中，可以采用但不限于本申请上述各实施例的方式，实现基于指定摄像头采集的待检测图像进行人脸防伪检测的操作。
在一个可选示例中，该操作304可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的比较模块和第一人脸防伪检测模块执行。
306，响应于基于指定摄像头采集的待检测图像通过人脸防伪检测、且相符性比较结果满足预定要求，电子设备将待检测图像输入第一神经网络，并经第一神经网络输出用于表示待检测图像是否包含至少一伪造人脸线索信息的检测结果。
若操作304中，基于指定摄像头采集的待检测图像通过人脸防伪检测、和/或相符性比 较结果不满足预定要求，不执行本实施例的后续流程，或者还可以进一步输出上述待检测图像中人脸未通过防伪检测提示消息。
其中的伪造人脸线索信息具有可见光条件下的人眼可观测性。第一神经网络基于包括有伪造人脸线索信息的训练用图像集预先训练完成。
示例性地，在本申请各实施例中提取的各项特征中包含的伪造人脸线索，可以预先通过训练第一神经网络，被第一神经网络学习到，之后任何包含这些伪造人脸线索信息的图像输入第一神经网络后均会被检测出来，就可以判断为伪造人脸图像，否则为真实人脸图像。
在一个可选示例中，该操作306可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第一神经网络执行。
308，响应于第一神经网络输出待检测图像未包含伪造人脸线索信息的检测结果，电子设备将该待检测图像发送给服务器。
若操作306中，第一神经网络输出待检测图像包含伪造人脸线索信息的检测结果，电子设备可以输出上述待检测图像中的人脸未通过防伪检测的提示消息，不执行本实施例的后续流程。
在一个可选示例中，该操作308可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第一发送模块执行。
310，服务器将待检测图像输入第二神经网络，并经第二神经网络输出用于表示待检测图像是否包含至少一伪造人脸线索信息的检测结果，并将该检测结果返回电子设备。
其中的伪造人脸线索信息具有可见光条件下的人眼可观测性。第二神经网络基于包括有伪造人脸线索信息的训练用图像集预先训练完成。
示例性地，在本申请各实施例中提取的各项特征中包含的伪造人脸线索，可以预先通过训练第二神经网络，被第二神经网络学习到，之后任何包含这些伪造人脸线索信息的图像输入第二神经网络后均会被检测出来，就可以判断为伪造人脸图像，否则为真实人脸图像。
在一个可选示例中，该操作310可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的第二神经网络和第二发送模块执行。
312，电子设备根据服务器返回的第二神经网络输出的检测结果，确定上述待检测图像中的人脸是否通过防伪检测。
若第二神经网络输出的检测结果为待检测图像未包含任何伪造人脸线索信息的检测结果，则确定上述待检测图像中的人脸通过防伪检测。否则，若第二神经网络输出的检测结果为待检测图像未包含任一伪造人脸线索信息的检测结果，则确定上述待检测图像中的人脸未通过防伪检测。
在一个可选示例中，该操作312可以由处理器调用存储器存储的相应指令执行，也可以由被处理器运行的确定模块执行。
在其中一个可选示例中，本申请上述各实施例的电子设备例如可以是手机终端或者平板电脑等。由于终端设备的硬件性能通常有限，进行更多特征提取和检测的神经网络将需要更多的计算和存储资源，而终端设备的计算、存储资源相对于云端服务器比较有限，为了节省终端设备侧神经网络占用的计算和存储资源、又能保证实现有效的人脸防伪检测，本申请实施例中，在终端设备中设置较小(网络较浅和/或网络参数较少)的第一神经网络，融合较少特征，例如仅从待检测图像中提取LBP特征与人脸SMALL特征、来进行相应的伪造人脸线索信息的检测，在硬件性能较好的云端服务器设置较大(网络较深和/或网络参数较多)的第二神经网络，融合全面的防伪线索特征，使得该第二神经网络更加健壮、检测性能更好，除了从待检测图像中提取LBP特征与人脸SMALL特征，还可以提取HSC特征、LARGE特征、TINY特征等其他可能包含伪造人脸线索信息的特征，在第一神经网 络采集到的视频中人脸通过人脸防伪检测时，再通过第二神经网络进行更加精确、全面的人脸防伪检测，提高了检测结果的准确性；在第一神经网络采集到的视频中人脸未通过人脸防伪检测时，便无需通过第二神经网络进行人脸防伪检测，提升了人脸防伪检测的效率。
本申请实施例提供的任一种人脸防伪检测方法可以由任意适当的具有数据处理能力的设备执行，包括但不限于：电子设备和服务器等。或者，本申请实施例提供的任一种人脸防伪检测方法可以由处理器执行，如处理器通过调用存储器存储的相应指令来执行本申请实施例提及的任一种人脸防伪检测方法。下文不再赘述。
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于一计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
图5为本申请人脸防伪检测系统一个实施例的结构示意图。该实施例的人脸防伪检系统可用于实现本申请上述各人脸防伪检方法实施例。如图5所示，该实施例的人脸防伪检测系统包括：多目摄像头，第一获取模块，比较模块和确定模块。其中：
多目摄像头，用于采集包括人脸的多个待检测图像。本申请各实施例中的多目摄像头例如可以是双目摄像头、三目摄像头、四目摄像头等。在其中一个可选示例中，多目摄像头例如可以包括但不限于：一个或多个可见光摄像头，和/或，一个或多个指定摄像头。其中的指定摄像头例如可以包括但不限于以下任意一种或多种：近红外摄像头，红外摄像头，低照度可见光摄像头，宽动态摄像头。
第一获取模块，用于通过多目摄像头采集的包括人脸的多个待检测图像，获取待检测图像中人脸的深度信息。
比较模块，用于将获取的人脸的深度信息与预设人脸深度信息进行相符性比较。
确定模块，用于根据相符性比较结果确定人脸是否通过防伪检测。
基于本申请上述实施例提供的人脸防伪检测系统，通过多目摄像头采集的包括人脸的多个待检测图像，获取待检测图像中人脸的深度信息；将获取的人脸的深度信息与预设人脸深度信息进行相符性比较；根据相符性比较结果确定人脸是否通过防伪检测，本申请实施例使用多目摄像头采集的图像中的深度信息，实现了有效的人脸防伪检测。
图6为本申请人脸防伪检测系统另一个实施例的结构示意图。如图6所示，在上述实施例的多目摄像头包括指定摄像头时，该实施例的人脸防伪检测系统还可以包括：第一人脸防伪检测模块，用于基于指定摄像头采集的待检测图像进行人脸防伪检测。相应地，该实施例中，确定模块用于响应于基于指定摄像头采集的待检测图像通过人脸防伪检测、且相符性比较结果满足预定要求，确定上述待检测图像中的人脸通过防伪检测。
在其中一个可选示例中，多目摄像头包括红外摄像头或近红外摄像头时，第一人脸防伪检测模块可用于：根据从红外摄像头或近红外摄像头采集的待检测图像中是否检测到人脸，进行人脸防伪检测；和/或，根据人脸中瞳孔的状态进行人脸防伪检测。响应于从红外摄像头或近红外摄像头采集的待检测图像中未检测到人脸、和/或检测到的人脸中瞳孔的状态未呈预设状态，确定指定摄像头采集的待检测图像未通过人脸防伪检测。
在另一个可选示例中，多目摄像头中还包括可见光摄像头。相应地，该实施例中，第一人脸防伪检测模块还用于：识别可见光摄像头采集的待检测图像中瞳孔的状态是否呈预设状态。响应于可见光摄像头采集的待检测图像中瞳孔的状态呈预设状态，确定该待检测图像中的人脸未通过防伪检测、或者指定摄像头采集的待检测图像未通过防伪检测。
在又一个可选示例中，多目摄像头包括宽动态摄像头时，第一人脸防伪检测模块用于：检测宽动态摄像头采集的待检测图像中是否包括摩尔纹，进行人脸防伪检测。响应于宽动态摄像头采集的待检测图像中包括摩尔纹，指定摄像头采集的待检测图像未通过人脸防伪检测。
另外，再参见图6，上述各实施例的人脸防伪检测系统还可以选择性地包括：第二人脸防伪检测模块，用于提取待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息。相应地，该实施例中，确定模块用于响应于基于指定摄像头采集的待检测图像通过人脸防伪检测、且相符性比较结果满足预定要求，且提取的特征中未包含伪造人脸线索信息，确定待检测图像中的人脸通过防伪检测。
在其中一个可选示例中，第二人脸防伪检测模块，用于基于指定摄像头采集的待检测图像通过人脸防伪检测、且相符性比较结果满足预定要求，开始执行提取待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息的操作。
在本申请各实施例的一个可选示例中，本申请各实施例中提取的特征，例如可以包括但不限于以下任意多项：LBP特征、HSC特征、LARGE特征、SMALL特征、TINY特征。在一些应用中，可以根据可能出现的伪造人脸线索信息对该提取的特征包括的特征项进行更新。在本申请各实施例的一个可选示例中，本申请各实施例中的伪造人脸线索信息具有可见光条件下的人眼可观测性。伪造人脸线索信息例如可以包括但不限于以下任意一项或多项：成像介质的伪造线索信息、成像媒介的伪造线索信息、真实存在的伪造人脸的线索信息。其中，成像介质的伪造线索信息例如可以包括但不限于：成像介质的边缘信息、反光信息和/或材质信息。成像媒介的伪造线索信息例如可以包括但不限于：显示设备的屏幕边缘、屏幕反光和/或屏幕摩尔纹。真实存在的伪造人脸的线索信息例如可以包括但不限于：带面具人脸的特性、模特类人脸的特性、雕塑类人脸的特性。
在本申请各实施例的一个可选示例中，第二人脸防伪检测模块包括：神经网络，用于接收待检测图像，并输出用于表示待检测图像是否包含至少一伪造人脸线索信息的检测结果，其中，该神经网络基于包括有伪造人脸线索信息的训练用图像集预先训练完成。其中，训练用图像集可以包括：可作为训练用正样本的多张人脸图像和可作为训练用负样本的多张图像；
另外，上述各实施例的人脸防伪检测系统还可以选择性地包括：第二获取模块，用于获取可作为训练用正样本的多张人脸图像；以及对获取的至少一张人脸图像的至少局部进行用于模拟伪造人脸线索信息的图像处理，以生成至少一张可作为训练用负样本的图像。
在其中一个实施方式中，上述神经网络包括位于电子设备中的第一神经网络。
在另一个实施方式中，上述神经网络包括位于服务器中的第二神经网络。相应地，该实施例的人脸防伪检测系统还可以包括：第一发送模块和/或第二发送模块。其中：
第一发送模块，位于电子设备中，用于将待检测图像发送给服务器；
第二发送模块，位于服务器中，用于将第二神经网络输出的、提取的特征中是否包含伪造人脸线索信息的检测结果发送给电子设备。
如图7所示，为本申请人脸防伪检测系统在该另一个实施方式下的一个结构示意图。
另外，再参见图7，上述实施例的人脸防伪检测系统中，神经网络还包括：位于电子设备中的第一神经网络，用于接收待检测图像并输出用于表示待检测图像是否包含至少一伪造人脸线索信息的检测结果。该第一神经网络的大小小于第二神经网络的大小。
相应地，该实施例中，第一发送模块用于响应于第一神经网络输出的、待检测图像未包含伪造人脸线索信息的检测结果，将待检测图像发送给服务器。
另外，本申请实施例还提供了一种电子设备，其可以包括如上任一实施例的人脸防伪检测系统。例如，该电子设备例如可以是电子设备或者服务器等设备。
另外，本申请实施例提供的另一种电子设备，包括：
存储器，用于存储可执行指令；以及
处理器，用于与所述存储器通信以执行所述可执行指令从而完成本申请上述任一实施例人脸防伪检测方法的操作。
图8为本申请电子设备一个应用实施例的结构示意图。下面参考图8，其示出了适于 用来实现本申请实施例的电子设备或服务器的电子设备的结构示意图。如图8所示，该电子设备包括一个或多个处理器、通信部等，所述一个或多个处理器例如：一个或多个中央处理单元(CPU)，和/或一个或多个图像处理器(GPU)等，处理器可以根据存储在只读存储器(ROM)中的可执行指令或者从存储部分加载到随机访问存储器(RAM)中的可执行指令而执行各种适当的动作和处理。通信部可包括但不限于网卡，所述网卡可包括但不限于IB(Infiniband)网卡，处理器可与只读存储器和/或随机访问存储器中通信以执行可执行指令，通过总线与通信部相连、并经通信部与其他目标设备通信，从而完成本申请实施例提供的任一方法对应的操作，例如，通过多目摄像头采集的包括人脸的多个待检测图像，获取所述待检测图像中人脸图像的深度信息；将获取的人脸的深度信息与预设人脸深度信息进行相符性比较；根据所述相符性比较结果确定所述人脸是否通过防伪检测。
此外，在RAM中，还可存储有装置操作所需的各种程序和数据。CPU、ROM以及RAM通过总线彼此相连。在有RAM的情况下，ROM为可选模块。RAM存储可执行指令，或在运行时向ROM中写入可执行指令，可执行指令使处理器执行本申请上述任一方法对应的操作。输入/输出(I/O)接口也连接至总线。通信部可以集成设置，也可以设置为具有多个子模块(例如多个IB网卡)，并在总线链接上。
以下部件连接至I/O接口：包括键盘、鼠标等的输入部分；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分；包括硬盘等的存储部分；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分。通信部分经由诸如因特网的网络执行通信处理。驱动器也根据需要连接至I/O接口。可拆卸介质，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器上，以便于从其上读出的计算机程序根据需要被安装入存储部分。
需要说明的，如图8所示的架构仅为一种可选实现方式，在一些实践过程中，可根据实际需要对上述图8的部件数量和类型进行选择、删减、增加或替换；在不同功能部件设置上，也可采用分离设置或集成设置等实现方式，例如GPU和CPU可分离设置或者可将GPU集成在CPU上，通信部可分离设置，也可集成设置在CPU或GPU上，等等。这些可替换的实施方式均落入本申请公开的保护范围。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括有形地包含在机器可读介质上的计算机程序，计算机程序包含用于执行流程图所示的方法的程序代码，程序代码可包括对应执行本申请实施例提供的人脸防伪检测方法步骤对应的指令。在这样的实施例中，该计算机程序可以通过通信部分从网络上被下载和安装，和/或从可拆卸介质被安装。在该计算机程序被CPU执行时，执行本申请的方法中限定的上述功能。
另外，本申请实施例还提供了一种计算机程序，包括计算机可读代码，当所述计算机可读代码在设备上运行时，所述设备中的处理器执行用于实现本申请任一实施例所述方法中各步骤的指令。
另外，本申请实施例还提供了一种计算机可读存储介质，用于存储计算机可读取的指令，所述指令被执行时执行本申请任一实施例所述方法中各步骤的操作。
本说明书中各个实施例均采用递进的方式描述，每个实施例重点说明的都是与其它实施例的不同之处，各个实施例之间相同或相似的部分相互参见即可。对于系统实施例而言，由于其与方法实施例基本对应，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
可能以许多方式来实现本申请的方法和系统。例如，可通过软件、硬件、固件或者软件、硬件、固件的任何组合来实现本申请的方法和系统。用于所述方法的步骤的上述顺序仅是为了进行说明，本申请的方法的步骤不限于以上描述的顺序，除非以其它方式特别说明。此外，在一些实施例中，还可将本申请实施为记录在记录介质中的程序，这些程序包 括用于实现根据本申请的方法的机器可读指令。因而，本申请还覆盖存储用于执行根据本申请的方法的程序的记录介质。
本申请的描述是为了示例和描述起见而给出的，而并不是无遗漏的或者将本申请限于所公开的形式。很多修改和变化对于本领域的普通技术人员而言是显然的。选择和描述实施例是为了更好说明本申请的原理和实际应用，并且使本领域的普通技术人员能够理解本申请从而设计适于指定用途的带有各种修改的各种实施例。

Claims (40)

  1. 一种人脸防伪检测方法，其特征在于，包括：
    通过多目摄像头采集的包括人脸的多个待检测图像，获取所述待检测图像中人脸的深度信息；
    将获取的人脸的深度信息与预设人脸深度信息进行相符性比较；
    根据所述相符性比较结果确定所述人脸是否通过防伪检测。
  2. 根据权利要求1所述的方法，其特征在于，所述多目摄像头包括：一个或多个可见光摄像头，和/或，一个或多个指定摄像头；
    所述指定摄像头包括以下任意一种或多种：近红外摄像头，红外摄像头，低照度可见光摄像头，宽动态摄像头。
  3. 根据权利要求2所述的方法，其特征在于，所述多目摄像头包括指定摄像头时，所述方法还包括：基于所述指定摄像头采集的待检测图像进行人脸防伪检测；
    所述根据所述相符性比较结果确定所述人脸是否通过防伪检测，包括：响应于基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，确定所述人脸通过防伪检测。
  4. 根据权利要求3所述的方法，其特征在于，所述多目摄像头包括红外摄像头或近红外摄像头时，基于所述指定摄像头采集的待检测图像进行人脸防伪检测，包括：
    根据从所述红外摄像头或所述近红外摄像头采集的待检测图像中是否检测到人脸，进行人脸防伪检测；和/或，根据所述人脸中瞳孔的状态进行人脸防伪检测；
    响应于从所述红外摄像头或所述近红外摄像头采集的待检测图像中未检测到人脸、和/或检测到的人脸中瞳孔的状态未呈预设状态，所述指定摄像头采集的待检测图像未通过人脸防伪检测。
  5. 根据权利要求4所述的方法，其特征在于，所述多目摄像头中还包括可见光摄像头；
    基于所述指定摄像头采集的待检测图像进行人脸防伪检测，还包括：
    识别所述可见光摄像头采集的待检测图像中人脸中瞳孔的状态是否呈预设状态；
    响应于所述可见光摄像头采集的待检测图像中人脸中瞳孔的状态呈预设状态，所述指定摄像头采集的待检测图像未通过防伪检测。
  6. 根据权利要求3或4所述的方法，其特征在于，所述多目摄像头包括宽动态摄像头时，基于所述指定摄像头采集的待检测图像进行人脸防伪检测，包括：
    检测所述宽动态摄像头采集的待检测图像中是否包括摩尔纹，进行人脸防伪检测；
    响应于所述宽动态摄像头采集的待检测图像中包括摩尔纹，所述指定摄像头采集的待检测图像未通过人脸防伪检测。
  7. 根据权利要求3-6任一所述的方法，其特征在于，还包括：
    提取所述待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息；
    所述根据所述相符性比较结果确定所述人脸是否通过防伪检测，包括：
    响应于基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，且提取的特征中未包含伪造人脸线索信息，所述人脸通过防伪检测。
  8. 根据权利要求7所述的方法，其特征在于，基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，执行所述提取所述待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息的操作。
  9. 根据权利要求7或8所述的方法，其特征在于，提取的所述特征包括以下一项或任意多项：局部二值模式特征、稀疏编码的柱状图特征、全景图特征、人脸图特征、人脸细节图特征。
  10. 根据权利要求7-9任一所述的方法，其特征在于，所述伪造人脸线索信息具有可 见光条件下的人眼可观测性。
  11. 根据权利要求7-10任一所述的方法，其特征在于，所述伪造人脸线索信息包括以下任意一项或多项：成像介质的伪造线索信息、成像媒介的伪造线索信息、真实存在的伪造人脸的线索信息。
  12. 根据权利要求11所述的方法，其特征在于，所述成像介质的伪造线索信息包括：成像介质的边缘信息、反光信息和/或材质信息；和/或，
    所述成像媒介的伪造线索信息包括：显示设备的屏幕边缘、屏幕反光和/或屏幕摩尔纹；和/或，
    所述真实存在的伪造人脸的线索信息包括：带面具人脸的特性、模特类人脸的特性、雕塑类人脸的特性。
  13. 根据权利要求7-12任一所述的方法，其特征在于，所述提取所述待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息，包括：
    将所述待检测图像输入神经网络，并经所述神经网络输出用于表示所述待检测图像是否包含至少一伪造人脸线索信息的检测结果，其中，所述神经网络基于包括有伪造人脸线索信息的训练用图像集预先训练完成。
  14. 根据权利要求13所述的方法，其特征在于，所述训练用图像集包括：可作为训练用正样本的多张人脸图像和可作为训练用负样本的多张图像；
    所述包括有伪造人脸线索信息的训练用图像集的获取方法，包括：
    获取可作为训练用正样本的多张人脸图像；
    对获取的至少一张人脸图像的至少局部进行用于模拟伪造人脸线索信息的图像处理，以生成至少一张可作为训练用负样本的图像。
  15. 根据权利要求13或14所述的方法，其特征在于，所述神经网络包括：位于所述电子设备中的第一神经网络。
  16. 根据权利要求13或14所述的方法，其特征在于，所述神经网络包括：位于所述服务器中的第二神经网络。
    所述方法还包括：
    所述电子设备将所述待检测图像发送给服务器；
    所述服务器将提取的特征中是否包含伪造人脸线索信息的检测结果发送给所述电子设备。
  17. 根据权利要求16所述的方法，其特征在于，所述神经网络还包括：位于电子设备中的第一神经网络；所述第一神经网络的大小小于所述第二神经网络的大小；
    所述方法还包括：
    将所述待检测图像输入第一神经网络，并经所述第一神经网络输出用于表示所述待检测图像是否包含至少一伪造人脸线索信息的检测结果；
    响应于所述待检测图像未包含伪造人脸线索信息的检测结果，执行所述电子设备将所述待检测图像发送给所述服务器的操作。
  18. 根据权利要求17所述的方法，其特征在于，响应于所述待检测图像包含伪造人脸线索信息的检测结果，所述根据所述相符性比较结果确定所述人脸是否通过防伪检测，包括：所述电子设备根据所述第一神经网络输出的检测结果确定所述人脸未通过防伪检测。
  19. 根据权利要求17所述的方法，其特征在于，还包括：所述服务器将所述第二神经网络输出的检测结果返回给所述电子设备；
    所述根据所述相符性比较结果确定所述人脸是否通过防伪检测，包括：所述电子设备根据基于所述指定摄像头采集的待检测图像是否通过人脸防伪检测、所述相符性比较结果是否满足预定要求、以及所述第二神经网络输出的检测结果确定所述待人脸是否通过防伪检测。
  20. 一种人脸防伪检测系统，其特征在于，包括：
    多目摄像头，用于采集包括人脸的多个待检测图像；
    第一获取模块，用于通过多目摄像头采集的包括人脸的多个待检测图像，获取所述待检测图像中人脸的深度信息；
    比较模块，用于将获取的人脸的深度信息与预设人脸深度信息进行相符性比较；
    确定模块，用于根据所述相符性比较结果确定所述人脸是否通过防伪检测。
  21. 根据权利要求20所述的系统，其特征在于，所述多目摄像头包括：一个或多个可见光摄像头，和/或，一个或多个指定摄像头；
    所述指定摄像头包括以下任意一种或多种：近红外摄像头，红外摄像头，低照度可见光摄像头，宽动态摄像头。
  22. 根据权利要求21所述的系统，其特征在于，所述多目摄像头包括指定摄像头时，所述系统还包括：
    第一人脸防伪检测模块，用于基于所述指定摄像头采集的待检测图像进行人脸防伪检测；
    所述确定模块用于：响应于基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，确定所述人脸通过防伪检测。
  23. 根据权利要求22所述的系统，其特征在于，所述多目摄像头包括红外摄像头或近红外摄像头时，第一人脸防伪检测模块用于：
    根据从所述红外摄像头或所述近红外摄像头采集的待检测图像中是否检测到人脸，进行人脸防伪检测；和/或，根据所述人脸中瞳孔的状态进行人脸防伪检测；
    响应于从所述红外摄像头或所述近红外摄像头采集的待检测图像中未检测到人脸、和/或检测到的人脸中瞳孔的状态未呈预设状态，所述指定摄像头采集的待检测图像未通过人脸防伪检测。
  24. 根据权利要求23所述的系统，其特征在于，所述多目摄像头中还包括可见光摄像头；
    所述第一人脸防伪检测模块还用于：
    识别所述可见光摄像头采集的待检测图像中人脸中瞳孔的状态是否呈预设状态；
    响应于所述可见光摄像头采集的待检测图像中人脸中瞳孔的状态呈预设状态，所述指定摄像头采集的待检测图像未通过防伪检测。
  25. 根据权利要求22或23所述的系统，其特征在于，所述多目摄像头包括宽动态摄像头时，所述第一人脸防伪检测模块用于：检测所述宽动态摄像头采集的待检测图像中是否包括摩尔纹，进行人脸防伪检测；
    响应于所述宽动态摄像头采集的待检测图像中包括摩尔纹，所述指定摄像头采集的待检测图像未通过人脸防伪检测。
  26. 根据权利要求22-25任一所述的系统，其特征在于，还包括：
    第二人脸防伪检测模块，用于提取所述待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息；
    所述确定模块用于：响应于基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，且提取的特征中未包含伪造人脸线索信息，确定所述人脸通过防伪检测。
  27. 根据权利要求26所述的系统，其特征在于，所述第二人脸防伪检测模块，用于基于所述指定摄像头采集的待检测图像通过人脸防伪检测、且所述相符性比较结果满足预定要求，开始执行所述提取所述待检测图像的特征、并检测提取的特征中是否包含伪造人脸线索信息的操作。
  28. 根据权利要求26或27所述的系统，其特征在于，提取的所述特征包括以下一项 或任意多项：局部二值模式特征、稀疏编码的柱状图特征、全景图特征、人脸图特征、人脸细节图特征。
  29. 根据权利要求26-28任一所述的系统，其特征在于，所述伪造人脸线索信息具有可见光条件下的人眼可观测性。
  30. 根据权利要求26-29任一所述的系统，其特征在于，所述伪造人脸线索信息包括以下任意一项或多项：成像介质的伪造线索信息、成像媒介的伪造线索信息、真实存在的伪造人脸的线索信息。
  31. 根据权利要求30所述的系统，其特征在于，所述成像介质的伪造线索信息包括：成像介质的边缘信息、反光信息和/或材质信息；和/或，
    所述成像媒介的伪造线索信息包括：显示设备的屏幕边缘、屏幕反光和/或屏幕摩尔纹；和/或，
    所述真实存在的伪造人脸的线索信息包括：带面具人脸的特性、模特类人脸的特性、雕塑类人脸的特性。
  32. 根据权利要求26-31任一所述的系统，其特征在于，所述第二人脸防伪检测模块包括：神经网络，用于接收所述待检测图像，并输出用于表示所述待检测图像是否包含至少一伪造人脸线索信息的检测结果，其中，所述神经网络基于包括有伪造人脸线索信息的训练用图像集预先训练完成。
  33. 根据权利要求32所述的系统，其特征在于，所述训练用图像集包括：可作为训练用正样本的多张人脸图像和可作为训练用负样本的多张图像；
    所述系统，还包括：
    第二获取模块，用于获取可作为训练用正样本的多张人脸图像；以及对获取的至少一张人脸图像的至少局部进行用于模拟伪造人脸线索信息的图像处理，以生成至少一张可作为训练用负样本的图像。
  34. 根据权利要求32或33所述的系统，其特征在于，所述神经网络包括：位于所述电子设备中的第一神经网络。
  35. 根据权利要求32或33所述的系统，其特征在于，所述神经网络包括：位于所述服务器中的第二神经网络；
    所述系统还包括：
    第一发送模块，位于所述电子设备中，用于将所述待检测图像发送给服务器；和/或，
    第二发送模块，位于所述服务器中，用于将所述第二神经网络输出的、所述提取的特征中是否包含伪造人脸线索信息的检测结果发送给所述电子设备。
  36. 根据权利要求35所述的系统，其特征在于，所述神经网络还包括：位于电子设备中的第一神经网络，用于接收所述待检测图像并输出用于表示所述待检测图像是否包含至少一伪造人脸线索信息的检测结果；所述第一神经网络的大小小于所述第二神经网络的大小；
    所述第一发送模块，用于响应于所述第一神经网络输出的、所述待检测图像未包含伪造人脸线索信息的检测结果，将所述待检测图像发送给所述服务器。
  37. 一种电子设备，其特征在于，包括权利要求20-36任一所述的人脸防伪检测系统。
  38. 一种电子设备，其特征在于，包括：
    存储器，用于存储可执行指令；以及
    处理器，用于与所述存储器通信以执行所述可执行指令从而完成权利要求1-19任一所述方法的操作。
  39. 一种计算机程序，包括计算机可读代码，其特征在于，当所述计算机可读代码在设备上运行时，所述设备中的处理器执行用于实现权利要求1-19任一所述方法中各步骤的指令。
  40. 一种计算机可读存储介质，用于存储计算机可读取的指令，其特征在于，所述指令被执行时执行权利要求1-19任一所述方法中各步骤的操作。
PCT/CN2018/079273 2017-03-16 2018-03-16 人脸防伪检测方法和系统、电子设备、程序和介质 Ceased WO2018166525A1 (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN201710157715 2017-03-16
CN201710157715.1 2017-03-16
CN201711289396.6 2017-12-07
CN201711289396.6A CN108229331A (zh) 2017-03-16 2017-12-07 人脸防伪检测方法和系统、电子设备、程序和介质

Publications (1)

Publication Number Publication Date
WO2018166525A1 true WO2018166525A1 (zh) 2018-09-20

Family

ID=62653294

Family Applications (3)

Application Number Title Priority Date Filing Date
PCT/CN2018/079247 Ceased WO2018166515A1 (zh) 2017-03-16 2018-03-16 人脸防伪检测方法和系统、电子设备、程序和介质
PCT/CN2018/079273 Ceased WO2018166525A1 (zh) 2017-03-16 2018-03-16 人脸防伪检测方法和系统、电子设备、程序和介质
PCT/CN2018/079267 Ceased WO2018166524A1 (zh) 2017-03-16 2018-03-16 人脸检测方法和系统、电子设备、程序和介质

Family Applications Before (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/079247 Ceased WO2018166515A1 (zh) 2017-03-16 2018-03-16 人脸防伪检测方法和系统、电子设备、程序和介质

Family Applications After (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/079267 Ceased WO2018166524A1 (zh) 2017-03-16 2018-03-16 人脸检测方法和系统、电子设备、程序和介质

Country Status (3)

Country Link
US (2) US11080517B2 (zh)
CN (5) CN108229325A (zh)
WO (3) WO2018166515A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112580621A (zh) * 2020-12-24 2021-03-30 成都新希望金融信息有限公司 身份证翻拍识别方法、装置、电子设备及存储介质
CN112733760A (zh) * 2021-01-15 2021-04-30 上海明略人工智能(集团)有限公司 人脸防伪检测方法及系统

Families Citing this family (58)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10635894B1 (en) * 2016-10-13 2020-04-28 T Stamp Inc. Systems and methods for passive-subject liveness verification in digital media
CN108229325A (zh) * 2017-03-16 2018-06-29 北京市商汤科技开发有限公司 人脸检测方法和系统、电子设备、程序和介质
US11093771B1 (en) 2018-05-04 2021-08-17 T Stamp Inc. Systems and methods for liveness-verified, biometric-based encryption
US11496315B1 (en) 2018-05-08 2022-11-08 T Stamp Inc. Systems and methods for enhanced hash transforms
CN109034059B (zh) * 2018-07-25 2023-06-06 深圳市中悦科技有限公司 静默式人脸活体检测方法、装置、存储介质及处理器
CN110163053B (zh) * 2018-08-02 2021-07-13 腾讯科技（深圳）有限公司 生成人脸识别的负样本的方法、装置及计算机设备
CN109325413A (zh) * 2018-08-17 2019-02-12 深圳市中电数通智慧安全科技股份有限公司 一种人脸识别方法、装置及终端
US11036789B2 (en) * 2018-09-10 2021-06-15 Algoface, Inc. Computer vision neural network system
CN111046703B (zh) * 2018-10-12 2023-04-18 杭州海康威视数字技术股份有限公司 人脸防伪检测方法、装置及多目相机
KR102140340B1 (ko) * 2018-10-18 2020-07-31 엔에이치엔 주식회사 컨볼루션 뉴럴 네트워크를 통해 이미지 위변조를 탐지하는 시스템 및 이를 이용하여 무보정 탐지 서비스를 제공하는 방법
CN111291586B (zh) * 2018-12-06 2024-05-24 北京市商汤科技开发有限公司 活体检测方法、装置、电子设备及计算机可读存储介质
CN109670430A (zh) * 2018-12-11 2019-04-23 浙江大学 一种基于深度学习的多分类器融合的人脸活体识别方法
CN111488756B (zh) 2019-01-25 2023-10-03 杭州海康威视数字技术股份有限公司 基于面部识别的活体检测的方法、电子设备和存储介质
WO2020159437A1 (en) * 2019-01-29 2020-08-06 Agency For Science, Technology And Research Method and system for face liveness detection
CN109828668A (zh) * 2019-01-30 2019-05-31 维沃移动通信有限公司 一种显示控制方法及电子设备
CN109858471A (zh) * 2019-04-03 2019-06-07 深圳市华付信息技术有限公司 基于图像质量的活体检测方法、装置及计算机设备
US11301586B1 (en) 2019-04-05 2022-04-12 T Stamp Inc. Systems and processes for lossy biometric representations
CN111783505B (zh) * 2019-05-10 2025-01-03 北京京东尚科信息技术有限公司 伪造人脸的识别方法、装置和计算机可读存储介质
CN110245612A (zh) 2019-06-14 2019-09-17 百度在线网络技术（北京）有限公司 人脸图像的检测方法和装置
CN110248100B (zh) * 2019-07-18 2021-02-19 联想(北京)有限公司 一种拍摄方法、装置及存储介质
CN110414437A (zh) * 2019-07-30 2019-11-05 上海交通大学 基于卷积神经网络模型融合篡改人脸检测分析方法和系统
US11669607B2 (en) 2019-08-29 2023-06-06 PXL Vision AG ID verification with a mobile device
CN110555931A (zh) * 2019-08-31 2019-12-10 华南理工大学 一种基于深度学习识别的人脸检测与门禁系统装置
CN110688946A (zh) * 2019-09-26 2020-01-14 上海依图信息技术有限公司 基于图片识别的公有云静默活体检测设备和方法
US11687778B2 (en) 2020-01-06 2023-06-27 The Research Foundation For The State University Of New York Fakecatcher: detection of synthetic portrait videos using biological signals
US11403369B2 (en) 2020-01-21 2022-08-02 Disney Enterprises, Inc. Secure content processing pipeline
CN111339832B (zh) * 2020-02-03 2023-09-12 中国人民解放军国防科技大学 人脸合成图像的检测方法及装置
US11425120B2 (en) 2020-02-11 2022-08-23 Disney Enterprises, Inc. Systems for authenticating digital contents
CN111444873B (zh) * 2020-04-02 2023-12-12 北京迈格威科技有限公司 视频中人物真伪的检测方法、装置、电子设备及存储介质
CN111611873B (zh) * 2020-04-28 2024-07-16 平安科技（深圳）有限公司 人脸替换检测方法及装置、电子设备、计算机存储介质
US11967173B1 (en) 2020-05-19 2024-04-23 T Stamp Inc. Face cover-compatible biometrics and processes for generating and using same
CN111611967A (zh) * 2020-05-29 2020-09-01 哈尔滨理工大学 一种人脸识别的活体检测方法
CN111739046A (zh) * 2020-06-19 2020-10-02 百度在线网络技术（北京）有限公司 用于模型更新和检测图像的方法、装置、设备和介质
CN112085701B (zh) * 2020-08-05 2024-06-11 深圳市优必选科技股份有限公司 一种人脸模糊度检测方法、装置、终端设备及存储介质
CN111986180B (zh) * 2020-08-21 2021-07-06 中国科学技术大学 基于多相关帧注意力机制的人脸伪造视频检测方法
CN112307973B (zh) * 2020-10-30 2023-04-18 中移（杭州）信息技术有限公司 活体检测方法、系统、电子设备和存储介质
CN112689159B (zh) * 2020-12-22 2023-04-18 深圳市九洲电器有限公司 视频文件处理方法、装置、终端设备以及存储介质
CN114760524A (zh) * 2020-12-25 2022-07-15 深圳Tcl新技术有限公司 视频处理方法、装置、智能终端及计算机可读存储介质
US12079371B1 (en) 2021-04-13 2024-09-03 T Stamp Inc. Personal identifiable information encoder
US12315294B1 (en) 2021-04-21 2025-05-27 T Stamp Inc. Interoperable biometric representation
CN113095272B (zh) * 2021-04-23 2024-03-29 深圳前海微众银行股份有限公司 活体检测方法、设备、介质及计算机程序产品
CN112906676A (zh) * 2021-05-06 2021-06-04 北京远鉴信息技术有限公司 人脸图像来源的识别方法、装置、存储介质及电子设备
CN113538185A (zh) * 2021-07-15 2021-10-22 山西安弘检测技术有限公司 一种放射卫生检测的模拟训练方法及装置
CN113486853B (zh) * 2021-07-29 2024-02-27 北京百度网讯科技有限公司 视频检测方法及装置、电子设备和介质
CN113869253A (zh) * 2021-09-29 2021-12-31 北京百度网讯科技有限公司 活体检测方法、训练方法、装置、电子设备及介质
CN113869906A (zh) * 2021-09-29 2021-12-31 北京市商汤科技开发有限公司 人脸支付方法及装置、存储介质
US12353530B1 (en) 2021-12-08 2025-07-08 T Stamp Inc. Shape overlay for proof of liveness
CN114359798B (zh) * 2021-12-29 2025-03-25 天翼物联科技有限公司 实人认证的数据稽核方法、装置、计算机设备及存储介质
CN114694209A (zh) * 2022-02-07 2022-07-01 湖南信达通信息技术有限公司 视频处理方法、装置、电子设备及计算机存储介质
CN114708630A (zh) * 2022-03-23 2022-07-05 贝壳找房网(北京)信息技术有限公司 用于识别图像的方法、装置、电子设备、介质和程序
CN115174138B (zh) * 2022-05-25 2024-06-07 北京旷视科技有限公司 摄像头攻击检测方法、系统、设备、存储介质及程序产品
TWI807851B (zh) * 2022-06-08 2023-07-01 中華電信股份有限公司 一種領域泛化之人臉防偽的特徵解析系統、方法及其電腦可讀媒介
CN115063870B (zh) * 2022-07-08 2024-04-30 广东警官学院(广东省公安司法管理干部学院) 一种基于面部动作单元的伪造视频人像检测方法
CN115205985B (zh) * 2022-07-18 2025-06-27 上海交通大学 一种因果干预的人脸防伪泛化方法、设备及介质
CN115272130A (zh) * 2022-08-22 2022-11-01 苏州大学 基于多光谱级联归一化的图像去摩尔纹系统及方法
CN116258507A (zh) * 2023-02-22 2023-06-13 中国建设银行股份有限公司 一种身份验证方法、装置、设备及介质
CN119046904A (zh) * 2024-07-15 2024-11-29 支付宝(杭州)信息技术有限公司 身份认证方法、装置、可读存储介质及电子设备
CN119091923B (zh) * 2024-11-05 2025-02-07 中国科学院自动化研究所 篡改音频的定位方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102622588A (zh) * 2012-03-08 2012-08-01 无锡数字奥森科技有限公司 双验证人脸防伪方法及装置
CN104766072A (zh) * 2015-04-29 2015-07-08 深圳市保千里电子有限公司 一种活体人脸识别的装置及其使用方法
CN204481940U (zh) * 2015-04-07 2015-07-15 北京市商汤科技开发有限公司 双目摄像头拍照移动终端
US9202105B1 (en) * 2012-01-13 2015-12-01 Amazon Technologies, Inc. Image analysis for user authentication
CN105224924A (zh) * 2015-09-29 2016-01-06 小米科技有限责任公司 活体人脸识别方法和装置

Family Cites Families (44)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2398711B (en) * 2003-02-18 2006-04-12 Samsung Electronics Co Ltd Neural networks
US7418128B2 (en) * 2003-07-31 2008-08-26 Microsoft Corporation Elastic distortions for automatic generation of labeled data
WO2006088042A1 (ja) * 2005-02-16 2006-08-24 Matsushita Electric Industrial Co., Ltd. 生体判別装置および認証装置ならびに生体判別方法
CN101833646B (zh) * 2009-03-11 2012-05-02 北京中科虹霸科技有限公司 一种虹膜活体检测方法
CN101669824B (zh) * 2009-09-22 2012-01-25 浙江工业大学 基于生物特征识别的人与身份证同一性检验装置
US9026580B2 (en) * 2009-11-20 2015-05-05 Microsoft Technology Licensing, Llc Validation pipeline
US9025830B2 (en) * 2012-01-20 2015-05-05 Cyberlink Corp. Liveness detection system based on face behavior
US9177246B2 (en) * 2012-06-01 2015-11-03 Qualcomm Technologies Inc. Intelligent modular robotic apparatus and methods
US10452894B2 (en) * 2012-06-26 2019-10-22 Qualcomm Incorporated Systems and method for facial verification
US9811775B2 (en) * 2012-12-24 2017-11-07 Google Inc. Parallelizing neural networks during training
CN103106397B (zh) * 2013-01-19 2016-09-21 华南理工大学 基于亮瞳效应的人脸活体检测方法
CN104143078B (zh) * 2013-05-09 2016-08-24 腾讯科技（深圳）有限公司 活体人脸识别方法、装置和设备
US9460382B2 (en) * 2013-12-23 2016-10-04 Qualcomm Incorporated Neural watchdog
CN103886301B (zh) 2014-03-28 2017-01-18 北京中科奥森数据科技有限公司 一种人脸活体检测方法
US9484022B2 (en) * 2014-05-23 2016-11-01 Google Inc. Training multiple neural networks with different accuracy
US20160005050A1 (en) * 2014-07-03 2016-01-07 Ari Teman Method and system for authenticating user identity and detecting fraudulent content associated with online activities
CN105447432B (zh) * 2014-08-27 2019-09-13 杨健伟 一种基于局部运动模式的人脸防伪方法
US10417525B2 (en) * 2014-09-22 2019-09-17 Samsung Electronics Co., Ltd. Object recognition with reduced neural network weight precision
CN105426848B (zh) 2014-11-03 2020-12-18 苏州思源科安信息技术有限公司 一种提高生物识别成功率的成像方法
CN104615997B (zh) * 2015-02-15 2018-06-19 四川川大智胜软件股份有限公司 一种基于多摄像机的人脸防伪方法
CN106033435B (zh) * 2015-03-13 2019-08-02 北京贝虎机器人技术有限公司 物品识别方法和装置，室内地图生成方法和装置
US10079827B2 (en) * 2015-03-16 2018-09-18 Ricoh Company, Ltd. Information processing apparatus, information processing method, and information processing system
US10275672B2 (en) * 2015-04-29 2019-04-30 Beijing Kuangshi Technology Co., Ltd. Method and apparatus for authenticating liveness face, and computer program product thereof
WO2016197298A1 (zh) * 2015-06-08 2016-12-15 北京旷视科技有限公司 活体检测方法、活体检测系统以及计算机程序产品
US10878320B2 (en) * 2015-07-22 2020-12-29 Qualcomm Incorporated Transfer learning in neural networks
CN105023005B (zh) * 2015-08-05 2018-12-07 王丽婷 人脸识别装置及其识别方法
CN105117695B (zh) * 2015-08-18 2017-11-24 北京旷视科技有限公司 活体检测设备和活体检测方法
CN105005779A (zh) * 2015-08-25 2015-10-28 湖北文理学院 基于交互式动作的人脸验证防伪识别方法及系统
CN105205455B (zh) * 2015-08-31 2019-02-26 李岩 一种移动平台上人脸识别的活体检测方法及系统
CN106897658B (zh) * 2015-12-18 2021-12-14 腾讯科技（深圳）有限公司 人脸活体的鉴别方法和装置
CN105513221B (zh) * 2015-12-30 2018-08-14 四川川大智胜软件股份有限公司 一种基于三维人脸识别的atm机防欺诈装置及系统
CN105718863A (zh) * 2016-01-15 2016-06-29 北京海鑫科金高科技股份有限公司 一种人脸活体检测方法、装置及系统
CN105718874A (zh) * 2016-01-18 2016-06-29 北京天诚盛业科技有限公司 活体检测及认证的方法和装置
CN105930797B (zh) * 2016-04-21 2019-03-26 腾讯科技（深圳）有限公司 一种人脸验证方法及装置
CN106096519A (zh) * 2016-06-01 2016-11-09 腾讯科技（深圳）有限公司 活体鉴别方法及装置
CN106203305B (zh) * 2016-06-30 2020-02-04 北京旷视科技有限公司 人脸活体检测方法和装置
KR102483642B1 (ko) * 2016-08-23 2023-01-02 삼성전자주식회사 라이브니스 검사 방법 및 장치
US10664722B1 (en) * 2016-10-05 2020-05-26 Digimarc Corporation Image processing arrangements
CN106372629B (zh) * 2016-11-08 2020-02-07 汉王科技股份有限公司 一种活体检测方法和装置
CN108229325A (zh) * 2017-03-16 2018-06-29 北京市商汤科技开发有限公司 人脸检测方法和系统、电子设备、程序和介质
KR102387571B1 (ko) * 2017-03-27 2022-04-18 삼성전자주식회사 라이브니스 검사 방법 및 장치
KR102324468B1 (ko) * 2017-03-28 2021-11-10 삼성전자주식회사 얼굴 인증을 위한 장치 및 방법
CN108229120B (zh) * 2017-09-07 2020-07-24 北京市商汤科技开发有限公司 人脸解锁及其信息注册方法和装置、设备、程序、介质
US10970571B2 (en) * 2018-06-04 2021-04-06 Shanghai Sensetime Intelligent Technology Co., Ltd. Vehicle control method and system, vehicle-mounted intelligent system, electronic device, and medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9202105B1 (en) * 2012-01-13 2015-12-01 Amazon Technologies, Inc. Image analysis for user authentication
CN102622588A (zh) * 2012-03-08 2012-08-01 无锡数字奥森科技有限公司 双验证人脸防伪方法及装置
CN204481940U (zh) * 2015-04-07 2015-07-15 北京市商汤科技开发有限公司 双目摄像头拍照移动终端
CN104766072A (zh) * 2015-04-29 2015-07-08 深圳市保千里电子有限公司 一种活体人脸识别的装置及其使用方法
CN105224924A (zh) * 2015-09-29 2016-01-06 小米科技有限责任公司 活体人脸识别方法和装置

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112580621A (zh) * 2020-12-24 2021-03-30 成都新希望金融信息有限公司 身份证翻拍识别方法、装置、电子设备及存储介质
CN112580621B (zh) * 2020-12-24 2022-04-29 成都新希望金融信息有限公司 身份证翻拍识别方法、装置、电子设备及存储介质
CN112733760A (zh) * 2021-01-15 2021-04-30 上海明略人工智能(集团)有限公司 人脸防伪检测方法及系统
CN112733760B (zh) * 2021-01-15 2023-12-12 上海明略人工智能(集团)有限公司 人脸防伪检测方法及系统

Also Published As

Publication number Publication date
US11482040B2 (en) 2022-10-25
CN108229325A (zh) 2018-06-29
US20210200995A1 (en) 2021-07-01
US11080517B2 (en) 2021-08-03
US20190318156A1 (en) 2019-10-17
WO2018166515A1 (zh) 2018-09-20
CN108229326A (zh) 2018-06-29
CN108229329B (zh) 2022-01-28
WO2018166524A1 (zh) 2018-09-20
CN108229329A (zh) 2018-06-29
CN108229331A (zh) 2018-06-29
CN108229328A (zh) 2018-06-29

Similar Documents

Publication Publication Date Title
WO2018166525A1 (zh) 人脸防伪检测方法和系统、电子设备、程序和介质
KR102324706B1 (ko) 얼굴인식 잠금해제 방법 및 장치, 기기, 매체
KR102406432B1 (ko) 신원 인증 방법 및 장치, 전자 기기 및 저장 매체
KR102319177B1 (ko) 이미지 내의 객체 자세를 결정하는 방법 및 장치, 장비, 및 저장 매체
US10699103B2 (en) Living body detecting method and apparatus, device and storage medium
CN111368601B (zh) 活体检测方法和装置、电子设备和计算机可读存储介质
WO2021073364A1 (zh) 一种人脸活体检测方法、装置、设备及存储介质
WO2020199577A1 (zh) 活体检测方法和装置、设备和存储介质
WO2019218621A1 (zh) 活体检测方法及装置、电子设备和存储介质
TW202011260A (zh) 活體檢測方法、裝置和電腦可讀取儲存媒介
CN109255299A (zh) 身份认证方法和装置、电子设备和存储介质
CN115359539A (zh) 办公场所信息安全检测方法、装置、设备和存储介质
CN112818874B (zh) 一种图像处理方法、装置、设备及存储介质
WO2023071180A1 (zh) 真伪识别方法、装置、电子设备以及存储介质
CN111126283A (zh) 一种自动过滤模糊人脸的快速活体检测方法及系统
CN109543635A (zh) 活体检测方法、装置、系统、解锁方法、终端及存储介质
CN111767845A (zh) 证件识别方法及装置
CN113518217B (zh) 对象识别方法、装置、服务器及介质
CN111931544B (zh) 活体检测的方法、装置、计算设备及计算机存储介质
JP7594140B1 (ja) プログラム、真贋判定方法及び真贋判定装置
CN116152932A (zh) 活体检测方法以及相关设备
JP7766835B1 (ja) 真贋判定プログラム、真贋判定方法、及び真贋判定装置
CN116012248B (zh) 图像处理方法、装置、计算机设备及计算机存储介质
CN113705486B (zh) 检测证件真伪的方法及装置
CN119273568B (zh) 图像处理方法和相关装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18768266

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS (EPO FORM 1205A DATED 17.12.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 18768266

Country of ref document: EP

Kind code of ref document: A1