[go: up one dir, main page]

WO2016086330A1 - Procédé et système de reconnaissance faciale - Google Patents

Procédé et système de reconnaissance faciale Download PDF

Info

Publication number
WO2016086330A1
WO2016086330A1 PCT/CN2014/001091 CN2014001091W WO2016086330A1 WO 2016086330 A1 WO2016086330 A1 WO 2016086330A1 CN 2014001091 W CN2014001091 W CN 2014001091W WO 2016086330 A1 WO2016086330 A1 WO 2016086330A1
Authority
WO
WIPO (PCT)
Prior art keywords
feature extraction
features
extraction module
images
convolutional layer
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/CN2014/001091
Other languages
English (en)
Inventor
Xiaoou Tang
Yi Sun
Xiaogang Wang
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.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to CN201480083717.5A priority Critical patent/CN107004115B/zh
Priority to PCT/CN2014/001091 priority patent/WO2016086330A1/fr
Publication of WO2016086330A1 publication Critical patent/WO2016086330A1/fr
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
    • G06V40/172—Classification, e.g. identification
    • 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
    • G06V30/192—Recognition using electronic means using simultaneous comparisons or correlations of the image signals with a plurality of references
    • G06V30/194—References adjustable by an adaptive method, e.g. learning

Definitions

  • the present application relates to a method for face recognition and a system thereof.
  • the deep learning achieved great success on face recognition and significantly outperformed systems using low level features.
  • the second is supervising the deep neural networks with both the identification and verification tasks. The verification task minimizes the distance between features of the same identity, and decreases intra-personal variations.
  • joint identification-verification achieved the current state-of-the-art 99.15% face verification accuracy on the most extensively evaluated LFW face recognition dataset.
  • features in deep neural networks have sparsity on identities and attributes.
  • deep neural networks in this application are not taught to distinguish attributes during training, they have implicitly learned such high-level concepts.
  • Directly employing features learned by deep neural networks leads to much higher classification accuracy on identity-related attributes than widely used handcrafted features such as high-dimensional LBP (Local Binary Pattern) .
  • LBP Local Binary Pattern
  • this application shows that deep neural networks trained by natural web face images without artificial occlusion patterns added during training have implicitly encoded invariance to occlusions.
  • features learned by the deep neural networks are moderately sparse. For an input face image, around half of the features in the top hidden layer are activated. On the other hand, each feature is activated on roughly half of the face images.
  • Such sparsity distributions can maximize the discriminative power of deep neural networks as well as the distance between images.
  • Different identities have different subsets of features activated. Two images of the same identity have similar activation patterns.
  • the apparatus may comprise a feature extractor and a recognition unit.
  • the feature extractor is configured with a plurality of cascaded feature extraction modules, wherein each of the feature extraction modules comprises a convolutional layer for extracting local features from input face images or from features extracted in a previous feature extraction module of the modules; and a fully-connected layer connected to the convolutional layer in the same feature extraction module and extracting global features from the extracted local features.
  • the recognizer is configured to, in accordance with distances between the extracted global features, determine: if two face images of the input images are from a same identity, or if one of the input images, as a probe face image, is belonging to a same identity as one of gallery face images consisting of the input images.
  • the convolutional layer in the first feature extraction module of the cascaded feature extraction modules is connected to an input face image, and the convolutional layer in each of the following feature extraction modules is connected to the convolutional layer in the previous feature extraction module.
  • the fully-connected layer in each feature extraction module is connected to the convolutional layer in the same feature extraction module.
  • the apparatus may further comprise a trainer configured to update neuron weights on connections between each convolutional layer and the corresponding fully-connected layer in the same feature extraction module by back-propagating identification supervisory signals and verification supervisory signals through the cascaded feature extraction modules.
  • the process of the updating may comprise: inputting two face images to the neural network, respectively, to get feature representations of each of the two face images; calculating identification errors by classifying feature representations of each face image in each fully-connected layer of the neural network into one of a plurality of identities; calculating verification errors by verifying if feature representations of two face images, respectively, in each fully-connected layer are from the same identity, the identification and verification errors being treated as identification and verification supervisory signals, respectively; and back-propagating all identification and verification supervisory signals through the neural network simultaneously, so as to update the neuron weights on connections between each convolutional layer and the corresponding fully-connected layer in the same feature extraction module.
  • the present application discovers and proves three properties of features extracted in later feature extraction modules, i.e., sparsity, selectiveness, and robustness, all of which are critical for face recognition, wherein features are sparse in both the sense that features of each face image have approximately half zero values and half positive values, and each feature has approximately half of the time being zero and half of the time being positive over all face images; features are selective to both identities and identity-related attributes such as sex and race in the sense that there are features which take either positive (activated) or zero (inhibited) values for all face images of a given identity or containing a given identity-related attribute; features are robust to image corruptions such as occlusions, wherein feature values remain largely unchanged under moderate image corruptions.
  • Fig. 1 is a schematic diagram illustrating an apparatus for face recognition consistent with some disclosed embodiments.
  • Fig. 2 is a schematic diagram illustrating the sparsity, selectiveness, and robustness of features extracted in later feature extraction modules.
  • Fig. 3 is a schematic diagram illustrating structures of cascaded feature extraction modules in the feature extractor, as well as input face images and supervisory signals in the trainer.
  • Fig. 4 is schematic histograms illustrating the sparsity of activated features (neurons) on individual face images as well as the sparsity of individual features (neurons) activated on all face images.
  • Fig. 5 is schematic histograms illustrating the selective activation and inhibition of features on face images of particular identities.
  • Fig. 6 is schematic histograms illustrating the selective activation and inhibition of features on face images containing particular attributes.
  • Fig. 7 is a schematic diagram illustrating face images with random block occlusions, which are used to test the robustness of features extracted by the feature extractor against image corruptions.
  • Fig. 8 is a schematic diagram illustrating the mean feature activations over face images of individual identities under various degrees of random block occlusions.
  • Fig. 9 is a schematic flowchart illustrating the trainer as shown in Fig. 1 consistent with some disclosed embodiments.
  • Fig. 10 is a schematic flowchart illustrating the feature extractor as shown in Fig. 1 consistent with some disclosed embodiments.
  • Fig. 11 is a schematic flowchart illustrating the recognizer as shown in Fig. 1 consistent with some disclosed embodiments.
  • the present invention may be embodied as a system, method or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc. ) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a “circuit, ” “module” or “system. ” Furthermore, the present invention may take the form of a computer program product embodied in any tangible medium of expression having computer-usable program code embodied in the medium.
  • Fig. 1 is a schematic diagram illustrating an exemplary apparatus 100 for face recognition consistent with some disclosed embodiments.
  • the apparatus 100 may comprise a feature extractor 10 and a recognizer 20.
  • the feature extractor 10 is configured to extract features from input face images.
  • the feature extractor 10 may comprise a neural network which may be constructed with a plurality of cascaded feature extraction modules, wherein each feature extraction module in the cascade comprises a convolutional layer and a fully-connected layer.
  • the cascaded feature extraction modules may be implemented by software, integrated circuits (ICs) or the combination thereof.
  • Fig. 3 illustrates a schematic diagram for structures of cascaded feature extraction modules in the feature extractor 10.
  • the convolutional layer in the first feature extraction module of the cascaded feature extraction modules is connected to an input face image
  • the convolutional layer in each of the following feature extraction modules is connected to the convolutional layer in the previous feature extraction module.
  • the fully-connected layer in each feature extraction module is connected to the convolutional layer in the same feature extraction module.
  • the apparatus 100 further comprises a trainer 30 configured to update neural weights on connections between the convolutional layer in the first feature extraction module and the input layer containing an input face image, connections between each convolutional layer in the second to the last feature extraction modules and the corresponding convolutional layer in the previous feature extraction module, and connections between each convolutional layer and the corresponding fully-connected layer in the same feature extraction module, by back-propagating identification supervisory signals and verification supervisory signals through the cascaded feature extraction modules, such that features extracted in last/highest one of the cascaded feature extraction modules are sparse, selective, and robust, which will be discussed later.
  • a trainer 30 configured to update neural weights on connections between the convolutional layer in the first feature extraction module and the input layer containing an input face image, connections between each convolutional layer in the second to the last feature extraction modules and the corresponding convolutional layer in the previous feature extraction module, and connections between each convolutional layer and the corresponding fully-connected layer in the same feature extraction module, by back-propagating identification supervisory signals and
  • the recognizer 20 may be implemented by software, integrated circuits (ICs) or the combination thereof, and is configured to calculate distances between features extracted from different face images to determine if two face images are from the same identity for face verification or determine if one of the input images, as a probe face image, is belonging to a same identity as one of gallery face images consisting of the input images for face identification.
  • ICs integrated circuits
  • the feature extractor 10 contains a plurality of cascaded feature extraction modules, and operates to extract features hierarchically from input face images.
  • the convolutional layer Conv-1 in the first feature extraction module of the feature extractor 10 is connected to an input face image as an input layer, while the convolutional layer Conv-n for n > 1 in each of the following feature extraction modules of the feature extractor 10 is connected to the convolutional layer Conv- (n-1) in the previous feature extraction module.
  • the fully-connected layer FC-n in each feature extraction module of the feature extractor 10 is connected to the convolutional layer Conv-n in the same feature extraction module.
  • Fig. 10 is a schematic flowchart illustrating the feature extraction process in the feature extractor 10.
  • the feature extractor 10 forward propagates an input face image through convolutional layers in all feature extraction modules of the feature extractor 10.
  • step 102 the feature extractor 10 forward propagates outputs of each of the convolutional layers to a corresponding fully-connected layer within the same feature extraction module.
  • step 103 it takes the outputs/representations from a last one of the fully-connected layers as features as discussed below.
  • Convolutional layers in the feature extractor 10 are configured to extract local facial features (i.e. features extracted from local regions of the input images or the input features) from input images (for the first convolutional layer) or the feature maps (which is output feature maps of the previous convolutional layer followed by max pooling as well known in the art) to form output feature maps of the current convolutional layer.
  • Each feature map is a certain kind of features organized in 2D.
  • the features in the same output feature map or in local regions of the same feature map are extracted from input feature maps with the same set of neural connection weights w between the input features maps and the output feature maps in the previous convolutional layers (followed by max pooling) and the current convolutional layers, respectively.
  • the convolution operation in each convolutional laver may be expressed as
  • x i and y j are the i-th input feature map and the j-th output feature map, respectively.
  • k ij is the convolution kernel between the i-th input feature map and the j-th output feature map. *denotes convolution.
  • b j is the bias of the j-th output feature map.
  • Each convolutional layer may be followed by max-pooling formulated as
  • each neuron in the i-th output feature map y i pools over an s ⁇ s non-overlapping local region in the i-th input feature map x i .
  • Each of the fully-connected layers in the feature extractor 10 is configured to extract global features (features extracted from the entire region of input feature maps) from the feature maps obtained from the convolutional layers on the same module. That is, the fully-connected layer FC-n extracts global features from the convolutional layer Conv-n.
  • the fully-connected layers also serve as interfaces for receiving supervisory signals during training and outputting features during feature extraction.
  • Fully-connected layers may be formulated as
  • x i represent the output of the i-th neuron in the previous convolutional layer (followed by max-pooling) .
  • y j represent the output of the j-th neuron in the current fully-connected layer.
  • w i,j is a weight on connections between the i-th neuron in the previous convolutional layer (followed by max-pooling) and the j-th neuron in the current fully-connected layer.
  • b j is a bias of the j-th neuron in the current fully-connected layer.
  • Max (0, x) is the ReLU non-linearity.
  • features extracted in the last/highest feature extraction modules of the feature extractor 10, e.g., those in FC-4 layer as shown in Fig. 3, are sparse, selective, and robust: features are sparse in both the sense that features of each face image have approximately half zero values and half positive values, and each feature has approximately half of the time being zero and half of the time being positive over all face images; features are selective to both identities and identity-related attributes such as sex and race in the sense that there are features which take either positive (activated) or zero (inhibited) values for all face images of a given identity or containing a given identity-related attribute; features are robust to image corruptions such as occlusions, wherein feature values remain largely unchanged under moderate image corruptions.
  • the sparse features can be converted to binary code by comparing to a threshold, wherein the binary code can be used for face recognition.
  • Fig. 2 illustrates the three properties, sparsity, selectiveness, and robustness, of features extracted in FC-4 layer.
  • Fig. 2 left shows features on three face images of Bush and one face image of Powell .
  • the second face image of Bush is partially occluded.
  • there are 512 features in FC-4 layer from which Fig. 2 subsamples 32 for illustration as an example.
  • Features are sparsely activated on each face image, in which there are approximately half of features being positive and half being zero.
  • Features of face images of the same identity have similar activation patterns while being different for different identities.
  • Features are robust in that when occlusions are presented, as shown on the second face of Bush, activation patterns of features keep largely unchanged.
  • a feature is generally activated on about half of face images. But it may constantly have activations (or no activation) for all images belonging to a particular identity of attribute. In this sense, features are sparse, and selective to identities and attributes.
  • Fig. 4 left shows the histogram of activated (positive) feature numbers on each of 46, 594 (for example) face images in a validating dataset
  • Fig. 4 fight shows the histogram of the number of images on which each feature are activated (positive) .
  • the evaluation is based features extracted by FC-4 layer.
  • the mean and standard deviation of the number of activated neurons on images is 292 ⁇ 34, while compared to all 46, 594 validating images, the mean and standard deviation of the number of images on which each feature are activated is 26, 565 ⁇ 5754, both of which are approximated centered at half of all features/images.
  • the activation patterns i.e., whether features are activated (with positive values) , are more important than precise activation values. Converting feature activations to binary code by thresholding only sacrifices less than 1%face verification accuracies. This shows that the state of excitation or inhibition of features already contains the majority of discriminative information. Binary code is economic for storage and fast for image search.
  • Fig. 5 and Fig. 6 show examples of activation histograms of features over given identities and attributes, respectively. Histograms over given identities exhibit strong selectiveness. Some features are constantly activated for a given identity, with histograms distributed in values greater than zero, as shown in the first two rows in Fig. 5, while some others are constantly inhibited, with histograms accumulated at zero or small values, as shown in the last two rows in Fig. 5. For attributes, each row of Fig. 7 shows histograms of a single feature over a few related attributes (those related to sex, race, and age) . The selected features are excitatory on each of attributes given in the left of each row. As shown in Fig.
  • features exhibit strong selectiveness to sex, race, and certain ages such as child and senior, in which features are strongly activated for a given attribute while inhibited for other attributes in the same category.
  • the selectiveness is weak, in which there are no features solely activated for each of these attributes. This is because ages do not exactly correspond to identities. For example, in face recognition, features have to be invariant to the same identity photographed at both young and middle aged.
  • Fig. 7 and Fig. 8 illustrate the robustness of features extracted in later feature extraction modules (FC-4 layer) against image corruptions. Face images are occluded by random blocks with various sizes from 10 ⁇ 10 to 70 ⁇ 70, as illustrated in Fig. 7.
  • Fig. 8 shows mean feature activations over images with random block occlusions, in which each column shows the mean activation over face images of a single identity given in the top of each column, with various degrees of occlusions given in the left of each row.
  • Feature values are mapped to a color map with warm colors indicating positive values and cool colors indicating zero or small values.
  • the order of features in figures in each column is sorted by the mean feature activation values on the original face images of each identity, respectively.
  • the activation patterns keep largely unchanged (with most activated features still being activated and most inhibited features still being inhibited) until a large degree of occlusions.
  • the Recognizer20 The Recognizer20
  • the recognizer 20 operates to calculate distances between global features for different face images extracted by the fully-connected layer of the feature extractor 10 to determine if two face images are from the same identity for face verification or determine if one of the input images, as a probe face image, is belonging to a same identity as one of gallery face images consisting of the input images for face identification.
  • Fig. 10 is a schematic flowchart illustrating the recognition process in the recognizer 20.
  • the recognizer 20 calculates distances between features (i.e. global features for different face images extracted by the fully-connected layer) extracted from different face images by the feature extractor 10.
  • the recognizer 20 determines if two face images are from the same identity for face verification, or, alternatively, in step 203, it determines one of the input images, as a probe face image, is belonging to a same identity as one of gallery face images consisting of the input images for face identification.
  • two face images are determined to belong to the same identity if their feature distance is smaller than a threshold, or the probe face image is determined to belong to the same identity as one of gallery face images if their feature distance is the smallest compared to feature distances of the probe face image to all the other gallery face images, wherein feature distances determined by the recognizer 20 could be Euclidean distances, Joint Bayesian distances, cosine distances, Hamming distances, or any other distances.
  • Joint Bayesian distances are used as feature distances.
  • Joint Bayesian has been a popular similarity metric of faces, which represents the extracted facial features x (after subtracting the mean) by the sum of two independent Gaussian variables
  • S S and S ⁇ can be learned from data with EM algorithm. In test, it calculates the likelihood ratio
  • the Trainer 30 The Trainer 30
  • the a trainer 30 is used to update the weights w on connections between neurons in convolutional and fully-connected layers in the feature extractor 10 by inputting initial weights on connections between neurons in convolutional and fully-connected layers in the feature extractor, a plurality of identification supervisory signals, and a plurality of verification supervisory signals, such that that features extracted in last one of the cascaded feature extraction modules in the extractor are sparse, selective, and robust..
  • the identification supervisory signals “Id” are generated in the trainer 30 by classifying all of the fully-connected layer representations/outputs (i.e., formula (4) ) of a single face image into one of N identities, wherein the classification errors are used as the identification supervisory signals.
  • the verification supervisory signals in the trainer 30 are generated by verifying the fully-connected layer representations of two compared face images, respectively, in each of the feature extraction modules, to determine if the two compared face images belong to the same identity, wherein the verification errors are used as the verification supervisory signals.
  • the feature extractor 10 Given a pair of training face images, the feature extractor 10 extracts two feature vectors f i and f j from the two face images respectively in each of the feature extraction modules.
  • the verification error is if f i and f j are features of face images of the same identity, or if f i and f j are features of face images of different identities, where
  • 2 is Euclidean distance of the two feature vectors, m is a positive constant value.
  • f i and f j are dissimilar for the same identity, or if f i and f j are similar for different identities.
  • Fig. 9 is a schematic flowchart illustrating the training process in the trainer 30.
  • the trainer 30 samples two face images and inputs them to the feature extractor 10, respectively, to get feature representations of each of the two face images in all fully-connected layers of the feature extractor 10.
  • the trainer 30 calculates identification errors by classifying feature representations of each face image in each fully-connected layer into one of a plurality of (N) identities.
  • the trainer 30 calculates verification errors by verifying if feature representations of two face images, respectively, in each fully-connected layer are from the same identity.
  • the identification and verification errors are used as identification and verification supervisory signals, respectively.
  • step 104 the trainer 30 back propagates all identification and verification supervisory signals through the feature extractor 10 simultaneously, so as to update weights on connections between neurons in the feature extractor 10.
  • step 105 the trainer 30 judges if training process has converged, and repeats steps 101-104 if a convergence point has not reached.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)
  • Collating Specific Patterns (AREA)

Abstract

La présente invention concerne un appareil et un procédé de reconnaissance faciale. L'appareil peut comprendre : un extracteur ayant une pluralité de modules d'extraction de caractéristiques en cascade, chacun des modules d'extraction de caractéristiques en cascade comprenant une couche convolutionnelle destinée à extraire des caractéristiques locales à partir d'images de visage d'entrée ou à partir de caractéristiques extraites dans un précédent module d'extraction de caractéristiques des modules ; et une couche entièrement connectée, connectée à la couche convolutionnelle sur un même module d'extraction de caractéristiques et qui extrait des caractéristiques globales à partir des caractéristiques locales extraites. L'appareil peut en outre comprendre un dispositif de reconnaissance configuré de façon à déterminer, en fonction des distances entre les caractéristiques globales extraites : si deux images de visage des images d'entrée proviennent d'une même identité ou si l'une des images d'entrée, sous la forme d'une image de visage de test, appartient à une même identité que l'une des images de visage de galerie constituée par les images d'entrée.
PCT/CN2014/001091 2014-12-03 2014-12-03 Procédé et système de reconnaissance faciale Ceased WO2016086330A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201480083717.5A CN107004115B (zh) 2014-12-03 2014-12-03 用于人脸识别的方法和系统
PCT/CN2014/001091 WO2016086330A1 (fr) 2014-12-03 2014-12-03 Procédé et système de reconnaissance faciale

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2014/001091 WO2016086330A1 (fr) 2014-12-03 2014-12-03 Procédé et système de reconnaissance faciale

Publications (1)

Publication Number Publication Date
WO2016086330A1 true WO2016086330A1 (fr) 2016-06-09

Family

ID=56090783

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/001091 Ceased WO2016086330A1 (fr) 2014-12-03 2014-12-03 Procédé et système de reconnaissance faciale

Country Status (2)

Country Link
CN (1) CN107004115B (fr)
WO (1) WO2016086330A1 (fr)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019067223A1 (fr) * 2017-09-29 2019-04-04 General Electric Company Authentification automatique pour contrôle d'accès à l'aide d'une reconnaissance faciale
CN111079549A (zh) * 2019-11-22 2020-04-28 杭州电子科技大学 一种利用门控融合判别特征进行漫画人脸识别的方法
US10922531B2 (en) 2018-04-09 2021-02-16 Pegatron Corporation Face recognition method
US11651229B2 (en) 2017-11-22 2023-05-16 Zhejiang Dahua Technology Co., Ltd. Methods and systems for face recognition

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108009481A (zh) * 2017-11-22 2018-05-08 浙江大华技术股份有限公司 一种cnn模型的训练方法及装置、人脸识别方法及装置
CN108073917A (zh) * 2018-01-24 2018-05-25 燕山大学 一种基于卷积神经网络的人脸识别方法
CN110309692B (zh) * 2018-03-27 2023-06-02 杭州海康威视数字技术股份有限公司 人脸识别方法、装置及系统、模型训练方法及装置
CN111968264A (zh) * 2020-10-21 2020-11-20 东华理工大学南昌校区 体育项目时间登记装置
CN114880636A (zh) * 2022-05-31 2022-08-09 中国银行股份有限公司 基于人脸识别的身份验证方法和系统
CN116311464B (zh) * 2023-03-24 2023-12-12 北京的卢铭视科技有限公司 模型训练方法、人脸识别方法、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050123202A1 (en) * 2003-12-04 2005-06-09 Samsung Electronics Co., Ltd. Face recognition apparatus and method using PCA learning per subgroup
CN1700240A (zh) * 2004-05-17 2005-11-23 香港中文大学 基于随机采样的面部识别方法
CN1866270A (zh) * 2004-05-17 2006-11-22 香港中文大学 基于视频的面部识别方法
CN101763506A (zh) * 2008-12-22 2010-06-30 Nec九州软件株式会社 脸部图像跟踪设备和方法以及计算机可读记录介质
US20130322708A1 (en) * 2012-06-04 2013-12-05 Sony Mobile Communications Ab Security by z-face detection

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102629320B (zh) * 2012-03-27 2014-08-27 中国科学院自动化研究所 基于特征层定序测量统计描述的人脸识别方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050123202A1 (en) * 2003-12-04 2005-06-09 Samsung Electronics Co., Ltd. Face recognition apparatus and method using PCA learning per subgroup
CN1700240A (zh) * 2004-05-17 2005-11-23 香港中文大学 基于随机采样的面部识别方法
CN1866270A (zh) * 2004-05-17 2006-11-22 香港中文大学 基于视频的面部识别方法
CN101763506A (zh) * 2008-12-22 2010-06-30 Nec九州软件株式会社 脸部图像跟踪设备和方法以及计算机可读记录介质
US20130322708A1 (en) * 2012-06-04 2013-12-05 Sony Mobile Communications Ab Security by z-face detection

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019067223A1 (fr) * 2017-09-29 2019-04-04 General Electric Company Authentification automatique pour contrôle d'accès à l'aide d'une reconnaissance faciale
CN111133433A (zh) * 2017-09-29 2020-05-08 通用电气公司 使用面部识别用于访问控制的自动认证
CN111133433B (zh) * 2017-09-29 2023-09-05 通用电气公司 使用面部识别用于访问控制的自动认证
US11651229B2 (en) 2017-11-22 2023-05-16 Zhejiang Dahua Technology Co., Ltd. Methods and systems for face recognition
US10922531B2 (en) 2018-04-09 2021-02-16 Pegatron Corporation Face recognition method
CN111079549A (zh) * 2019-11-22 2020-04-28 杭州电子科技大学 一种利用门控融合判别特征进行漫画人脸识别的方法
CN111079549B (zh) * 2019-11-22 2023-09-22 杭州电子科技大学 一种利用门控融合判别特征进行漫画人脸识别的方法

Also Published As

Publication number Publication date
CN107004115A (zh) 2017-08-01
CN107004115B (zh) 2019-02-15

Similar Documents

Publication Publication Date Title
WO2016086330A1 (fr) Procédé et système de reconnaissance faciale
CN106415594B (zh) 用于面部验证的方法和系统
CN111814584B (zh) 基于多中心度量损失的多视角环境下车辆重识别方法
CN108352072B (zh) 物体跟踪方法、物体跟踪装置以及记录介质
US9811718B2 (en) Method and a system for face verification
Khan et al. Human Gait Recognition Using Deep Learning and Improved Ant Colony Optimization.
WO2016119076A1 (fr) Procédé et système de reconnaissance faciale
CN111523621A (zh) 图像识别方法、装置、计算机设备和存储介质
Zheng et al. Vlad encoded deep convolutional features for unconstrained face verification
Cai et al. HOG-assisted deep feature learning for pedestrian gender recognition
Xia et al. Loop closure detection for visual SLAM using PCANet features
CN111709311A (zh) 一种基于多尺度卷积特征融合的行人重识别方法
CN110765860A (zh) 摔倒判定方法、装置、计算机设备及存储介质
US9842279B2 (en) Data processing method for learning discriminator, and data processing apparatus therefor
CN114358205B (zh) 模型训练方法、模型训练装置、终端设备及存储介质
CN108985200A (zh) 一种基于终端设备的非配合式的活体检测算法
Wang et al. Hierarchical spatial sum–product networks for action recognition in still images
CN109033321B (zh) 一种图像与自然语言特征提取及基于关键词的语言指示图像分割方法
CN114093003A (zh) 一种更具欺诈辨别性的人脸活体检测方法及其网络模型
CN108805280B (zh) 一种图像检索的方法和装置
CN108496174B (zh) 用于面部识别的方法和系统
Pramukha et al. End-to-end latent fingerprint enhancement using multi-scale Generative Adversarial Network
CN104200222B (zh) 一种基于因子图模型的图片中对象识别方法
Jammalamadaka et al. Human pose search using deep poselets
CN113591593B (zh) 基于因果干预的异常天气下目标检测方法、设备及介质

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: 14907199

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 14907199

Country of ref document: EP

Kind code of ref document: A1