WO2022067543A1 - Fingerprint recognition method, fingerprint recognition apparatus, electronic device and storage medium - Google Patents

Abstract

A fingerprint recognition method, a fingerprint recognition apparatus, an electronic device and a storage medium. The method comprises: according to fingerprint data corresponding to a fingerprint to be detected, determining fingerprint feature information for indicating a ridge/valley line feature and a polarization property of said fingerprint (S301); inputting the fingerprint feature information into a pre-trained decision tree model, so as to obtain a score for indicating that said fingerprint is a real fingerprint (S302); and determining the authenticity of said fingerprint according to a comparison result of the score and a preset fingerprint threshold value (S303). By using the method, whether a fingerprint to be detected is a real fingerprint or a false fingerprint with a three-dimensional depth feature can be determined, thereby improving the security of fingerprint detection.

Description

Fingerprint identification method, fingerprint identification device, electronic device and storage medium technical field

The embodiments of the present application relate to the technical field of biometric identification, and in particular, to a fingerprint identification method, a fingerprint identification device, an electronic device, and a storage medium.

Background technique

With the wide application of optical fingerprint recognition technology in terminal devices, users have higher and higher security requirements for fingerprint recognition. The relevant fingerprint identification scheme is based on the polarization information of the device screen, which can better identify real fingerprints and fake planar fake fingerprints (also called 2D fake fingerprints), and has a better anti-counterfeiting effect on 2D fake fingerprints. However, since the fake fingerprints (also known as 2.5D fake fingerprints) produced by simple processes such as corroding circuit boards according to the extracted user fingerprints have 3D depth characteristics, the above fingerprint identification scheme has poor interception effect on such fake fingerprints, which seriously affects the Information security for end users.

Therefore, how to identify real fingerprints and 2.5D fake fingerprints to improve the security of fingerprint identification is an urgent problem to be solved.

SUMMARY OF THE INVENTION

In view of this, one of the technical problems solved by the embodiments of the present invention is to provide a fingerprint identification method, a fingerprint identification device and an electronic device to overcome all or some of the above-mentioned defects.

In a first aspect, an embodiment of the present application provides a fingerprint identification method, which includes:

According to the fingerprint data corresponding to the fingerprint to be detected, the fingerprint feature information used to indicate the ridge-valley line feature and the polarization feature of the fingerprint to be detected is determined, wherein the fingerprint data is a multi-path optical signal guided by the fingerprint sensor according to the multi-optical path structure Obtained, the multi-optical path structure at least includes a polarized light guide channel with projection parallel to the screen polarization direction and a non-polarized light guide channel perpendicular to the screen polarization direction on the plane where the photosensitive region is located;

Inputting the fingerprint feature information into a pre-trained decision tree model to obtain a score for indicating that the fingerprint to be detected is a true fingerprint;

According to the comparison result between the score and the preset fingerprint threshold, the authenticity of the fingerprint to be detected is determined.

In a second aspect, an embodiment of the present application provides a fingerprint identification device, which includes:

A feature extraction module is used to determine fingerprint feature information for indicating the ridge-valley line feature and polarization feature of the fingerprint to be detected according to the fingerprint data corresponding to the fingerprint to be detected, wherein the fingerprint data is the fingerprint sensor according to the multi-optical path structure Obtained from the guided multi-path optical signals, the multi-optical path structure at least includes a polarized light guide channel projected on the plane where the photosensitive area is located parallel to the screen polarization direction and a non-polarized light guide channel perpendicular to the screen polarization direction;

A score calculation module for inputting the fingerprint feature information into a pre-trained decision tree model to obtain a score for indicating that the fingerprint to be detected is a true fingerprint;

The authenticity fingerprint determination module is configured to determine the authenticity of the fingerprint to be detected according to the comparison result between the score and the preset fingerprint threshold.

In a third aspect, an embodiment of the present application provides an electronic device, which includes: a processor, a memory, a display screen, a touch control module, and a fingerprint identification device;

the memory is used to store computer programs;

The fingerprint identification device includes an optical image acquisition module, and the optical image acquisition module includes a pixel array;

The processor executes the computer program stored in the memory, so that the electronic device executes the fingerprint identification method according to any one of the first aspects.

In a fourth aspect, an embodiment of the present application provides a storage medium, which includes: a readable storage medium and a computer program, where the computer program is stored in the readable storage medium, and the computer program is used for any of the first aspect. The fingerprint recognition method described in one item.

Based on the above technical solutions, since the multi-optical path structure includes a polarized light guide channel projected on the plane where the photosensitive area is located parallel to the polarization direction of the screen and a non-polarized light guide channel perpendicular to the screen polarization direction, the multi-path light guided by the multi-optical path structure The fingerprint data obtained by the signal can determine the fingerprint feature information used to indicate the ridge-valley line feature and polarization feature of the fingerprint to be detected, and input the feature information into the pre-trained decision tree model, and use the output of the decision tree model to indicate. The comparison result of the score of the fingerprint to be detected as a real fingerprint and the preset fingerprint threshold value can determine whether the fingerprint to be detected is a real fingerprint or a fake fingerprint with three-dimensional depth feature, which improves the security of fingerprint detection.

Description of drawings

Hereinafter, some specific embodiments of the embodiments of the present application will be described in detail by way of example and not limitation with reference to the accompanying drawings. The same reference numbers in the figures designate the same or similar parts or parts. It will be understood by those skilled in the art that the drawings are not necessarily to scale. In the attached picture:

1 is a schematic cross-sectional view of an electronic device to which an embodiment of the application can be applied;

Fig. 2 is the schematic diagram of the relative positional relationship between each light path in a kind of four light path light guide channel group provided by the embodiment of the application;

3 is a schematic flowchart of a fingerprint identification method provided by an embodiment of the present application;

FIG. 4 is a schematic flowchart of another fingerprint identification method provided by an embodiment of the present application;

5a and 5b are schematic diagrams of acquiring a first preset data group and a second preset data group, respectively, provided by an embodiment of the present application;

6a and 6b are schematic diagrams of a process for determining a common area provided by an embodiment of the present application;

FIG. 7 provides an exemplary real finger and a 2.5D fake fingerprint and a corresponding fingerprint cross-sectional view provided in an embodiment of the present application;

8 is a flowchart of a method for determining the coefficient of variation of a ridge line and a coefficient of variation of a valley line provided by an embodiment of the present application;

9 is a schematic diagram of polarization characteristics of fingerprint ridge lines and fingerprint valley lines of a real fingerprint provided by an embodiment of the present application;

FIG. 10 is an exemplary flowchart of determining a first signal strength ratio and a second signal strength ratio according to an embodiment of the present application;

11 is a schematic flowchart of a method for determining grayscale similarity provided by an embodiment of the present application;

12a and 12b are schematic diagrams of grayscale distributions of real fingerprints and 2.5D fake fingerprints provided by the embodiments of the present application;

FIG. 13 is a schematic structural diagram of a fingerprint identification device according to an embodiment of the present application.

Detailed ways

The specific implementation of the embodiments of the present invention is further described below with reference to the accompanying drawings of the embodiments of the present invention.

The technical solutions provided in the embodiments of the present application can be applied to various electronic devices. For example, smart phones, tablet computers, and other mobile terminals or other electronic devices with display screens and fingerprint recognition devices. More specifically, in the above-mentioned electronic equipment, the fingerprint identification device may be specifically an optical fingerprint device, which may be arranged in a partial area or an entire area under the display screen, thereby forming an under-display or Under-screen optical fingerprint system. . Specifically, in the electronic device, the fingerprint identification device receives the light returned from the top surface of the display screen of the electronic device, and the returned light carries the information of the object in contact with the top surface of the display screen, such as a finger, by collecting And detect the fingerprint information of the finger from the returned light.

FIG. 1 is a schematic cross-sectional view of an electronic device to which an embodiment of the present application can be applied. As shown in FIG. 1 , the electronic device includes a display screen 12 and a fingerprint identification device 13 .

The display screen 12 includes an upper cover 121 , a light-emitting layer 122 and a lower cover 123 . Depending on the light-emitting layer, the display screen 12 may be a display screen with self-luminous display units or a non-self-luminous display screen.

The display screen 12 is a display screen with a self-luminous display unit. For example, as shown in FIG. 1 , the display screen 12 can be a display screen using an organic light-emitting diode (Organic Light-Emitting Diode, OLED), however, the present application is not limited to this For example, a micro light-emitting diode (Micro-LED) can also be used. When an OLED display screen is used, the fingerprint identification device 13 can use the OLED light source of the display screen 12 corresponding to the position of the fingerprint collection area as the excitation light source for fingerprint detection. When the finger is pressed on the fingerprint collection area of the display screen 12 , the light source at the corresponding position in the display screen 12 emits a light beam to the finger above the fingerprint collection area, and the light beam is reflected on the surface contacting the finger and the screen to form reflected light. The reflected light from the fingerprint ridge and the reflected light from the fingerprint valley have different light intensities. After the reflected light with different intensities passes through the optical components, the fingerprint identification device 13 receives and converts it into a corresponding electrical signal, that is, the fingerprint detection signal. Based on the fingerprint detection signal, fingerprint data can be obtained, which is used to realize the fingerprint identification function in the electronic device.

The display screen 12 is a non-self-luminous display screen, such as a liquid crystal display screen. The fingerprint identification device 13 needs to use a built-in light source or an external light source as an excitation light source to provide an optical signal for fingerprint detection. The fingerprint detection principle when the built-in light source or the external light source is used as the excitation light source is the same as the fingerprint detection principle when the OLED display screen is used as mentioned above, and will not be repeated here.

The display screen 12 may further include a polarizing unit 124. As shown in FIG. 1, the polarizing unit 124 is located above the light-emitting layer 122. The polarizing unit 122 may be set with a polarizing direction, and the polarizing unit 122 may allow light parallel to its polarizing direction to pass through and block the light. Light perpendicular to its polarization direction.

The fingerprint identification device 13 , specifically an optical fingerprint identification device, may be disposed in a partial area below the display screen 12 , and may include a multi-optical path structure 131 and an optical detection component 132 . The multi-optical path structure 131 may be disposed above the optical detection component 132 , and is mainly used to guide the light signal reflected or scattered from the finger to the optical detection component for optical detection by the optical detection component 132 . The optical detection part 132 includes a photosensitive array and a reading circuit and other auxiliary circuits electrically connected to the photosensitive array. The photosensitive array may include a plurality of photosensitive units distributed in an array, which may also be referred to as pixel units or photosensitive pixels. The photosensitive array is mainly used to detect the received light signal, so as to generate fingerprint data through the reading circuit etc. which are electrically connected to it.

In this embodiment, the multi-optical path structure 131 may include at least one light guide channel group, and each light guide channel group includes at least N1 polarized light guide channels projected on the plane where the photosensitive area is located parallel to the polarization direction of the screen and perpendicular to the polarization direction of the screen. N2 non-polarized light guide channels in the polarization direction of the screen, where N1 and N2 are both positive integers.

For example, as shown in FIG. 2, in an implementation manner, N1 and N2 are both 2, and each light guide channel group includes four light guide channels 21-24, and the four light guide channels 21-24 are relative to the optical The plane on which the photosensitive area of the detection part 132 is located is inclined, eg, 30 degrees. The angle between the adjacent two light guide channels in the four light guide channels 21 to 24 is 45 degrees in space, and the projection of the adjacent two light guide channels in the four light guide channels on the plane where the photosensitive area is located The included angle is 90 degrees. As shown in FIG. 2 , assuming that the screen polarization direction of the display screen 12 is 135 degrees, the four light guide channels 21 to 24 include two light guide channels whose projections on the plane where the photosensitive area is located are parallel to the screen polarization direction of the display screen 12 . Channels 21 and 24 and two light guiding channels 22 and 23 perpendicular to the screen polarization direction of the display screen 12 .

It should be understood that being parallel to the screen polarization direction of the display screen can be understood as being approximately parallel to the screen polarization direction of the display screen, and being perpendicular to the screen polarization direction of the display screen can be understood as being approximately perpendicular to the screen polarization direction of the display screen. The four light-guiding channels 21 to 24 correspond to the four photosensitive units of the photosensitive array, respectively, and the photosensitive areas of the four photosensitive units respectively receive four optical signals 0 to 3 through the four light-guiding channels diagonally. Optical signals 0-3 can generate four sets of fingerprint data.

During fingerprint detection, the fingerprint feature information for the ridge-valley line feature and the polarization feature of the fingerprint to be detected is determined according to the fingerprint data corresponding to the fingerprint to be detected, and the feature information is input into a pre-trained decision tree model, and the decision is made. The comparison result of the score output by the tree model for indicating that the fingerprint to be detected is a real fingerprint and the preset fingerprint threshold value can determine the authenticity of the fingerprint to be detected. The embodiments of the present application can not only be applied to planar fake fingerprint recognition, but also can effectively identify 2.5D fake fingerprints with 3D depth information. 2.5D fake fingerprints with three-dimensional features obtained by rubbing and shaping with glue, thus improving the security of fingerprint identification.

FIG. 3 is an exemplary flowchart of a method for fingerprint identification according to an embodiment of the present application. The fingerprint identification method is applicable to the electronic device shown in FIG. 1 . As shown in Figure 3, the method includes:

S301 , according to the fingerprint data corresponding to the fingerprint to be detected, determine fingerprint feature information for indicating the ridge-valley line feature and the polarization feature of the fingerprint to be detected.

The fingerprint data is obtained by the fingerprint sensor according to the multi-path optical signals guided by the multi-optical path structure, and the multi-optical path structure at least includes a polarized light guide channel projected on the plane where the photosensitive area is located parallel to the polarization direction of the screen and a polarization light guide channel perpendicular to the polarization direction of the screen. Unpolarized light guide channel.

In this embodiment, the fingerprint data may include N groups of fingerprint data, where N is a positive integer greater than or equal to 2. The specific size of N is related to the number of polarized light guide channels and non-polarized light guide channels included in each light guide channel group in the multi-optical path structure. Specifically, if each light guide channel group includes N1 polarized light guide channels and N2 non-polarized light guide channels, then N is less than or equal to N1+N2. In other words, the fingerprint data can be obtained from the multi-path optical signals guided by part or all of the polarized light-guiding channels and the non-polarized light-guiding channels in the multi-optical path structure.

The display screen usually has a polarization characteristic, and its polarization direction is at a certain angle with the horizontal (or vertical) direction of the display screen, for example, 45 degrees or 135 degrees. The polarization characteristics of the display screen make the optical signal carrying the fingerprint information different with the angle between the incident surface and the polarization direction of the screen. When the incident plane is parallel to the polarization direction of the screen, the intensity of the light signal is the largest, and when the incident plane is perpendicular to the polarization direction of the screen, the signal amount is the smallest. In other words, the best light is received along the screen polarization direction, and the worst light is received perpendicular to the screen polarization direction.

Due to the polarization characteristics of the display screen, the intensity of the optical signal guided by the polarized light guide channel is greater than the intensity of the optical signal guided by the unpolarized light guide channel, so the optical signal received by the photosensitive areas corresponding to the polarized light guide channel and the unpolarized light guide channel There are differences in intensities, which in turn result in differences between fingerprint data generated from optical signals, in other words, differences in information carried by different fingerprint data. Based on these fingerprint data, fingerprint feature information indicating the ridge-valley line feature and polarization feature of the fingerprint to be detected can be determined. Thus, based on these fingerprint feature information, it can be determined that the fingerprint to be detected is a real fingerprint or a 2.5D fake fingerprint.

S302. Input the fingerprint feature information into a pre-trained decision tree model to obtain a score for indicating that the fingerprint to be detected is a true fingerprint.

Among them, the decision tree model is trained according to the fingerprint feature information of each fingerprint sample in the fingerprint sample set and the authenticity result of each fingerprint sample. The fingerprint feature information of each fingerprint sample and the fingerprint feature information of the fingerprint to be detected have the same feature type. For example, the feature types of fingerprint feature information include variation coefficients (including ridge variation coefficients and valley variation coefficients) used to indicate the uniformity of the fingerprint, signal intensity ratios used to indicate the polarization characteristics of the fingerprint, grayscale values used to indicate the fingerprint Grayscale similarity of degree distribution characteristics, or any combination thereof. It should be understood that the feature type of the fingerprint feature information here is illustrated by way of example, and this embodiment is not limited thereto.

The fingerprint samples in the fingerprint sample set may include, for example, real fingers and fake fingers in various scenarios, for example, real fingers and fake fingers in low temperature scenarios, high temperature scenarios, normal temperature scenarios, oily, dry fingers and/or wet fingers finger lamp. Correspondingly, the fingerprint feature information of the fingerprint sample is the fingerprint feature information determined according to the fingerprint data corresponding to the fingerprint samples in various scenarios.

When training the decision tree model, each feature type of the fingerprint feature information can be regarded as a decision node, and each decision node is used to classify the fingerprint samples, thereby training the generated decision tree model. The decision tree model can include and The judgment threshold and weight corresponding to each feature type.

During fingerprint identification, the fingerprint feature information generated according to the fingerprint data corresponding to the fingerprint to be detected is input into the pre-trained decision tree model, and the pre-trained decision tree model generates the score of the fingerprint to be detected according to the predetermined judgment threshold and weight .

For example, if the feature types of fingerprint feature information include ridge line variation coefficient, valley line variation coefficient, signal intensity ratio and grayscale similarity, when training the decision tree model, the ridge corresponding to each fingerprint sample in the fingerprint sample set can be extracted. The line variation coefficient, valley line variation coefficient, signal intensity ratio and grayscale similarity are used as the fingerprint feature information corresponding to the fingerprint samples, and the extracted fingerprint feature information of each fingerprint sample and the authenticity structure corresponding to each fingerprint sample are input into decision-making The tree model is trained to obtain a trained prediction model. The trained prediction model includes a first judgment threshold and a first weight corresponding to the coefficient of variation of the ridge line, a second judgment threshold and a second weight corresponding to the coefficient of variation of the valley line, and a signal intensity ratio. The corresponding third judgment threshold and the third weight, and the fourth judgment threshold and the fourth weight corresponding to the grayscale similarity. When identifying the fingerprint to be detected, the coefficient of variation of the ridge line, the coefficient of variation of the valley line, the signal intensity ratio and the grayscale similarity of the fingerprint to be detected can be extracted. The trained decision tree model is based on the coefficient of variation of the ridge line of the fingerprint to be detected and the first The comparison result of the judgment threshold, the comparison result of the coefficient of variation of the ridge line of the fingerprint to be detected and the second judgment threshold, the comparison result of the signal intensity ratio of the fingerprint to be detected and the third judgment threshold, the grayscale similarity of the fingerprint to be detected and the fourth The comparison result of the judgment thresholds and the weight corresponding to each judgment condition determine the score used to indicate that the fingerprint to be detected is a true fingerprint.

S303. Determine the authenticity of the fingerprint to be detected according to the comparison result between the score and the preset fingerprint threshold.

Specifically, when the score of the fingerprint to be detected is greater than the preset fingerprint threshold, it is determined that the fingerprint to be detected is a true fingerprint. When the score of the fingerprint to be detected is less than the preset fingerprint threshold, it is determined that the fingerprint to be detected is a fake fingerprint.

The preset fingerprint threshold can be flexibly set according to the user's security level requirements. For example, in an application scenario with low security level requirements, such as an application scenario in which an electronic device is unlocked through fingerprint verification, the preset fingerprint threshold can be set Set it relatively low, such as 0.5. However, in an application scenario with high security level requirements, such as an application scenario in which fee payment is made through fingerprint verification, the preset fingerprint threshold can be set relatively high, such as 0.7.

In the embodiment of the present application, since the multi-optical path structure at least includes a polarized light guide channel with a projection parallel to the polarization direction of the screen and a non-polarized light guide channel perpendicular to the polarization direction of the screen on the plane where the photosensitive area is located, the multi-optical path guided by the multi-optical path structure The fingerprint data corresponding to the road light signal can determine the fingerprint feature information used to indicate the ridge-valley line feature and polarization feature of the fingerprint to be detected. By inputting the feature information into the pre-trained decision tree model, the output of the decision tree model is used. Based on the comparison result of the score indicating that the fingerprint to be detected is a real fingerprint and the preset fingerprint threshold, it can be determined whether the fingerprint to be detected is a real fingerprint or a fake fingerprint with a three-dimensional depth feature, which improves the security of fingerprint detection.

Based on the embodiment shown in FIG. 3 , further, the embodiment of the present application provides another fingerprint identification method. As shown in FIG. 4 , the fingerprint identification method includes:

S401 , using the first preset data group and the second preset data group to perform regularization processing on the fingerprint raw data corresponding to the fingerprint to be detected to obtain fingerprint data.

Wherein, the first preset data set and the second preset data set are respectively data sets obtained during the calibration phase of the fingerprint sensor and used for calibrating the fingerprint raw data of the fingerprint sensor.

The fingerprint original data may include N groups of fingerprint original data, where N is a positive integer greater than or equal to 2. The specific size of N is related to the number of polarized light guide channels and non-polarized light guide channels included in each light guide channel group in the multi-optical path structure. The N groups of fingerprint raw data may be fingerprint data obtained from the multi-path optical signals guided by part or all of the polarized light-guiding channels and the non-polarized light-guiding channels in the multi-optical path structure without regularization processing.

During the fingerprint recognition under the screen, the light-emitting layer of the display screen will emit a screen light signal to the finger placed on the screen. The screen light signal is at the interface between the display screen and the air layer of the fingerprint valley, the fingerprint valley and the fingerprint ridge. The reflected light enters the display screen and is received by the fingerprint sensor after multiple refraction, reflection and diffraction. In addition, a part of the screen light signal (also called screen light leakage) emitted by the light-emitting layer of the display screen is directly received by the fingerprint sensor through multiple refraction, reflection and diffraction. The fingerprint sensor generates fingerprint raw data according to the received optical signal. Since the light reflectivity of the fingerprint ridge and the fingerprint valley is different, the generated fingerprint raw data can reflect the fingerprint ridge and the fingerprint valley. However, the fingerprint raw data includes not only fingerprint information, but also interference information (hereinafter, also referred to as noise floor) such as background noise of the display screen (such as screen light leakage), and the noise floor of each fingerprint sensor is different. In order to eliminate the influence of the noise floor difference of the fingerprint sensor on the fingerprint original data, the fingerprint original data is regularized. Specifically, the original fingerprint data is normalized by using the first preset data set and the second preset data set obtained in the calibration stage of the fingerprint sensor, and the first preset data set and the second preset data set can usually be stored in In the base file generated during the fingerprint sensor calibration phase.

The first preset data set may be a data set obtained by simulating a user's finger by using the flesh-colored flat head fingerprint model 51 in the calibration stage of the fingerprint sensor. The flesh-colored flat head fingerprint model 51 is used to simulate a user's finger without fingerprints, that is, the flesh-colored flat head fingerprint model 51 is equivalent to a finger full of fingerprint valleys. As shown in Fig. 5a, when acquiring the first preset data set, the flesh-colored flat-head fingerprint model 51 can be pressed on the fingerprint collection area (ie, the partial area of the display screen 12 corresponding to the fingerprint sensor), and the fingerprint sensor can receive light according to the received light. The signal determines the first preset data set. Since the flesh-colored flat head fingerprint model 51 is equivalent to a finger full of fingerprint valleys, the first preset data set not only includes information related to the light reflected by the central concave surface of the flesh-colored flat head fingerprint model 51 , but also includes the background noise of the display screen 12 (for example, the light leakage information of the display screen 12) and other interference information.

The second preset data set may be a data set obtained by simulating a user's finger by using the black flat head fingerprint model 52 in the calibration stage of the fingerprint sensor. The black flat head fingerprint model 52 is used to simulate a pressed state without finger touch. As shown in FIG. 5b , when acquiring the second fingerprint data set, the black flat head fingerprint model 52 can be pressed in the fingerprint collection area, and the fingerprint sensor determines the second preset data set according to the received optical signal. Since the black flat-head fingerprint model 52 will absorb the light transmitted to the upper part of the display screen, the second fingerprint data only includes the background noise of the display screen (such as the light leakage information of the display screen 12) and other interference information, that is, only includes the background noise of the fingerprint sensor. .

By subtracting the second preset data set from the first preset data set, fingerprint data without noise floor can be obtained. In this embodiment, the first preset data set and the second preset data set are used to regularize the fingerprint raw data corresponding to the fingerprint to be detected, thereby eliminating the influence of the noise floor of different fingerprint sensors on the fingerprint data, and improving the fingerprint recognition efficiency. Accuracy. A possible regularization processing method is described below by taking the regularization processing of one group of fingerprint original data in the N groups of fingerprint original data as an example.

Here, for the convenience of description, the first preset data group and the second preset data group can be represented as H_Flesh and H_black respectively, a set of fingerprint raw data of the fingerprint to be detected is represented as Rawdata, and it is assumed that H_Flesh, H_black and Rawdata Both include T pieces of data, where T is the size of the fingerprint data collected by the fingerprint sensor, for example, it can be 120×120. If any fingerprint raw data in the group of fingerprint raw data is represented as Rawdata(t), the data corresponding to Rawdata(t) in the first preset data group and the second preset data group are represented as H_Flesh(t) and H_black (t), where 1≤t≤T, then the fingerprint data Ndata(t) corresponding to Rawdata(t) can be calculated by the regularization formula (1). The regularization formula (1) can be expressed as:

Ndata(t)=(Rawdata(t)-H_black(t))/(H_Flesh(t)-H_black(t))

In this way, fingerprint data corresponding to a set of fingerprint raw data can be calculated. It should be noted that the calculation method here is only to illustrate the specific principle of regularization processing, and matrix operations can be used in actual calculation to improve the processing speed.

It should be understood that the implementation manner of the above-mentioned regularization processing is only an example, and the specific implementation manner of the regularization processing is not limited in this embodiment, and the first preset data set and the second preset data set can also be used through other suitable data sets. The regularization processing method performs regularization processing on the original fingerprint data.

S402 , according to the fingerprint data corresponding to the fingerprint to be detected, determine fingerprint feature information for indicating the ridge-valley line feature and the polarization feature of the fingerprint to be detected.

In this embodiment, the fingerprint data includes N groups of fingerprint data, and the fingerprint feature information of the fingerprint to be detected can be directly determined according to the N groups of fingerprint data of the fingerprint to be detected. However, since the fingerprint data are obtained from multiple optical signals guided by different light guide channels, the angles of the light signals received by the photosensitive areas corresponding to different light guide channels are different. Therefore, N sets of fingerprint data and corresponding N fingerprints are generated. There will be some offset between the images.

In order to improve the accuracy of the extracted fingerprint feature information, optionally, as shown in FIG. 4 , in a possible implementation manner, according to the fingerprint data corresponding to the fingerprint to be detected, determine the ridge and valley lines used to indicate the fingerprint to be detected Fingerprint signature information for characteristics and polarization properties, including:

S4021, generating corresponding N fingerprint images according to N groups of fingerprint data;

For example, the maximum and minimum value quantization processing of the N groups of fingerprint data can be performed, and the N groups of fingerprint data can be normalized to the gray level range of the image, for example, between 0 and 255, so as to generate corresponding N fingerprint images. It should be understood that, in order to improve the clarity of the fingerprint image, other image processing processes may also be included when generating the fingerprint image according to the fingerprint data, which is not limited in this embodiment.

S4022, according to the fingerprint common area between any two fingerprint images in the N fingerprint images, determine the fingerprint common area to be used;

In this embodiment, before determining the fingerprint common area to be used, it is necessary to determine the fingerprint between any two fingerprint images in the N fingerprint images according to the offset between any two fingerprint images in the N fingerprint images Public area.

For example, when N is 1, according to the offset between the two fingerprint images, a fingerprint common area can be determined; when N is 2, according to the offset between the four fingerprint images, a total of Identify six fingerprint common areas.

The fingerprint common area refers to the common part of the corresponding two fingerprint images. The size of the common area of each fingerprint is the same. For example, the size of the fingerprint image is 120×120, and the size of the fingerprint common area can be 100×100. The offset between any two fingerprint images in the N fingerprint images is related to the direction of the light signal received by the corresponding photosensitive area. The two fingerprint images can be offset only in the horizontal direction or only in the vertical direction. Offset occurs, or can be offset both horizontally and vertically.

The process of determining the fingerprint common area between two fingerprint images will be described in detail below with reference to FIG. 6a and FIG. 6b. For the convenience of description, the offset between two fingerprint images is represented in the following coordinate system with the coordinates of the lower left corner of the fingerprint image as the center, the X axis as the horizontal direction, and the Y axis as the vertical direction.

Referring to Fig. 6a, when determining the fingerprint common area between the fingerprint image I1 and the fingerprint image I2, first, the reference feature point A is determined in the fingerprint image I1, then, matching is performed in the fingerprint image I2, and it is determined that the fingerprint image I1 matches the fingerprint image I1. The reference feature point A corresponds to the target feature point A'. As shown in Figure 6a, the target feature point A' in the fingerprint image I1 and the reference feature point A in the fingerprint image I2 are not offset in the x direction, and in the y direction, the target feature point A' is relative to the reference feature point. A is offset by Δy. According to the offset Δy between the fingerprint image I1 and the fingerprint image I2 in the y direction, the fingerprint common area between the fingerprint image I1 and the fingerprint image I2 can be segmented in the fingerprint image I2, as shown in the solid line box in the lower right corner of Figure 6a area shown. It should be understood that, according to the offset Δy of the fingerprint image I1 and the fingerprint image I2 in the y direction, the fingerprint common area (not shown) between the fingerprint image I1 and the fingerprint image I2 can also be segmented in the fingerprint image I1.

6b, in determining the common area between the fingerprint image I1 and the fingerprint image I3, in the same way as in FIG. 6a, first, the reference feature point A is determined in the fingerprint image I1, and then, matching is performed in the fingerprint image I3 , determine the target feature point A" corresponding to the reference feature point A in the fingerprint image I1. As shown in Figure 6b, the target feature point A' in the fingerprint image I1 and the reference feature point A" in the fingerprint image I3 are in the x direction. Offset Δx up, no offset occurs in the y direction. Therefore, according to the offset Δx between the fingerprint image I1 and the fingerprint image I2 in the x direction, the fingerprint common area between the fingerprint image I1 and the fingerprint image I3 can be segmented in the fingerprint image I1, as shown by the solid line in the lower right corner of Figure 6b the area shown in the box. It should be understood that, according to the offset Δx of the fingerprint image I1 and the fingerprint image I3 in the x direction, the fingerprint common area (not shown) between the fingerprint image I1 and the fingerprint image I3 can also be segmented in the fingerprint image I1.

It should be noted that the embodiments of FIG. 6a and FIG. 6b respectively only show three reference feature points for description. In practical applications, the number of reference feature points can be set according to actual needs. In addition, it should be understood that the common area of the two fingerprint images with offsets in both the X-axis and Y-axis directions can also be determined in the same manner. For the sake of brevity, details are not repeated here.

After determining the fingerprint common area between any two fingerprint images in the N fingerprint images, at least one fingerprint common area may be selected from the determined fingerprint common area as the fingerprint common area to be used.

The fingerprint common area to be used may be any selected fingerprint common area among the determined fingerprint common areas. Optionally, in an optional implementation manner, the common area of the fingerprint to be used includes the first fingerprint image portion corresponding to the polarized light guide channel, and includes the second fingerprint image portion corresponding to the non-polarized light guide channel. The fingerprint common area of the fingerprint image part. Since the intensity of the optical signal guided by the polarized light guide channel is quite different from the intensity of the optical signal guided by the unpolarized light guide channel, correspondingly, the fingerprint data corresponding to the first fingerprint image part and the fingerprint corresponding to the second fingerprint image part The degree of discrimination of the data is large, so the fingerprint feature information can be better extracted according to the common area of the fingerprint to be used.

S4023. Determine fingerprint feature information according to the fingerprint common area to be used.

Specifically, according to the different feature types of the fingerprint feature information, the fingerprint feature information can be determined according to the pixel data and/or the corresponding fingerprint data in the common area of the fingerprint to be used.

Optionally, in an embodiment of the present application, as shown in FIG. 8 , the fingerprint feature information is determined according to the fingerprint common area to be used, including:

S801. Identify the ridges and valleys in the public area of the fingerprint to be used, and determine the ridges and valleys of the fingerprints in the public area of the fingerprint to be used.

S802. Determine the coefficient of variation of the ridge line according to the fingerprint data corresponding to the ridge line of the fingerprint, and determine the coefficient of variation of the valley line according to the fingerprint data corresponding to the valley line of the fingerprint.

The coefficient of variation of the ridge line is used to indicate the uniformity of the ridge line of the fingerprint to be detected, and the coefficient of variation of the valley line is used to indicate the uniformity of the valley line of the fingerprint to be detected.

并且将谷线标准差与谷线平均值之比作为谷线变异系数

Specifically, according to the fingerprint data corresponding to the fingerprint ridge line, the ridge line standard deviation std _v and the ridge line average value avg _v are calculated, and according to the fingerprint data corresponding to the fingerprint valley line, the valley line standard deviation std _r and the valley line average value avg are calculated _r ; use the ratio of the ridge standard deviation to the ridge mean as the ridge variation coefficient

And take the ratio of the standard deviation of the valley line to the mean value of the valley line as the coefficient of variation of the valley line

S803. Determine the coefficient of variation of the ridge line and the coefficient of variation of the valley line as fingerprint feature information.

In this embodiment, since the 2.5D fake fingerprint is affected by the molding process, the consistency between the fingerprint valley line and the fingerprint ridge line is relatively high. Therefore, the fingerprint sensor obtained for the 2.5D fake fingerprint corresponds to the fingerprint ridge valley line. The volatility of the fingerprint data is smaller than that of the fingerprint data corresponding to the fingerprint ridge and valley lines obtained for the real finger. Specifically, as shown in the figure in the lower left corner of the fingerprint profile in Figure 7, the height of the ridge and the depth of the valley in the 2.5D fake fingerprint are the same, so the uniformity of the ridge and valley of the 2.5D is better, and accordingly , the coefficient of variation of the ridge line and the valley line of the 2.5D fake fingerprint are smaller. As shown in the figure in the lower right corner of the fingerprint profile in Figure 7, in a real fingerprint, each ridge line is the highest in the middle, and gradually becomes smaller toward both sides, and the middle of each valley line is the lowest, and gradually increases toward both sides, Therefore, the uniformity of the ridges and valleys of the real fingerprints is poor, and the coefficients of variation of the ridges and valleys of the real fingerprints are therefore larger.

Since the coefficient of variation of the ridge line and the coefficient of variation of the valley line of the real fingerprint is greater than that of the 2.5D fake fingerprint, after determining the coefficient of variation of the ridge line and the valley line corresponding to the fingerprint to be detected, the The coefficient of variation of the ridge line and the coefficient of variation of the valley line are respectively compared with the corresponding first preset thresholds. If it is greater than the first preset threshold, it means that the fingerprint to be detected is a true fingerprint, and if it is less than the first preset threshold, it means that the fingerprint to be detected is to be detected. Fingerprints are fake fingerprints.

It should be noted that each fingerprint common area corresponds to two sets of fingerprint data. For example, the fingerprint data corresponding to the fingerprint common area of the kth fingerprint image and the pth fingerprint image includes the fingerprint data corresponding to the fingerprint common area in the kth fingerprint image. The fingerprint data of , and the fingerprint data corresponding to the fingerprint common area in the p-th fingerprint image. Therefore, when determining the coefficient of variation of the ridge line and the coefficient of variation of the valley line, any one or two sets of fingerprint data in the two groups of fingerprint data corresponding to the common area of the fingerprint to be used can be selected to determine the coefficient of variation of the ridge line and the valley line.

For example, if the fingerprint common area to be used is the fingerprint common area between the kth fingerprint image and the pth fingerprint image, in a possible implementation manner, the fingerprint common area in the kth fingerprint image may correspond to The ridge line variation coefficient and valley line variation data are determined as fingerprint feature information to reduce the amount of calculation.

For another example, if the fingerprint common area to be used is the fingerprint common area between the kth fingerprint image and the pth fingerprint image, and the kth fingerprint image is the fingerprint image corresponding to the optical signal guided by the polarized light guide channel, the The p fingerprint images are fingerprint images guided by the optical signal corresponding to the non-polarized light guide channel. In another possible implementation, the fingerprint data corresponding to the fingerprint common area in the kth fingerprint image and the pth fingerprint The coefficient of variation of the ridge line and the coefficient of variation of the valley line are determined respectively according to the fingerprint data corresponding to the fingerprint common area in the fingerprint image as fingerprint feature information, so as to improve the accuracy of fingerprint identification. For convenience of description, the determined ridge line variation coefficient and valley line variation coefficient are referred to as the first ridge line variation coefficient, the first valley line variation coefficient, the second ridge line variation coefficient and the second valley line variation coefficient, respectively.

Specifically, according to the fingerprint data corresponding to the fingerprint ridges in the fingerprint common area in the kth fingerprint image, the standard deviation of the first ridges and the average value of the first ridges are calculated. According to the fingerprint data corresponding to the fingerprint valley line in the fingerprint common area in the kth fingerprint image, the standard deviation of the first valley line and the average value of the first valley line are calculated. The ratio of the first ridge standard deviation to the first ridge mean is used as the first ridge coefficient of variation, and the ratio of the first valley standard deviation to the first valley mean is used as the first valley coefficient of variation.

According to the fingerprint data corresponding to the fingerprint ridges in the fingerprint common area in the p-th fingerprint image, the second ridge standard deviation and the second ridge average are calculated. According to the fingerprint data corresponding to the fingerprint valley line in the fingerprint common area in the p-th fingerprint image, the second valley line standard deviation and the second valley line average value are calculated. The ratio of the second ridge line standard deviation to the second ridge line mean is used as the second ridge line variation coefficient, and the ratio of the second valley line standard deviation to the second valley line mean value is used as the second valley line variation coefficient.

Since the intensity of the optical signal guided by the polarized light guide channel is higher than that of the optical signal guided by the non-polarized light guide channel, the fingerprint data corresponding to the fingerprint common area in the kth fingerprint image and the fingerprint in the pth fingerprint image are common The fingerprint data corresponding to the region has nonlinear differences and different degrees of data discrimination. According to the two sets of fingerprint data with nonlinear relationship and different degrees of data discrimination, the ridge line variation coefficient and the valley line variation coefficient are respectively determined as fingerprint feature information, which can be better. Identify the fingerprint to be detected as a real fingerprint or a 2.5D fake fingerprint, thereby improving the accuracy of fingerprint detection.

In addition, since the refractive index of the air is n1=1, the refractive index of the real fingerprint is n2=1.3, and the refractive index of the screen of the display screen is n3=1.4. The real fingerprint is an optically sparse medium relative to the screen of the display screen, and correspondingly, the screen of the display screen is an optically dense medium relative to the real fingerprint. As shown in FIG. 9 , when the real fingerprint is pressed on the fingerprint collection area of the display screen for fingerprint identification, the light-emitting layer of the display screen 13 emits a screen light signal including S waves and P waves, and the screen light signal is displayed on the display screen 13 . Reflection occurs at the interface with the fingerprint valley air layer, the fingerprint valley line 112 and the fingerprint ridge line 111 . Specifically, when the fingerprint ridge line of the real fingerprint is in contact with the screen of the display screen, the light goes from an optically sparser medium to an optically denser medium, and the relative refractive index of the real fingerprint is 0.92. According to Fresnel's law, the reflectance of the S wave is Rs～=0.116%, and the reflectance of the P wave is Rp～=1.14%.

2.5D fake fingerprints are usually made of white glue, wood glue, black glue, silica gel, beautifying agent, paint or glue, etc. The refractive index n4=1.6~1.8, which is quite different from the refractive index of real fingerprints. For the 2.5D fake fingerprint, the 2.5D fake fingerprint is an optically dense medium relative to the screen of the display screen, and correspondingly, the screen of the display screen is an optically sparser medium relative to the 2.5D fake fingerprint. When the 2.5D finger is pressed on the fingerprint collection area of the display screen for fingerprint recognition, the fingerprint ridge of the 2.5D fake fingerprint is in contact with the screen of the display screen. Refractive index 1.21. Assuming that the refractive index n4=1.7 of the 2.5D false fingerprint, according to the Fresnel principle, the reflectivity Rs of the S wave and the reflectivity of the P wave both tend to be 0.02% at this time. Therefore, there is a difference in the intensity of the reflected light signal at the fingerprint ridge line between the real fingerprint and the 2.5D fake fingerprint.

At the same time, since the S wave in the light signal returned from the display screen is filtered by the polarization unit inside the display screen. As shown in Figure 9, for a real fingerprint, since the reflectivity of the S wave is Rs～=0.116% and the reflectivity of the P wave is Rp～=1.14%, the intensity of the optical signal guided by the polarized light guide channel is greater than that of the unpolarized light guide The intensity of the channel-guided optical signal. However, for false fingerprints, since the reflectivity of the s-wave Rs and the reflectivity of the P-wave both tend to be 0.02%, the intensity of the reflected light is weak, and the intensity of the optical signal guided by the polarized light guide channel is different from that of the unpolarized light guide channel. The intensities of the guided optical signals are approximately equal. Therefore, it can be determined whether the fingerprint to be detected is a real fingerprint or a 2.5D fake fingerprint according to the ratio of the intensity of the optical signal guided by the unpolarized light guide channel corresponding to the fingerprint to be detected and the intensity of the optical signal guided by the polarized light guide channel as the fingerprint feature information . If the ratio of the intensity of the optical signal guided by the unpolarized light guide channel corresponding to the fingerprint to be detected to the intensity of the optical signal guided by the polarized light guide channel is less than or greater than the corresponding second preset threshold, such as 1, it means that the fingerprint to be detected is real fingerprints. On the contrary, if the ratio of the intensity of the optical signal guided by the unpolarized light guide channel corresponding to the fingerprint to be detected and the intensity of the optical signal guided by the polarized light guide channel is approximately equal to the corresponding second preset threshold, it means that the fingerprint to be detected is 2.5D Fake fingerprints.

Optionally, as shown in FIG. 10 , in an embodiment of the present application, the number of fingerprint public areas to be used is M, where M is a positive integer greater than or equal to 1, and the fingerprint is determined according to the fingerprint public areas to be used. Characteristic information, including:

S1001, according to the first fingerprint data corresponding to the first fingerprint image part contained in the ith fingerprint common area to be used and the second fingerprint data corresponding to the second fingerprint image part contained in the ith fingerprint common area to be used. A signal strength ratio, where i is a positive integer less than or equal to M.

Wherein, the first signal intensity ratio is used to indicate the first polarization characteristic of the fingerprint to be detected.

S1002. Determine the first signal intensity ratio as fingerprint feature information.

Specifically, in an implementation manner, the first polarized average value may be determined according to the first fingerprint data, and the first non-polarized average value may be determined according to the second fingerprint data; according to the first non-polarized average value and the first polarized average value The ratio of the values determines the first signal strength ratio.

It should be noted that, in a possible implementation manner, the ratio of the first non-polarized average value to the first polarized average value may be the ratio of the first non-polarized average value to the first polarized average value. In another possible implementation manner, the ratio of the first non-polarized average value to the first polarized average value may be the ratio of the first polarized average value to the first non-polarized average value.

In this embodiment, for a real fingerprint, the intensity of the optical signal guided by the polarized light guide channel is greater than that of the optical signal guided by the non-polarized light guide channel; for a fake fingerprint, the intensity of the optical signal guided by the polarized light guide channel The intensity is approximately equal to that of the optical signal guided by the unpolarized light guide channel. Therefore, if the first signal strength ratio is less than or greater than the corresponding third preset threshold, such as 1, it means that the fingerprint to be detected is a true fingerprint. If the first signal strength ratio is approximately equal to the third preset threshold, it means that the fingerprint to be detected is a 2.5D fake fingerprint.

Optionally, in another embodiment of the present application, when the number M of fingerprint common areas to be used is greater than or equal to 2, the fingerprint feature information is determined according to the fingerprint common areas to be used, and further includes:

S1003: Determine the second signal intensity ratio according to the third fingerprint data corresponding to the fingerprint image part of the jth fingerprint common area to be used and the fourth fingerprint data corresponding to the fingerprint image part of the jth fingerprint common area to be used, wherein , j is a positive integer not equal to i and less than or equal to M.

Wherein, the second signal strength is used to indicate the second polarization characteristic of the fingerprint to be detected.

S1004. Determine the second signal intensity ratio as fingerprint feature information.

Specifically, in an implementation manner, the second polarization average value may be determined according to the third fingerprint data; the second non-polarization average value may be determined according to the fourth fingerprint data; ratio, which determines the second signal strength ratio.

It should be noted that when the first signal intensity ratio is the ratio of the first non-polarized average value to the first polarized average value, the second signal intensity ratio is the ratio of the second polarized average value to the second non-polarized average value; on the contrary , if the first signal intensity ratio is the ratio of the first polarized average value to the first non-polarized average value, and the second signal intensity ratio is the ratio of the second non-polarized average value to the second polarized average value.

In this embodiment, for a real fingerprint, the intensity of the optical signal guided by the polarized light guide channel is smaller or greater than the intensity of the optical signal guided by the non-polarized light guide channel; for a fake fingerprint, the intensity of the light guided by the polarized light guide channel The intensity of the signal is approximately equal to the intensity of the optical signal guided by the unpolarized light guide channel. Therefore, for a real fingerprint, the first signal strength ratio is less than the corresponding third preset threshold, and the second signal strength ratio is greater than the corresponding fourth preset threshold, or the first signal strength ratio is greater than the corresponding third preset threshold, and The second signal strength ratio is smaller than the corresponding fourth preset threshold. For fake fingerprints, the first signal strength ratio is approximately equal to the third predetermined threshold, and the second signal strength ratio is approximately equal to the fourth predetermined threshold. By combining the first signal intensity ratio and the second signal intensity ratio, a real fingerprint and a 2.5D fake fingerprint can be better distinguished, thereby improving the accuracy of fingerprint detection.

Optionally, in an embodiment of the present application, determining fingerprint feature information according to the fingerprint common area to be used includes:

S1101. Determine a hash value list corresponding to the common area of the fingerprint to be used according to the pixel data of the common area of the fingerprint to be used.

S1102: Determine the grayscale similarity according to the Hamming distance between the hash value lists corresponding to the common area of the fingerprint to be used. The grayscale similarity is used to indicate the grayscale distribution characteristics of the fingerprint to be detected.

S1103. Determine the grayscale similarity as fingerprint feature information.

Referring to Figures 12a to 12b, Figure 12a shows a corresponding grayscale distribution of a fingerprint image of an exemplary real fingerprint. It can be seen that the grayscale of the real fingerprint is obviously widely distributed between 0 and 255. However, affected by the molding process, the consistency of fingerprint ridges and valleys of 2.5D fake fingerprints is high, and correspondingly, the uniformity of fingerprint ridges and valleys of 2.5D fake fingerprints is high. As shown in FIG. 12b, FIG. 12b shows the grayscale distribution corresponding to the fingerprint image of an exemplary fake fingerprint, and it can be seen that the grayscale distribution of the fake fingerprint is concentrated. For example, as shown in Fig. 12b, the grayscale distribution of fake fingerprints is between 0 and 190, and is mainly concentrated between 70 and 125. Based on the difference in gray level between the fingerprint images of the real fingerprint and the 2.5D fake fingerprint, the grayscale similarity can be used to characterize the grayscale distribution characteristics of the fingerprint to be detected, and the real fingerprint and the 2.5D fake fingerprint can be distinguished according to the grayscale similarity. .

Specifically, the fingerprint common area to be used may be all the fingerprint common areas or a part of the fingerprint common areas in the fingerprint common areas between pairs of N fingerprint images. Each fingerprint common area to be used corresponds to two fingerprint images. According to the pixel data of each fingerprint common area to be used, two hash value lists can be determined.

Optionally, the hash value list may include a mean hash value list and/or a difference hash value list. For the specific method of obtaining the mean hash value list and/or the difference hash value list, you can refer to the ahash and dhash algorithms commonly used in the image field.

Taking the hash value list as the average hash value list as an example, the corresponding pixel average value can be obtained according to the pixel data in the public area of each fingerprint; each pixel data in the fingerprint public area is compared with the corresponding pixel average value. For comparison, if it is greater than or equal to the corresponding pixel average value, set the value in the corresponding hash value list to 1, and if it is less than the corresponding pixel average value, set the value in the corresponding hash value list to 0.

After determining the two hash value lists corresponding to the common area of the fingerprint to be used, the Hamming distance between the two hash value lists can be calculated as the grayscale similarity.

In this embodiment, since the uniformity of the fingerprint ridge lines and the fingerprint valley lines of the 2.5D fake fingerprint is relatively high, the grayscale distribution of the corresponding fingerprint image is relatively concentrated. Therefore, the Hamming distance calculated according to the fingerprint image of the 2.5D fake fingerprint is relatively high. Small, correspondingly, the grayscale similarity corresponding to the 2.5D fake fingerprint is higher. On the contrary, the uniformity of the fingerprint ridge lines and fingerprint valley lines of the real fingerprint is lower than that of the 2.5D fake fingerprint, and the corresponding grayscale distribution of the fingerprint image is relatively wide. Therefore, the Hamming distance calculated according to the fingerprint image of the real fingerprint is larger, and accordingly , the grayscale similarity of real fingerprints is low. After obtaining the grayscale similarity of the fingerprint to be detected, the grayscale similarity can be compared with the corresponding preset threshold. If the grayscale similarity is less than the preset threshold, it means that the grayscale similarity is relatively high, and it can be determined that the grayscale similarity is to be detected. The fingerprint is a 2.5D fake fingerprint. If it is higher than the preset threshold, it means that the grayscale similarity is low, and it can be determined that the fingerprint to be detected is a real fingerprint.

It should be understood that, in order to improve the calculation speed, before determining the hash list corresponding to the public area of the fingerprint to be used according to the pixel data of the public area of the fingerprint to be used, other image processing may also be performed on the public area of the fingerprint to be used. The fingerprint common area is scaled, and a hash value list corresponding to the fingerprint common area to be used is determined according to the processed fingerprint common area.

For ease of understanding, the method for determining the grayscale similarity is hereinafter taken as the fingerprint common area to be used is the fingerprint common area between the kth fingerprint image and the pth fingerprint image, and the grayscale similarity is aHash similarity. Explain in detail. Specifically, the method includes:

S1201a, performing image scaling on the fingerprint common area of the kth fingerprint image;

For example, the size of the fingerprint common area of the kth fingerprint image is 100×100, and the size of the scaled fingerprint common area is 60×60. By performing image scaling on the fingerprint common area, the amount of computational data can be reduced and the processing speed can be improved.

S1202a: Calculate the pixel average value of the pixel data in the fingerprint common area of the k-th fingerprint image after scaling.

S1203a, compare the pixel data of the fingerprint common area of the kth fingerprint image after scaling with the pixel average value, if the pixel data is greater than or equal to the pixel average value, then add the first hash value list corresponding to the kth fingerprint image in the first hash value list The corresponding value of is set to 1. If the pixel data is greater than or equal to the pixel average, the corresponding value in the first hash value list is set to 0.

In the same way, the p-th fingerprint image is processed through S1201b, S1202b and S1203b to obtain a second hash value list corresponding to the p-th fingerprint image. The processing methods of S1201a, S1202a, and S1203a are similar to those of S1201b, S1202b, and S1203b, respectively, and will not be repeated here. In addition, S1201a and S1201b, S1202a and S1202b, and S1203a and S1203b can be executed in parallel, which is not limited in this application.

S1205. Calculate the Hamming distance between the first hash value list and the second hash value list as the grayscale similarity between the kth fingerprint image and the pth fingerprint image.

If the Hamming distance calculated in S1205 is smaller, it means that the grayscale similarity between the kth fingerprint image and the pth fingerprint image is higher, and the fingerprints to be detected corresponding to the kth fingerprint image and the pth fingerprint image are: The higher the probability of a 2.5D fake fingerprint. On the contrary, the probability that the fingerprints to be detected corresponding to the kth fingerprint image and the pth fingerprint image are true fingerprints is higher.

In the same way, the grayscale similarity between any other two fingerprint images in the N fingerprint images can be calculated as fingerprint feature information, which is not limited in this application.

S403. Obtain the score of the fingerprint to be detected according to the fingerprint feature information as the input of the pre-trained decision tree model.

It should be noted that, in this embodiment, the fingerprint feature information obtained according to the 2N sets of fingerprint data of the fingerprint to be detected may include, for example, the first ridge variation coefficient, the first valley variation coefficient, the first ridge variation coefficient, the first valley variation coefficient The line variation coefficient, the first signal intensity ratio, the second signal intensity ratio, the grayscale similarity, or any combination thereof, are not limited in this embodiment.

S404, according to the comparison result of the score of the fingerprint to be detected and the preset fingerprint threshold, determine the authenticity of the fingerprint to be detected.

The above steps S403 and S404 are the same as the working principles of S302 and S303 in the embodiment shown in FIG. 3 , and will not be repeated here.

In the embodiment of the present application, since the multi-optical path structure includes N polarized light guide channels parallel to the polarization direction of the screen and N non-polarized light guide channels perpendicular to the screen polarization direction on the plane where the photosensitive area is located, according to the multi-optical path The structure-guided 2N-path optical signals correspond to 2N sets of fingerprint data, which can be used to determine the coefficient of variation of the ridge line, the coefficient of variation of the valley line, the first signal intensity ratio, the second signal intensity ratio and/or the grayscale similarity, etc., which can be used to determine the fingerprint to be detected It is the fingerprint feature information of a real fingerprint or a 2.5D fake fingerprint. By inputting the feature information into a pre-trained decision tree model, the output of the decision tree model is used to indicate that the fingerprint to be detected is a true fingerprint. The score and the preset fingerprint threshold are calculated. By comparing the results, it can be determined whether the fingerprint to be detected is a real fingerprint or a fake fingerprint with three-dimensional depth features, which improves the security of fingerprint detection.

FIG. 13 further provides a fingerprint identification device according to an embodiment of the present application, and the fingerprint identification device is configured to execute the fingerprint identification method provided by any of the above method embodiments. As shown in Figure 13, the fingerprint identification device includes:

The feature extraction module 1301 is used to determine the fingerprint feature information used to indicate the ridge-valley line feature and the polarization feature of the fingerprint to be detected according to the fingerprint data corresponding to the fingerprint to be detected, wherein the fingerprint data is the multi-optical path guided by the fingerprint sensor according to the multi-optical path structure. The multi-optical path structure at least includes a polarized light guide channel with projection parallel to the screen polarization direction and a non-polarized light guide channel perpendicular to the screen polarization direction on the plane where the photosensitive area is located;

The score calculation module 1302 is used to input the fingerprint feature information into the pre-trained decision tree model to obtain a score for indicating that the fingerprint to be detected is a true fingerprint;

The authenticity fingerprint determination module 1303 is configured to determine the authenticity of the fingerprint to be detected according to the comparison result between the score and the preset fingerprint threshold.

Optionally, in an embodiment of the present application, the fingerprint identification device further includes a data regularization module, configured to use the first preset data set and the second preset data set to regularize the fingerprint raw data of the fingerprint to be detected. process to obtain fingerprint data, wherein the first preset data set and the second preset data set are data sets obtained during the calibration phase of the fingerprint sensor and used for calibrating the fingerprint raw data of the fingerprint sensor.

Optionally, in an embodiment of the present application, the fingerprint data corresponding to the fingerprint to be detected includes N groups of fingerprint data, and the feature extraction module 1301 is further configured to:

Generate corresponding N fingerprint images according to N groups of fingerprint data;

According to the fingerprint common area between any two fingerprint images in the N fingerprint images, determine the fingerprint common area to be used;

The fingerprint feature information is determined according to the fingerprint common area to be used.

Optionally, in an embodiment of the present application, the common area of the fingerprint to be used is the first fingerprint image part corresponding to the polarized light guide channel, and the second fingerprint image part corresponding to the non-polarized light guide channel. Fingerprint public area.

Optionally, in an embodiment of the present application, the feature extraction module 1301 is further configured to:

Identify the ridges and valleys in the public area of the fingerprint to be used, and determine the ridges and valleys of the fingerprints in the public area of the fingerprint;

Determine the ridge line variation coefficient according to the fingerprint data corresponding to the fingerprint ridge line, and determine the valley line variation coefficient according to the fingerprint data corresponding to the fingerprint valley line;

The ridge line variation coefficient and the valley line variation coefficient are determined as fingerprint feature information.

Optionally, in an embodiment of the present application, the feature extraction module 1301 is further configured to:

According to the fingerprint data corresponding to the fingerprint ridge line, calculate the ridge line standard deviation and the ridge line average value, and according to the fingerprint data corresponding to the fingerprint valley line, calculate the valley line standard deviation and the valley line average value;

The coefficient of variation of the ridges is determined from the ratio of the standard deviation of the ridges to the mean of the ridges, and the coefficient of variation of the valleys is determined from the ratio of the standard deviation of the valleys to the mean of the valleys.

Optionally, in an embodiment of the present application, the number of fingerprint public areas to be used is M, where M is a positive integer greater than or equal to 1, and the feature extraction module 1301 is further configured to:

The first signal is determined according to the first fingerprint data corresponding to the first fingerprint image part contained in the ith fingerprint common area to be used and the second fingerprint data corresponding to the second fingerprint image part contained in the ith fingerprint common area to be used Intensity ratio, where i is a positive integer less than or equal to M, and the first signal intensity ratio is used to indicate the first polarization characteristic of the fingerprint to be detected.

The first signal strength ratio is determined as fingerprint feature information.

Optionally, in an embodiment of the present application, the feature extraction module 1301 is specifically configured to:

determining a first polarized average value from the first fingerprint data, and determining a first non-polarized average value from the second fingerprint data;

The first signal intensity ratio is determined based on the ratio of the first unpolarized average value to the first polarized average value.

Optionally, in an embodiment of the present application, when the number M of fingerprint common areas to be used is greater than or equal to 2, the feature extraction module 1301 is further configured to:

The second signal intensity ratio is determined according to the third fingerprint data corresponding to the first fingerprint image part of the jth fingerprint common area to be used and the fourth fingerprint data corresponding to the second fingerprint image part of the jth fingerprint common area to be used , where j is a positive integer not equal to i and less than or equal to M, and the second signal strength is used to indicate the second polarization characteristic of the fingerprint to be detected;

The second signal strength ratio is determined as fingerprint feature information.

Optionally, in an embodiment of the present application, the feature extraction module 1301 is further configured to:

determining a second polarized average value from the third fingerprint data, and determining a second non-polarized average value from the fourth fingerprint data;

A second signal intensity ratio is determined based on the ratio of the second polarized average value to the second non-polarized average value.

Optionally, in an embodiment of the present application, the feature extraction module 1301 is further configured to:

According to the pixel data of the fingerprint public area to be used, determine the hash value list corresponding to the fingerprint public area to be used;

According to the Hamming distance between the hash value lists corresponding to the common area of the fingerprint to be used, the grayscale similarity is determined, and the grayscale similarity is used to indicate the grayscale distribution characteristic of the fingerprint to be detected;

The grayscale similarity is determined as fingerprint feature information.

Optionally, in an embodiment of the present application, the hash value list includes an average hash value list and/or a differential hash value list.

The fingerprint identification device provided in this embodiment is used to implement the fingerprint identification method provided by the foregoing method embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here. In addition, for the functional realization of each module in the fingerprint identification device of this embodiment, reference may be made to the descriptions of the corresponding parts of the foregoing embodiments, which will not be repeated here.

Embodiments of the present application further provide an electronic device, a processor, a memory, a display screen, a touch control module, and a fingerprint identification device;

memory for storing computer programs;

The fingerprint identification device includes an optical image acquisition module, and the optical image acquisition module includes a pixel array;

The processor executes the computer program stored in the memory, so that the electronic device executes the fingerprint identification method provided in any of the foregoing method embodiments.

The processor may include a central processing unit (CPU, single-core or multi-core), a graphics processing unit (GPU), a microprocessor, an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, or multiple integrated circuits used to control program execution.

Memory may include Read-Only Memory (ROM) or other types of static storage devices that can store static information and instructions, Random Access Memory (RAM) or other types of storage devices that can store information and instructions Dynamic storage devices may also include Electrically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or other optical disk storage, optical disk storage ( including compact discs, laser discs, compact discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or capable of carrying or storing desired program code in the form of instructions or data structures and capable of being stored by a computer any other medium taken, but not limited to this. The memory can be set independently or integrated with the processor.

In a specific implementation, as an embodiment, the processor may include one or more CPUs. In a specific implementation, as an embodiment, the above electronic device may include multiple processors. Each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (eg, computer program instructions).

For the specific execution process of the electronic device, reference may be made to any method embodiment of the present application, and the implementation principle and technical effect thereof are similar, and details are not described herein again in this embodiment.

Embodiments of the present application further provide a storage medium, which includes a readable storage medium and a computer program, where the computer program is stored in the readable storage medium, and the computer program is used to implement the fingerprint identification method provided by any of the foregoing method embodiments.

The electronic devices in the embodiments of the present application exist in various forms, including but not limited to:

(1) Mobile communication equipment: This type of equipment is characterized by having mobile communication functions, and its main goal is to provide voice and data communication. Such terminals include: smart phones (eg iPhone), multimedia phones, functional phones, and low-end phones.

(2) Ultra-mobile personal computer equipment: This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has the characteristics of mobile Internet access. Such terminals include: PDAs, MIDs, and UMPC devices, such as iPads.

(3) Portable entertainment equipment: This type of equipment can display and play multimedia content. Such devices include: audio and video players (eg iPod), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

(4) Other electronic devices with data interaction function.

So far, specific embodiments of the present subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In certain embodiments, multitasking and parallel processing may be advantageous.

The systems, devices, modules or units described in the above embodiments may be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.

For the convenience of description, when describing the above device, the functions are divided into various units and described respectively. Of course, when implementing the present application, the functions of each unit may be implemented in one or more software and/or hardware.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

It should also be noted that the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device comprising a series of elements includes not only those elements, but also Other elements not expressly listed, or which are inherent to such a process, method, article of manufacture, or apparatus are also included. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article of manufacture, or device that includes the element.

It will be appreciated by those skilled in the art that the embodiments of the present application may be provided as a method, a system or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for related parts, please refer to the partial descriptions of the method embodiments.

The above descriptions are merely examples of the present application, and are not intended to limit the present application. Various modifications and variations of this application are possible for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims (26)

A fingerprint identification method, comprising: According to the fingerprint data corresponding to the fingerprint to be detected, the fingerprint feature information used to indicate the ridge-valley line feature and the polarization feature of the fingerprint to be detected is determined, wherein the fingerprint data is a multi-path optical signal guided by the fingerprint sensor according to the multi-optical path structure Obtained, the multi-optical path structure at least includes a polarized light guide channel with projection parallel to the screen polarization direction and a non-polarized light guide channel perpendicular to the screen polarization direction on the plane where the photosensitive region is located; Inputting the fingerprint feature information into a pre-trained decision tree model to obtain a score for indicating that the fingerprint to be detected is a true fingerprint; According to the comparison result between the score and the preset fingerprint threshold, the authenticity of the fingerprint to be detected is determined. The method of claim 1, further comprising: The fingerprint data of the fingerprint to be detected is normalized by using the first preset data set and the second preset data set, and the fingerprint data is obtained, wherein the first preset data set and the second preset data set are The preset data set is a data set obtained during the calibration phase of the fingerprint sensor and used to calibrate the fingerprint raw data of the fingerprint sensor. The method according to claim 1, wherein the fingerprint data corresponding to the fingerprint to be detected comprises N groups of fingerprint data, and N is a positive integer greater than or equal to 2; Described according to the fingerprint data corresponding to the fingerprint to be detected, determine the fingerprint feature information for indicating the ridge-valley line feature and the polarization feature of the fingerprint, including: Generate corresponding N fingerprint images according to the N groups of fingerprint data; According to the fingerprint common area between any two fingerprint images in the N fingerprint images, determine the fingerprint common area to be used; The fingerprint feature information is determined according to the to-be-used fingerprint common area. The method according to claim 3, wherein the common area of the fingerprint to be used is a first fingerprint image portion corresponding to the polarized light guide channel, and includes a first fingerprint image portion corresponding to the non-polarized light guide channel. The fingerprint common area of the two fingerprint image parts. The method according to claim 3 or 4, wherein the determining the fingerprint feature information according to the to-be-used fingerprint common area comprises: Identifying the ridges and valleys in the public area of the fingerprint to be used, and determining the ridges and valleys of the fingerprints in the public area of the fingerprints to be used; Determine the coefficient of variation of the ridge line according to the fingerprint data corresponding to the ridge line of the fingerprint, and determine the coefficient of variation of the valley line according to the fingerprint data corresponding to the valley line of the fingerprint; The ridge line variation coefficient and the valley line variation coefficient are determined as the fingerprint feature information. The method according to claim 5, wherein the determining the coefficient of variation of the ridge line according to the fingerprint data corresponding to the ridge line of the fingerprint, and determining the coefficient of variation of the valley line according to the fingerprint data corresponding to the valley line of the fingerprint, comprises: According to the fingerprint data corresponding to the fingerprint ridge line, calculate the ridge line standard deviation and the ridge line average value, and according to the fingerprint data corresponding to the fingerprint valley line, calculate the valley line standard deviation and the valley line average value; The coefficient of variation of the ridges is determined from the ratio of the standard deviation of the ridges to the mean value of the ridges, and the coefficient of variation of the valleys is determined from the ratio of the standard deviation of the valleys to the mean value of the valleys . The method according to claim 4, wherein the number of the fingerprint common areas to be used is M, where M is a positive integer greater than or equal to 1, and the fingerprint common area to be used is determined according to the Fingerprint feature information, including: According to the first fingerprint data corresponding to the first fingerprint image part contained in the ith fingerprint common area to be used and the second fingerprint data corresponding to the second fingerprint image part contained in the ith fingerprint common area to be used determining a first signal strength ratio, where i is a positive integer less than or equal to M, and the first signal strength ratio is used to indicate the first polarization characteristic of the fingerprint to be detected; The first signal strength ratio is determined as the fingerprint feature information. The method according to claim 7, wherein, according to the first fingerprint data corresponding to the first fingerprint image part contained in the ith fingerprint common area to be used and the ith fingerprint to be used Determining the first signal intensity ratio from the second fingerprint data corresponding to the second fingerprint image part contained in the common area includes: determining a first polarized average value from the first fingerprint data, and determining a first non-polarized average value from the second fingerprint data; The first signal intensity ratio is determined based on the ratio of the first unpolarized average value to the first polarized average value. The method according to claim 7, wherein when the number M of the fingerprint common areas to be used is greater than or equal to 2, the determining the fingerprint feature information according to the fingerprint common areas to be used, and further include: According to the third fingerprint data corresponding to the first fingerprint image part of the jth fingerprint common area to be used and the fourth fingerprint data corresponding to the second fingerprint image part of the jth fingerprint common area Two signal strength ratios, where j is a positive integer not equal to i and less than or equal to M, and the second signal strength is used to indicate the second polarization characteristic of the fingerprint to be detected; The second signal strength ratio is determined as the fingerprint feature information. The method according to claim 9, wherein the third fingerprint data corresponding to the first fingerprint image part of the jth common area of the fingerprint to be used and the jth fingerprint to be used are common The second signal intensity ratio is determined by the fourth fingerprint data corresponding to the second fingerprint image part of the area, including: determining a second polarized average value from the third fingerprint data, and determining a second non-polarized average value from the fourth fingerprint data; The second signal intensity ratio is determined based on the ratio of the second polarized average value to the second non-polarized average value. The method according to claim 3, wherein the determining the fingerprint feature information according to the to-be-used fingerprint common area comprises: According to the pixel data of the fingerprint public area to be used, determine the hash value list corresponding to the fingerprint public area to be used; According to the Hamming distance between the hash value lists corresponding to the common areas of the fingerprints to be used, the grayscale similarity is determined, and the grayscale similarity is used to indicate the grayscale distribution characteristics of the fingerprint to be detected; The grayscale similarity is determined as the fingerprint feature information. The method according to claim 11, wherein the hash value list comprises a mean hash value list and/or a differential hash value list. A fingerprint identification device, comprising: A feature extraction module is used to determine fingerprint feature information for indicating the ridge-valley line feature and polarization feature of the fingerprint to be detected according to the fingerprint data corresponding to the fingerprint to be detected, wherein the fingerprint data is the fingerprint sensor according to the multi-optical path structure Obtained from the guided multi-path optical signals, the multi-optical path structure at least includes a polarized light guide channel projected on the plane where the photosensitive area is located parallel to the screen polarization direction and a non-polarized light guide channel perpendicular to the screen polarization direction; A score calculation module for inputting the fingerprint feature information into a pre-trained decision tree model to obtain a score for indicating that the fingerprint to be detected is a true fingerprint; The authenticity fingerprint determination module is configured to determine the authenticity of the fingerprint to be detected according to the comparison result between the score and the preset fingerprint threshold. The apparatus according to claim 13, further comprising: a data regularization module for: The fingerprint data of the fingerprint to be detected is normalized by using the first preset data set and the second preset data set, and the fingerprint data is obtained, wherein the first preset data set and the second preset data set are The preset data set is a data set obtained during the calibration phase of the fingerprint sensor and used to calibrate the fingerprint raw data of the fingerprint sensor. The device according to claim 13, wherein the fingerprint data corresponding to the fingerprint to be detected comprises N groups of fingerprint data, and N is a positive integer greater than or equal to 2; The feature extraction module is further used for: Generate corresponding N fingerprint images according to the N groups of fingerprint data; According to the fingerprint common area between any two fingerprint images in the N fingerprint images, determine the fingerprint common area to be used; The fingerprint feature information is determined according to the to-be-used fingerprint common area. The device according to claim 15, wherein the common area of the fingerprint to be used is a first fingerprint image portion corresponding to the polarized light guide channel, and includes a first fingerprint image portion corresponding to the unpolarized light guide channel. The fingerprint common area of the two fingerprint image parts. The apparatus according to claim 15 or 16, wherein the feature extraction module is further configured to: Identify the ridges and valleys in the fingerprint public area to be used, and determine the fingerprint ridges and the fingerprint valleys in the fingerprint public area; Determine the coefficient of variation of the ridge line according to the fingerprint data corresponding to the ridge line of the fingerprint, and determine the coefficient of variation of the valley line according to the fingerprint data corresponding to the valley line of the fingerprint; The ridge line variation coefficient and the valley line variation coefficient are determined as the fingerprint feature information. The apparatus according to claim 17, wherein the feature extraction module is further configured to: According to the fingerprint data corresponding to the fingerprint ridge line, calculate the ridge line standard deviation and the ridge line average value, and according to the fingerprint data corresponding to the fingerprint valley line, calculate the valley line standard deviation and the valley line average value; The ridge coefficient of variation is determined from the ratio of the ridge standard deviation to the ridge mean, and the valley coefficient of variation is determined from the ratio of the valley standard deviation to the valley mean . The device according to claim 16, wherein the number of the fingerprint public areas to be used is M, where M is a positive integer greater than or equal to 1, and the feature extraction module is further configured to: According to the first fingerprint data corresponding to the first fingerprint image part contained in the ith fingerprint common area to be used and the second fingerprint image part corresponding to the i th fingerprint common area to be used The fingerprint data determines a first signal strength ratio, where i is a positive integer less than or equal to M, and the first signal strength ratio is used to indicate the first polarization characteristic of the fingerprint to be detected; The first signal strength ratio is determined as the fingerprint feature information. The apparatus according to claim 19, wherein the feature extraction module is further configured to: determining a first polarized average value from the first fingerprint data, and determining a first non-polarized average value from the second fingerprint data; The first signal intensity ratio is determined based on the ratio of the first unpolarized average value to the first polarized average value. The device according to claim 19, wherein when the number M of the fingerprint common areas to be used is greater than or equal to 2, the feature extraction module is further configured to: According to the third fingerprint data corresponding to the first fingerprint image part of the jth fingerprint common area to be used and the fourth fingerprint data corresponding to the second fingerprint image part of the jth fingerprint common area Two signal strength ratios, where j is a positive integer not equal to i and less than or equal to M, and the second signal strength is used to indicate the second polarization characteristic of the fingerprint to be detected; The second signal strength ratio is determined as the fingerprint feature information. The apparatus according to claim 21, wherein the feature extraction module is further configured to: determining a second polarized average value from the third fingerprint data, and determining a second non-polarized average value from the fourth fingerprint data; The second signal intensity ratio is determined based on the ratio of the second polarized average value to the second non-polarized average value. The apparatus according to claim 15, wherein the feature extraction module is further configured to: According to the pixel data of each said fingerprint common area, determine two hash value lists corresponding to the fingerprint common area; According to the Hamming distance between the two hash value lists corresponding to each of the fingerprint common areas, determine the grayscale similarity, where the grayscale similarity is used to indicate the grayscale distribution characteristic of the fingerprint to be detected; The grayscale similarity is determined as the fingerprint feature information. The apparatus according to claim 23, wherein the hash value list comprises a mean hash value list and/or a differential hash value list. An electronic device, comprising: processor, memory, display screen, touch control module, and fingerprint identification device; the memory is used to store computer programs; The fingerprint identification device includes an optical image acquisition module, and the optical image acquisition module includes a pixel array; The processor executes the computer program stored in the memory, so that the electronic device executes the fingerprint identification method according to any one of claims 1 to 12. A storage medium, comprising: a readable storage medium and a computer program, wherein the computer program is stored in the readable storage medium, and the computer program is used to implement any one of claims 1 to 12. fingerprint identification method.

Images