Fingerprint anti-counterfeiting processing method, device, medium, system and equipment

Abstract

The present application provides a fingerprint anti-counterfeiting processing method, device, medium, system and equipment, which relates to the field of fingerprint recognition. The method includes: obtaining a fingerprint recognition request, wherein the fingerprint recognition request includes a fingerprint to be recognized; obtaining a preset first anti-counterfeiting index value corresponding to the fingerprint to be recognized or a binary classification model established based on the first anti-counterfeiting index value, and determining whether the fingerprint to be recognized is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model; wherein the first anti-counterfeiting index value is a value preset based on the characteristic parameter value corresponding to the fingerprint to be recognized as a target fingerprint at different time sequences. Through the above method, the present application can efficiently identify forged fingerprints and improve the security of fingerprint recognition.

Description

Technical Field

[0001] The present application relates to fingerprint recognition technology, and in particular to a fingerprint anti-counterfeiting processing method, device, medium, system and equipment. Background Art

[0002] Fingerprinting is a technology that uses the information of system responses to determine the identity of a system and has been widely used in various electrical equipment.

[0003] Current fingerprint recognition technology mainly performs anti-counterfeiting identification by identifying the ridge and valley features of fingerprints, which can be easily cracked by 25D and 3D fake fingerprints. These fake fingerprints can simulate the ridges and valleys of the fingers and form acoustic impedance differences when they are attached to the screen, obtaining information consistent with the real fingerprint image. As a result, these fake fingerprints can pass through the fingerprint anti-counterfeiting system smoothly, greatly reducing user safety. Summary of the invention

[0004] The present application provides a fingerprint anti-counterfeiting processing method, device, medium, system and equipment to solve the problem of low security of current fingerprint anti-counterfeiting systems.

[0005] In a first aspect, the present application provides a fingerprint anti-counterfeiting processing method, comprising:

[0006] Obtaining a fingerprint recognition request, wherein the fingerprint recognition request includes a fingerprint to be recognized;

[0007] Obtaining a preset first anti-counterfeiting index value corresponding to the fingerprint to be identified or a binary classification model established based on the first anti-counterfeiting index value, and determining whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model;

[0008] The first anti-counterfeiting index value is a value preset based on the characteristic parameter value corresponding to the fingerprint to be identified as the target fingerprint obtained at different time sequences.

[0009] In one implementation, presetting the first anti-counterfeiting index value includes:

[0010] For each target fingerprint, obtaining the epidermis layer characteristic parameter values ​​and the dermis layer characteristic parameter values ​​corresponding to the target fingerprint at different time sequences;

[0011] Based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value, a first anti-counterfeiting index value corresponding to each target fingerprint is set respectively.

[0012] In one embodiment, establishing the binary classification model includes:

[0013] Training a preset binary classification model based on the first anti-counterfeiting index value to obtain the binary classification model;

[0014] Then, determining whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model includes:

[0015] The binary classification model is used to analyze and process the fingerprint to be identified, obtain a binary classification result, and determine whether the fingerprint to be identified is a forged fingerprint based on the binary classification result.

[0016] In one embodiment, obtaining the epidermis layer characteristic parameter values ​​and the dermis layer characteristic parameter values ​​corresponding to the target fingerprint at different time sequences respectively includes:

[0017] Acquire a first fingerprint image of the target fingerprint at a first time sequence, determine the ridge position and the valley position in the first fingerprint image, and obtain the ridge parameter value and the valley parameter value of the epidermis according to the ridge position and the valley position in the first fingerprint image; and,

[0018] A second fingerprint image of the target fingerprint at a second timing sequence having a preset timing difference from the first timing sequence is collected, the ridge position and the valley position in the second fingerprint image are determined, and the ridge parameter value and the valley parameter value of the dermis layer are obtained according to the ridge position and the valley position in the second fingerprint image.

[0019] In one embodiment, the first anti-counterfeiting index value corresponding to each target fingerprint is set based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value, including:

[0020] For each target fingerprint, based on the ridge parameter value and the valley parameter value of the epidermis layer, a fingerprint contrast of the epidermis layer is obtained, and based on the ridge parameter value and the valley parameter value of the dermis layer, a fingerprint contrast of the dermis layer is obtained;

[0021] Determine the anti-counterfeiting index value in a first time sequence based on the fingerprint contrast of the epidermis layer, the ridge parameter value and the valley parameter value of the epidermis layer, and determine the anti-counterfeiting index value in a second time sequence based on the fingerprint contrast of the dermis layer, the ridge parameter value and the valley parameter value of the dermis layer;

[0022] Based on the anti-counterfeiting index value in the first time sequence and the anti-counterfeiting index value in the second time sequence, a first anti-counterfeiting index value corresponding to the target fingerprint is set.

[0023] In one embodiment, the first anti-counterfeiting index value corresponding to each target fingerprint is set based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value, including:

[0024] For each target fingerprint, determining a ridge parameter ratio between a first time series and a second time series based on the ridge parameter value of the epidermis layer and the ridge parameter value of the dermis layer; and determining a valley parameter ratio between the first time series and the second time series based on the valley parameter value of the epidermis layer and the valley parameter value of the dermis layer;

[0025] Acquire a fingerprint contrast of the epidermis layer based on the ridge parameter values ​​and the valley parameter values ​​of the epidermis layer, and acquire a fingerprint contrast of the dermis layer based on the ridge parameter values ​​and the valley parameter values ​​of the dermis layer; and determine a contrast ratio between a first time series and a second time series based on the fingerprint contrast of the epidermis layer and the fingerprint contrast of the dermis layer;

[0026] Based on the ridge parameter ratio, valley parameter ratio and contrast ratio between the first time sequence and the second time sequence, the anti-counterfeiting index values ​​between different time sequences are determined, and the first anti-counterfeiting index value corresponding to the target fingerprint is set based on the anti-counterfeiting index values ​​between different time sequences.

[0027] In one embodiment, obtaining the epidermis layer characteristic parameter values ​​and the dermis layer characteristic parameter values ​​corresponding to the target fingerprint at different time sequences respectively includes:

[0028] Collecting a third fingerprint image of the target fingerprint at a third time sequence, obtaining the gradient of each pixel point in the third fingerprint image in a preset number of directions, and taking the direction with the smallest gradient as the first gradient direction of each pixel point;

[0029] Based on the first gradient direction of each pixel point, determining the first texture direction of the pixel block where each pixel point is located, and acquiring the texture direction feature value of the epidermis layer based on the first texture direction of each pixel block; and,

[0030] Collecting a fourth fingerprint image of the target fingerprint at a fourth time sequence having a preset time sequence difference with the third time sequence, obtaining the gradient of each pixel point in the fourth fingerprint image in a preset number of directions, and taking the direction with the smallest gradient as the second gradient direction of each pixel point;

[0031] Based on the second gradient direction of each pixel point, the second texture direction of the pixel block where each pixel point is located is determined, and the texture direction feature value of the dermis layer is obtained based on the second texture direction of each pixel block.

[0032] In one embodiment, the first anti-counterfeiting index value corresponding to each target fingerprint is set based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value, including:

[0033] For each target fingerprint, the texture change rate of the target fingerprint is obtained based on the texture direction feature value of the epidermis layer and the texture direction feature value of the dermis layer, and the first anti-counterfeiting index value corresponding to the target fingerprint is set based on the texture change rate.

[0034] In one embodiment, the acquiring the texture change rate of the target fingerprint based on the texture direction feature value of the epidermis layer and the texture direction feature value of the dermis layer includes:

[0035] Based on the texture direction feature value of the epidermis layer and the texture direction feature value of the dermis layer, a pixel block producing a texture direction change is acquired, and the pixel block is marked as a superposition block;

[0036] Based on the ratio between the number of the superimposed blocks and the total number of pixel blocks, the texture change rate of the target fingerprint is determined.

[0037] In one embodiment, the method further comprises:

[0038] Acquire a preset second anti-counterfeiting index value, where the second anti-counterfeiting index value is preset based on a fitting parameter value corresponding to the fingerprint to be identified as a target fingerprint;

[0039] Then, determining whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model includes:

[0040] Based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value, determine whether the fingerprint to be identified is a forged fingerprint; or, based on a binary classification model established based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value, determine whether the fingerprint to be identified is a forged fingerprint.

[0041] In one implementation, presetting the second anti-counterfeiting index value includes:

[0042] Collecting a fifth fingerprint image of the target fingerprint, and obtaining fingerprint gradient information of each pixel point in the fifth fingerprint image;

[0043] Filter out effective fingerprint gradient information and its corresponding pixel points that meet preset conditions from the fingerprint gradient information of each pixel point;

[0044] Obtaining the effective gradient proportion of the target fingerprint based on the number of pixels corresponding to the effective fingerprint gradient information; and / or obtaining an average effective gradient value based on the effective fingerprint gradient information and the number of pixels corresponding to it;

[0045] Based on the effective gradient proportion and / or the average effective gradient value, a fitting parameter value of the target fingerprint is obtained.

[0046] According to a second aspect of the present application, a fingerprint anti-counterfeiting processing device is provided, comprising:

[0047] A first acquisition module, configured to acquire a fingerprint recognition request, wherein the fingerprint recognition request includes a fingerprint to be recognized;

[0048] A second acquisition module, which is configured to acquire a preset first anti-counterfeiting index value corresponding to the fingerprint to be identified or a binary classification model established based on the first anti-counterfeiting index value;

[0049] a determination module, configured to determine whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model;

[0050] The first anti-counterfeiting index value is a value preset based on the characteristic parameter value corresponding to the fingerprint to be identified as the target fingerprint obtained at different time sequences.

[0051] According to a third aspect of the present application, a computer storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the fingerprint anti-counterfeiting processing method.

[0052] According to a fourth aspect of the present application, a fingerprint anti-counterfeiting system is provided, comprising an ultrasonic sensing device and the fingerprint anti-counterfeiting processing device, wherein the fingerprint anti-counterfeiting processing device is used to be electrically connected to the ultrasonic sensing device to realize ultrasonic fingerprint anti-counterfeiting detection.

[0053] According to a fifth aspect of the present application, an electronic device is provided, comprising the fingerprint anti-counterfeiting processing system.

[0054] The fingerprint anti-counterfeiting processing method, device, medium, system and equipment provided by the present application take into account that the fingerprint feature parameters of forged fingerprints vary more greatly than those of real fingerprints at different time sequences. When obtaining a fingerprint recognition request, a pre-set first anti-counterfeiting index value or a corresponding binary classification model corresponding to the fingerprint to be recognized is obtained to perform anti-counterfeiting recognition on the fingerprint to be recognized. The anti-counterfeiting index value is set by obtaining the fingerprint feature data of the target fingerprint at different time sequences. When performing fingerprint recognition, forged fingerprints can be efficiently identified, effectively improving the security of fingerprint recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0056] Figure 1 A schematic diagram of a possible application scenario provided by an embodiment of the present application;

[0057] Figure 2a is a schematic diagram of an ultrasonic signal emission model;

[0058] Figure 2b is a schematic diagram of an ultrasonic signal receiving model;

[0059] Figure 3a It is a schematic diagram of the ultrasonic signal receiving model when a real finger is pressed;

[0060] Figure 3b One of the schematic diagrams of the ultrasonic signal receiving model when the mold or fake finger is pressed;

[0061] Figure 3c This is a schematic diagram of the echo signal when a real finger is pressed;

[0062] Figure 3d This is a schematic diagram of the echo signal when the mold or fake finger is pressed;

[0063] Figure 4 This is a comparison chart of different fingerprint echo signals;

[0064] Figure 5 This is a contrast diagram of the epidermis of different fingerprints;

[0065] Figure 6 A schematic diagram of a fingerprint anti-counterfeiting processing method provided in an embodiment of the present application;

[0066] Figure 7 for Figure 6 Schematic diagram of the process of step S602;

[0067] Figure 8a A schematic diagram of the fingerprint direction in an embodiment of the present application;

[0068] Figure 8b is a schematic diagram of a pixel block in an embodiment of the present application;

[0069] Figure 8c This is a schematic diagram of texture direction calculation in an embodiment of the present application;

[0070] Figure 9a Schematic diagram of fingerprint image and direction field of fake finger in the third time sequence;

[0071] Figure 9b is a schematic diagram of the fingerprint image and direction field of the fake finger in the fourth time sequence;

[0072] Fig.10a Schematic diagram of fingerprint image and direction field of the stripe head in the third time sequence;

[0073] Fig.10b Schematic diagram of fingerprint image and direction field of the stripe head in the fourth time sequence;

[0074] Fig.11 The second schematic diagram of the ultrasonic signal receiving model when the mold or fake finger is pressed;

[0075] Fig.12 A schematic diagram of a process flow of another fingerprint anti-counterfeiting processing method provided in an embodiment of the present application;

[0076] Fig.13a A schematic diagram of an original fingerprint image in an embodiment of the present application;

[0077] Fig.13b The gradient map corresponding to the original fingerprint image in the embodiment of the present application;

[0078] Fig.13c A valid area map corresponding to the original fingerprint image in the embodiment of the present application;

[0079] Fig.14 A schematic diagram of the structure of a fingerprint anti-counterfeiting processing device provided in an embodiment of the present application;

[0080] Fig.15 A schematic diagram of the structure of a fingerprint anti-counterfeiting processing system provided in an embodiment of the present application;

[0081] Fig.16 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0082] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0083] Before describing the embodiments of the present application, the following terms are first explained: ridges and valleys: ridges and valleys are both fingerprint patterns, representing raised or sunken patterns respectively, and are represented in the fingerprint data as parts with relatively large and small signal intensities; contrast: the difference between ridges and valleys in the fingerprint data, which represents the fingerprint signal strength.

[0084] The following describes the embodiments of the present application in combination with the application scenarios. The fingerprint anti-counterfeiting processing method provided in the embodiments of the present application can be applied to the ultrasonic fingerprint unlocking application scenario, and more specifically, can be applied to the ultrasonic fingerprint recognition application scenario of intelligent electronic devices. For example, personal electronic devices such as mobile phones and computers can also be applied to other electronic equipment fields such as financial payment, access control systems, and identity verification.

[0085] Ultrasonic fingerprint recognition creates a visual image of the fingerprint by obtaining the intensity of sound waves reflected by the screen, fingerprint, and air. Unlike optical imaging, the piezoelectric transducer inside the ultrasonic sensor generates ultra-high frequency sound waves that can penetrate the epidermis of the skin and form an image by measuring the energy of the reflected waves. It is less affected by the details of the fingerprint surface and can be recognized even when it is stained or wet. Compared with capacitive and optical fingerprint recognition in related technologies, it has advantages in security (anti-counterfeiting) and accuracy. However, ultrasonic fingerprint technology is also more easily cracked by 25D and 3D fake fingerprints. This type of fake fingerprint can simulate the ridges and valleys of the finger, forming a difference in acoustic impedance when it fits the screen, obtaining information consistent with the real fingerprint image, and can pass the recognition and anti-counterfeiting system, greatly reducing the user's safety.

[0086] In view of this, embodiments of the present application provide a fingerprint anti-counterfeiting processing method, device, medium, system and equipment. Figure 1 The schematic diagram of the ultrasonic fingerprint recognition application scenario provided in this application is as follows: Figure 1 As shown, it includes an ultrasonic sensor device 10 and an anti-counterfeiting server 20 electrically connected to the ultrasonic sensor device 10. The ultrasonic sensor device 10 includes an ultrasonic piezoelectric sensor 11, an analog-to-digital converter 12, a storage unit 13, and a data processing center 14. The ultrasonic piezoelectric sensor 11, the analog-to-digital converter 12, the storage unit 13, and the data processing center 14 are electrically connected to a central controller 15, respectively. The ultrasonic piezoelectric sensor 11 can be a PVDF ultrasonic array sensor, which is used to complete the excitation of the ultrasonic array and the reception of the echo signal. The analog-to-digital converter 12 can use a high-precision analog-to-digital converter, which is used to convert the analog echo signal intensity into a digital signal, which is transmitted to the data processing center 14 through the storage unit 13 to complete the preliminary processing of the fingerprint data, and the processed fingerprint data is transmitted to the server 20. The anti-counterfeiting server 20 uses the fingerprint processing algorithm for further processing to complete the relevant fingerprint registration, fingerprint recognition and unlocking functions. Among them, the (real finger) ultrasonic signal transmission and reception model is as follows Figure 2a and Figure 2b shown.

[0087] The embodiments of the present application take into account that in actual applications, a real finger of a human body includes an epidermis layer and a dermis layer, while a mold or a fake finger cannot distinguish between the dermis layer and the epidermis layer, and usually imitates the thickness of the epidermis layer and the dermis layer to imitate the fingerprint. Figure 3a-3d As shown, let the thickness of the coupling layer be d0, the sound velocity in the coupling layer be c0, ignore the thickness of the screen, the thickness from the dermis to the epidermis of the finger be d1, and the sound velocity be c1. Then the time for the sensor to receive the epidermis echo is t0, and the time to receive the dermis layer echo is t1. The sound velocity of the acoustic wave in the fake finger material is c2, and the thickness of the fake fingerprint is d1. Then the time to receive the echo of its deep texture is t2. If c1 = c2, the echo signal received at time t1 or t2 is the surface texture of the pressed object. If c1 < c2, the echo signal of the deep texture has not been received at time t1. If c1 > c2, the echo signal of the deep texture has passed at time t1. When c1 < c2 or c1 > c2, there are differences between the deep texture and its epidermis texture. Thus, the authenticity of the finger can be identified by comparing the differences in the echo signals received at different time sequences. Among them, the calculation formulas for t0, t1, and t1 are as follows:

[0088]

[0089]

[0090]

[0091] Moreover, there are significant differences in acoustic impedance between real fingers and other materials used to make fake fingers. Therefore, there are differences in sound velocity in different materials, which affects the fingerprint echo signal. There are not only differences in the amount of fingerprint signals, but also certain changes in the texture characteristics of real and fake fingerprints. As Figure 4 shown, these differences are due to different acoustic parameters of the materials. At the same time sequence, the signal sizes of different materials will be inconsistent, and the time sequences at which the echo signals are maximum will also be inconsistent. Moreover, there are significant differences in the fingerprint epidermis layer contrast (taking the average of a large amount of data) between real fingers and fake fingers made of different materials. As Figure 5 shown.

[0092] Compared with the fingerprint processing algorithm in the related art, when receiving the fingerprint recognition request, this embodiment performs anti-counterfeiting recognition on the fingerprint to be recognized by obtaining the pre-set anti-counterfeiting index value or the corresponding binary classification model. The anti-counterfeiting index value is set by the fingerprint feature data of the target fingerprint at different time sequences obtained in advance. In the recognition process, the anti-counterfeiting index value or binary classification model determined by the fingerprint features and their changes at different time sequences can effectively improve the security of fingerprint recognition. Furthermore, by respectively calculating the ridge and valley parameters and contrast values ​​of the target fingerprint at different time sequences, and calculating the ridge and valley ratio and contrast ratio between the time sequences; and according to the fingerprint texture direction field at different time sequences, comparing the change rate of the fingerprint texture at different time sequences, the real and fake fingerprints can be distinguished; in addition, by combining the second anti-counterfeiting index value set based on the fitting parameters of the target fingerprint, the fingerprint to be recognized is recognized, which can further improve the anti-counterfeiting effect of distinguishing real and fake fingers.

[0093] The following takes the anti-counterfeiting server 20 applied in the above application scenario as an example, and describes the technical solution of the present application in detail in combination with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0094] Figure 6 A schematic flow chart of a fingerprint anti-counterfeiting processing method provided in an embodiment of the present application includes steps S601-S603.

[0095] Step S601: Obtain a fingerprint recognition request, wherein the fingerprint recognition request includes a fingerprint to be recognized.

[0096] Taking the screen unlocking of a mobile phone as an example, the user presses his finger at the corresponding position of the fingerprint collection function module of the mobile phone to trigger a fingerprint recognition request. The anti-counterfeiting server obtains the user's fingerprint to be recognized and performs subsequent fingerprint anti-counterfeiting recognition. The fingerprint to be recognized may include fingerprint feature data at two different time sequences, which may correspond to two different time sequences under the target fingerprint feature parameter value. The timing difference between the two different time sequences may be in the range of 1100ns to 2000ns.

[0097] Step S602, obtaining a pre-set first anti-counterfeiting index value corresponding to the fingerprint to be identified or a binary classification model established based on the first anti-counterfeiting index value; wherein the first anti-counterfeiting index value is a pre-set value based on the characteristic parameter value corresponding to the fingerprint to be identified as the target fingerprint at different time sequences.

[0098] In the related art, the fingerprint image of the fingerprint to be identified is usually matched with the stored authentication fingerprint image, and the fingerprint features in the fingerprint to be identified and each fingerprint image are compared, such as the consistency or similarity between the ridge and valley features, to further identify whether the fingerprint to be identified is the authentication fingerprint. This process is easily cracked by highly imitated fake fingers and cannot achieve a good anti-counterfeiting effect.

[0099] In this embodiment, after obtaining a fingerprint recognition request, a first anti-counterfeiting index value corresponding to the fingerprint to be recognized is obtained, and a binary classification model established based on the first anti-counterfeiting index value is obtained, and the first anti-counterfeiting index value or the binary classification model is used to perform fingerprint anti-counterfeiting recognition in subsequent steps. The first anti-counterfeiting index value or the corresponding binary classification model is pre-set according to the characteristic parameter value corresponding to the fingerprint to be recognized as the target fingerprint at different time sequences, taking into account the characteristic changes of the real finger at different time sequences, thereby improving the anti-counterfeiting effect against fake fingers.

[0100] It can be understood that the fingerprint to be identified is taken as the target fingerprint, that is, the fingerprint of the real finger corresponding to the fingerprint to be identified is taken as the target fingerprint. Among them, the first anti-counterfeiting index value is a value pre-set according to the characteristic parameter value corresponding to the target fingerprint at different time sequences. Taking the characteristic parameter value as the ridge parameter value as an example, the ridge parameter value of the fingerprint at 1100ns is 143.7, and the ridge parameter of the fingerprint at 1900ns is 143.9. Those skilled in the art can set a reasonable range of values ​​according to the ridge parameter values ​​at different time sequences in combination with actual applications, for example, set it at 143.5~144.0, and / or set the range of variation of the ridge parameter between different time sequences, for example, set it at 0.2~0.5. It should be noted that those skilled in the art can adaptively set the value range of the first anti-counterfeiting index value in combination with actual applications and a large number of real finger fingerprint samples. This embodiment only provides a possible illustration of the above numerical range without specific limitation.

[0101] In some embodiments, in addition to the recognition scenario of imitating fake fingers of the authentication fingerprint (i.e., the target fingerprint) in actual applications, there are also some recognition scenarios of non-authentication fingerprints or non-imitation fingerprints, for example, fingerprint recognition requests initiated by users who have not performed fingerprint authentication. In order to improve the fingerprint recognition efficiency of the system, after step S601 and before step S602, this embodiment can also perform initial recognition on the fingerprint to be recognized. This process can be implemented based on the existing technology, and the similarity between the fingerprint to be recognized and the stored authentication fingerprint is judged, and the fingerprint with the highest similarity is screened out. If the similarity is greater than or equal to the similarity threshold, step S602 is entered to obtain the corresponding first anti-counterfeiting index value, that is, the first anti-counterfeiting index value set based on the screened fingerprint. If the similarity is lower than the similarity threshold, it means that there is a large difference between the fingerprint to be recognized and the authentication fingerprint, and it is a non-authentication fingerprint or a non-imitation fingerprint, and it can be directly determined that the fingerprint recognition fails.

[0102] Step S603: Determine whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model.

[0103] In one embodiment, by obtaining the characteristic value corresponding to the first anti-counterfeiting index value of the fingerprint to be identified and comparing it with the first anti-counterfeiting index value, if it meets the range corresponding to the first anti-counterfeiting index value, it is explained as the target fingerprint, otherwise it is a forged fingerprint. Exemplarily, the first anti-counterfeiting index value is set according to the ridge parameter value of the target fingerprint at 1100ns and the ridge parameter value of the fingerprint at 1900ns, and the range of the ridge parameter change between different time sequences is set between 0.2 and 0.5. By obtaining the ridge parameter value of the fingerprint to be identified at 1100ns and the ridge parameter value of the fingerprint at 1900ns, it is determined whether the ridge parameter change of the fingerprint to be identified at the two time sequences is within the range of 0.2 to 0.5.

[0104] In another embodiment, in order to further improve the efficiency of fingerprint recognition, the first anti-counterfeiting index value can also be used to train a binary classification model. When performing fingerprint recognition, the fingerprint feature data of the fingerprint to be identified at different time sequences is input into the binary classification model, and the output result of the binary classification model is used to determine whether the fingerprint to be identified is a target fingerprint or a forged fingerprint.

[0105] It can be seen that in this embodiment, the first anti-counterfeiting index value or the corresponding binary classification model pre-set by the fingerprint feature data of the target fingerprint at different time sequences is used to perform anti-counterfeiting identification on the fingerprint to be identified. Compared with the related technology that only identifies the static ridges and valleys of the finger, which is easily cracked by highly imitated fake fingerprints, this embodiment takes into account the fingerprint feature data of the fingerprint at different time sequences, effectively improves the anti-counterfeiting effect against fake fingers, and thus ensures the security of the fingerprint identification process.

[0106] In one implementation, the first anti-counterfeiting index value is preset in the above step S602, such as Figure 7 As shown, the following steps may be included:

[0107] Step S602a, for each target fingerprint, obtaining the epidermis layer characteristic parameter values ​​and the dermis layer characteristic parameter values ​​corresponding to the target fingerprint at different time sequences;

[0108] Step S602b: Based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value, respectively set a first anti-counterfeiting index value corresponding to each target fingerprint.

[0109] It can be understood that in this embodiment, each target fingerprint is all authentication fingerprints of the anti-counterfeiting server.

[0110] As the types of fake fingerprints increase, the anti-counterfeiting effect of only using single-frame fingerprint data or fingerprint texture is poor. In this embodiment, taking into account the biological characteristics of the human body, a real finger includes an epidermis and a dermis, wherein the characteristic parameters of the epidermis and the dermis are usually consistent or the difference is slight and negligible, while a fake fingerprint does not have a dermis and an epidermis, and can usually only imitate the depth (i.e., thickness) information between the real epidermis, because the difference in their acoustic impedance is prone to large changes at different time sequences. Therefore, this embodiment obtains the characteristic parameter values ​​of the epidermis and the dermis corresponding to different time sequences, and sets the first anti-counterfeiting index value based on this, so as to better distinguish between real and fake fingerprints and achieve the purpose of anti-counterfeiting.

[0111] In one embodiment, establishing the binary classification model may include the following steps:

[0112] Training a preset binary classification model based on the first anti-counterfeiting index value to obtain the binary classification model;

[0113] Then, in step S603, determining whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model may include the following steps:

[0114] The binary classification model is used to analyze and process the fingerprint to be identified, obtain a binary classification result, and determine whether the fingerprint to be identified is a forged fingerprint based on the binary classification result.

[0115] In this embodiment, the preset binary classification model may adopt a support vector machine (SVM) model, whose basic model is a linear classifier with the largest interval defined in the feature space, and the optimal separation hyperplane is obtained by maximizing the interval.

[0116] In some embodiments, when verifying the fingerprint to be identified, in order to further improve the fingerprint anti-counterfeiting accuracy, in addition to the first anti-counterfeiting index value, other anti-counterfeiting index values ​​are also included, such as the second anti-counterfeiting index value set by the fingerprint fitting parameters mentioned later. The various anti-counterfeiting index values ​​can be used to train the SVM model, and when performing fingerprint identification, the feature data corresponding to the fingerprint to be identified is input into the trained model, and based on the binary classification output result, it can be quickly determined whether the fingerprint to be identified is a forged fingerprint.

[0117] In one embodiment, considering that the ridge and valley parameters of the epidermis layer and the ridge and valley parameters of the dermis layer of the finger have certain characteristics and change rules, the ridge and valley parameter values ​​of the fingerprint can be used to set the first anti-counterfeiting index value. In the above steps, the epidermis layer characteristic parameter values ​​and the dermis layer characteristic parameter values ​​corresponding to the target fingerprint at different time sequences are obtained, which can include the following steps:

[0118] Acquire a first fingerprint image of the target fingerprint at a first time sequence, determine the ridge position and the valley position in the first fingerprint image, and obtain the ridge parameter value and the valley parameter value of the epidermis according to the ridge position and the valley position in the first fingerprint image; and,

[0119] A second fingerprint image of the target fingerprint at a second timing sequence having a preset timing difference from the first timing sequence is collected, the ridge position and the valley position in the second fingerprint image are determined, and the ridge parameter value and the valley parameter value of the dermis layer are obtained according to the ridge position and the valley position in the second fingerprint image.

[0120] In this embodiment, ultrasound can be used to collect fingerprint images at different time sequences. For example, the fingerprint image collected at 1100ns is the epidermis fingerprint image, and the fingerprint image collected at 1900ns is the human dermis fingerprint image. The ridge and valley positions in the fingerprint image are calculated respectively, and then all the ridge values ​​and valley values ​​in the fingerprint image are counted respectively, and the ridge / valley parameter values ​​at different time sequences are obtained by the mean algorithm.

[0121] For applications in which the epidermal layer characteristic parameter values ​​at different time sequences include ridge / valley parameter values, at least the following two implementations may be used to set the corresponding first anti-counterfeiting value.

[0122] Method 1: In the above steps, the first anti-counterfeiting index value corresponding to each target fingerprint is set based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value, which may include the following steps:

[0123] For each target fingerprint, based on the ridge parameter value and the valley parameter value of the epidermis layer, a fingerprint contrast of the epidermis layer is obtained, and based on the ridge parameter value and the valley parameter value of the dermis layer, a fingerprint contrast of the dermis layer is obtained;

[0124] Determine the anti-counterfeiting index value in a first time sequence based on the fingerprint contrast of the epidermis layer, the ridge parameter value and the valley parameter value of the epidermis layer, and determine the anti-counterfeiting index value in a second time sequence based on the fingerprint contrast of the dermis layer, the ridge parameter value and the valley parameter value of the dermis layer;

[0125] Based on the anti-counterfeiting index value in the first time sequence and the anti-counterfeiting index value in the second time sequence, a first anti-counterfeiting index value corresponding to the target fingerprint is set.

[0126] In this embodiment, the first anti-counterfeiting index value is determined according to the ridge / valley parameter value and the fingerprint contrast at different time sequences, wherein the fingerprint contrast = the ridge parameter value - the valley parameter value, which can represent the fingerprint signal strength.

[0127] In one example, based on the anti-counterfeiting index value at the first time sequence and the anti-counterfeiting index value at the second time sequence, a first anti-counterfeiting index value is set. The first anti-counterfeiting index value can respectively include the ridge / valley parameter value and the fingerprint contrast threshold at the first time sequence. When performing fingerprint recognition, the ridge / valley parameter value and the fingerprint contrast of the fingerprint to be recognized at the first time sequence are respectively judged and compared with the corresponding threshold. If they are all within the threshold range, the recognition is passed; otherwise, the fingerprint to be recognized is determined to be a forged fingerprint.

[0128] Method 2: In the above steps, the first anti-counterfeiting index value corresponding to each target fingerprint is set based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value, which may include the following steps:

[0129] For each target fingerprint, determining a ridge parameter ratio between a first time series and a second time series based on the ridge parameter value of the epidermis layer and the ridge parameter value of the dermis layer; and determining a valley parameter ratio between the first time series and the second time series based on the valley parameter value of the epidermis layer and the valley parameter value of the dermis layer;

[0130] Acquire a fingerprint contrast of the epidermis layer based on the ridge parameter values ​​and the valley parameter values ​​of the epidermis layer, and acquire a fingerprint contrast of the dermis layer based on the ridge parameter values ​​and the valley parameter values ​​of the dermis layer; and determine a contrast ratio between a first time series and a second time series based on the fingerprint contrast of the epidermis layer and the fingerprint contrast of the dermis layer;

[0131] Based on the ridge parameter ratio, valley parameter ratio and contrast ratio between the first time sequence and the second time sequence, the anti-counterfeiting index values ​​between different time sequences are determined, and the first anti-counterfeiting index value corresponding to the target fingerprint is set based on the anti-counterfeiting index values ​​between different time sequences.

[0132] Compared with the above method 1, since the acoustic impedance of some materials may be close to that of fingers, using only the contrast and other indicators at a certain time sequence is not sufficient. This embodiment calculates the contrast and ridge-valley ratio of two sets of time sequences, and then controls the threshold range of the ratio indicators between these two time sequences to judge true and false fingers. Adding the ratio indicator to the discrimination of true and false fingers improves the discrimination of true and false fingerprints, and optimizes the anti-counterfeiting performance.

[0133] Specifically, the setting of the first anti-counterfeiting index value in this embodiment is determined based on the anti-counterfeiting index values ​​between different time sequences (referred to as time sequences), that is, the fingerprint characteristic parameter changes between different time sequences are determined. Specifically, the contrast value ratio between time sequences = the fingerprint contrast of the dermis in the second time sequence / the fingerprint contrast of the epidermis in the first time sequence, and the ridge / valley parameter ratio between time sequences = the ridge (valley) parameter value of the dermis in the second time sequence / the ridge (valley) parameter value of the epidermis in the first time sequence. Since the fingerprint characteristic data of the dermis layer and the fingerprint characteristic data of the epidermis layer of the real finger are consistent, the contrast ratio and the ridge-valley parameter ratio between time sequences usually have a small difference. In this embodiment, the first anti-counterfeiting index value is set according to the contrast ratio and the ridge-valley parameter ratio between time sequences. When the fingerprint to be identified exceeds the corresponding threshold range, it can be identified as a forged fingerprint.

[0134] In some embodiments, the first anti-counterfeiting index value can be determined by both the above-mentioned method 1 and method 2, that is, the first anti-counterfeiting index value is determined according to the anti-counterfeiting index values ​​at different time sequences and the index anti-counterfeiting values ​​between different time sequences. When performing fingerprint recognition, it is necessary to compare the fingerprint information to be recognized with the anti-counterfeiting index values ​​at different time sequences and the index anti-counterfeiting values ​​between time sequences at the same time to further improve the anti-counterfeiting effect.

[0135] In another embodiment, considering that sound propagation is related to time, the longer the time, the farther the sound wave is transmitted, and the sound wave signal is reflected after reaching the epidermis for the first time, and a part of the sound wave passes through the epidermis and continues to be transmitted to the deep layer, and is reflected again after reaching the dermis. Therefore, the echo signals received at different times can represent textures at different depths. This embodiment is designed based on the consistency of the texture of the epidermis and dermis of human fingerprints, forms fingerprint images in different time sequences in one press, and improves the fingerprint anti-counterfeiting performance by comparing the texture differences. Specifically, the above steps to obtain the epidermis layer characteristic parameter values ​​and dermis layer characteristic parameter values ​​corresponding to the target fingerprint at different time sequences can include the following steps:

[0136] Collecting a third fingerprint image of the target fingerprint at a third time sequence, obtaining the gradient of each pixel point in the third fingerprint image in a preset number of directions, and taking the direction with the smallest gradient as the first gradient direction of each pixel point;

[0137] Determining the first texture direction of the pixel block where each pixel is located based on the first gradient direction of each pixel point, and acquiring the texture direction feature value of the epidermis layer based on the first texture direction of each pixel block; and,

[0138] Collecting a fourth fingerprint image of the target fingerprint at a fourth time sequence having a preset time sequence difference with the third time sequence, obtaining the gradient of each pixel point in the fourth fingerprint image in a preset number of directions, and taking the direction with the smallest gradient as the second gradient direction of each pixel point;

[0139] Based on the second gradient direction of each pixel point, the second texture direction of the pixel block where each pixel point is located is determined, and the texture direction feature value of the dermis layer is obtained based on the second texture direction of each pixel block.

[0140] In this embodiment, by calculating the directional feature value of the fingerprint texture, the common directional operator convolution is compared to find the direction algorithm that makes the convolution result maximum or minimum as the solution for the direction of the point. Specifically, a gradient operation is performed on pixels in a preset neighborhood (e.g., a 5×5 neighborhood) of a single pixel point, and the minimum gradient direction is used as the direction of the pixel point, and the direction is divided into blocks to define the direction, and the fingerprint image is divided into a preset number of pixel blocks (e.g., 8×8 large blocks), and the direction is expanded from the pixel point direction to the block direction to obtain a more accurate fingerprint direction field. The texture directional feature value at different time sequences can be used to determine the first anti-counterfeiting index value, or in subsequent steps, the changes in the directions of each block at different time sequences are compared, and then the texture change rate of the pixel block at different time sequences is obtained to further determine the anti-counterfeiting index value.

[0141] For ease of understanding, combined Figure 8a-8c As shown, the fingerprint direction is defined as Figure 8a As shown, Figure 8a The numbers 0 to 7 represent 8 different directions. Taking a certain pixel point x as the center, the fingerprint texture direction is divided into eight directions in its 5×5 neighborhood. The entire fingerprint image can be divided into 8×8 pixel blocks and the texture direction of each pixel block is marked, such as Figure 8b As shown, it is easy to compare the changes in its texture.

[0142] Wherein, obtaining the gradient of each pixel in the third / fourth fingerprint image (hereinafter referred to as image) in a preset number of directions, and taking the direction with the smallest gradient as the first / second gradient direction of each pixel, respectively, may be the following steps:

[0143] Step 1: Take a pixel point x in the image, take the pixel values ​​of the surrounding 5×5 neighborhood, and calculate the gradients in eight directions.

[0144] Step 2: Combine Figure 8c As shown, the gradient is calculated for three parallel lines in a certain direction. The formula is as follows:

[0145] Grad i =abs(p i+1 -p i+8 )+abs(p i+2 -p i+6 )+abs(p i -p i+9 )

[0146] Among them, Grad irepresents the gradient of the pixel in the i-th direction, i = 0, 1, ..., 7, p i Represents the neighborhood pixel point in the i direction.

[0147] Step 3: Take the minimum gradient in the 5×5 neighborhood of each pixel as the gradient direction of the point. The formula is as follows:

[0148]

[0149] After obtaining the gradient direction of the pixel point, this embodiment determines the texture direction of the pixel block where each pixel point is located according to the gradient direction of the pixel point, and obtains the texture direction feature value of the epidermis / dermis layer based on the texture direction of each pixel block. Specifically,

[0150] Step 4: Extend the point direction calculation to block direction calculation, and count the direction BlockOF with the highest frequency in each block as the texture direction of the block. The formula is as follows, where Indicates the frequency or number of times the i-th direction appears.

[0151]

[0152] It should be noted that, in this embodiment, the third time sequence may be the same as or different from the first time sequence, and the fourth time sequence may be different from the second time sequence. In this embodiment, first, second, third, fourth, etc. are used to distinguish similar objects and have no other special meanings.

[0153] Compared with the above method, in which the first anti-counterfeiting index value is set by using the parameter values ​​such as the ridge and valley parameters between the epidermis and the dermis, this embodiment takes into account the texture feature changes between the epidermis and the dermis to set the first anti-counterfeiting index value. Specifically, in the above step, determining the first anti-counterfeiting index value based on the characteristic parameter value of the epidermis layer and the characteristic parameter value of the dermis layer may include the following steps:

[0154] For each target fingerprint, the texture change rate of the target fingerprint is obtained based on the texture direction feature value of the epidermis layer and the texture direction feature value of the dermis layer, and the first anti-counterfeiting index value corresponding to the target fingerprint is set based on the texture change rate.

[0155] It should be noted that those skilled in the art can adaptively set the first anti-counterfeiting index value according to the texture change rate in combination with actual applications. For example, if the fingerprint change rate of the target fingerprint is 0.36, the first anti-counterfeiting index value is set to a texture change rate within 0.4.

[0156] Furthermore, in the above step, obtaining the texture change rate of the target fingerprint based on the texture direction feature value of the epidermis layer and the texture direction feature value of the dermis layer may include the following steps:

[0157] Based on the texture direction feature value of the epidermis layer and the texture direction feature value of the dermis layer, a pixel block producing a texture direction change is acquired, and the pixel block is marked as a superposition block;

[0158] Based on the ratio between the number of the superimposed blocks and the total number of pixel blocks, the texture change rate of the target fingerprint is determined.

[0159] Taking the epidermis texture directional feature value OF0 at the third time sequence (e.g., the first frame of fingerprint data) as a reference, the OF0 represents the directional field at the third time sequence, and calculating the directional field OF0 of the fingerprint image at a different time sequence (e.g., the fourth time sequence with a time sequence difference). j , compare the rate of change between its direction field and OF0:

[0160]

[0161]

[0162] In the formula, Diff OF It indicates that the texture direction of the pixel block changes between the third timing and the fourth timing. It represents the pixel blocks that produce texture direction changes, that is, the texture direction changes of the pixel blocks are greater than 1 and less than 7, and 64 is the total number of pixel blocks.

[0163] Through experimental comparison, the directional fields of the real and fake fingerprints in the first frame (1100ns) and the subsequent frames (for example, 1900ns) are obtained. The fake fingerprint is pressed with oblique stripes to collect fingerprint images and their directional fields in different frames. Figure 9a and Figure 9b As shown, it can be clearly seen that the fingerprint image acquired at 1900ns is superimposed with the stripe head texture behind the fake fingerprint, which shows that the method proposed in this embodiment to judge the true and false fingerprints by the fingerprint texture changes at different time sequences is reasonable:

[0164] Through statistics, it can be found that the number of blocks with texture changes between 1900ns and 1100ns is 51, so the superposition rate at 1900ns is The striped head of the diagonal stripes is as follows Fig.10a and Fig.10b As shown in the figure, the number of blocks whose fingerprint textures change between 1900ns and 1100ns is 2, so the superposition rate at 1900ns is That is to say, the texture change affected by the stripe head is only 0.0313.

[0165] In some embodiments, more groups of texture change rates under time sequences may be obtained to improve the fingerprint anti-counterfeiting effect.

[0166] In some embodiments, the first anti-counterfeiting index value can be set in combination with the data such as the ridge and valley parameter values ​​and the texture change data at different time sequences in the above-mentioned embodiments, that is, the first anti-counterfeiting index value includes the anti-counterfeiting index value (threshold value) set according to various characteristic parameter values. When performing fingerprint identification to be identified, the parameter data corresponding to each anti-counterfeiting index value is obtained respectively, and the respective threshold values ​​are compared. When all the comparisons pass, it can be determined that the fingerprint to be identified is the real fingerprint of the target fingerprint, otherwise, it is a forged fingerprint of the target fingerprint. Alternatively, for different anti-counterfeiting index values, the corresponding ratios are set to set the first anti-counterfeiting index value. When performing fingerprint identification, the parameter data corresponding to each anti-counterfeiting index value is obtained respectively and multiplied by the corresponding ratios to obtain the final value, and it is determined whether the final value meets the numerical range corresponding to the first anti-counterfeiting index value. In other examples, other methods can also be used to set the first anti-counterfeiting index value, and this embodiment will not be described in detail.

[0167] This embodiment further takes into account that real fingers and fake fingerprints have different fits with the screen during the fingerprint collection process. Fake fingerprints require external force to press, and due to the different materials, hardness and pressing strength of fake fingerprints, fake fingerprints are more likely to have weak edges during collection, that is, there are fewer high-frequency signals in this part, which is manifested as a small value on the gradient. Fake fingerprints made of hard materials have a certain hardness and their shape is not easy to change. It is difficult to fit completely with the screen when pressed; fake fingerprints made of soft materials are more likely to deform when pressed, so they are prone to wrinkles when pressed, and it is also difficult to achieve a smooth fit with the screen. Since ultrasonic fingerprints affect the echo size through the difference in acoustic impedance, thereby forming a ridge and valley texture, in places where the fit is not good, it is not completely in contact with the screen. Fig.11 As shown, air is introduced between the fake fingerprint and the screen, and weak edges appear in places where the fit is not good.

[0168] In view of this, the present application embodiment provides another fingerprint anti-counterfeiting processing method to further improve the fingerprint anti-counterfeiting effect, such as Fig.12 As shown, in addition to the above steps S601-S603, the method further includes step S121, and step S603 is further divided into step S603a.

[0169] Step S121, obtaining a preset second anti-counterfeiting index value, where the second anti-counterfeiting index value is preset based on a fitting parameter value corresponding to the fingerprint to be identified as a target fingerprint;

[0170] Step S603a, determining whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value; or determining whether the fingerprint to be identified is a forged fingerprint based on a binary classification model established based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value.

[0171] In this embodiment, the fit parameter value can be used to indicate the fit between the fingerprint and the fingerprint collection device (eg, ultrasonic sensor device).

[0172] In one possible implementation, based on the first anti-counterfeiting index value and the second anti-counterfeiting index value, to determine whether the fingerprint to be identified is a forged fingerprint, the parameter data corresponding to the fingerprint to be identified and the first anti-counterfeiting index value and the second anti-counterfeiting index value can be obtained respectively, and compared respectively. When both are compared and passed, the fingerprint to be identified is determined to be a real fingerprint corresponding to the target fingerprint, otherwise, it is determined to be a forged fingerprint corresponding to the target fingerprint. In other possible implementations, the first anti-counterfeiting index value and the second anti-counterfeiting index value can also be set with a corresponding anti-counterfeiting ratio (similar to the above-mentioned first anti-counterfeiting index value includes a plurality of types of anti-counterfeiting index values ​​identification method), the identification order for the first anti-counterfeiting index value and the second anti-counterfeiting index value (for example, first determine whether the fingerprint to be identified is a forged index according to the first anti-counterfeiting index value, and when it is identified as not a forged index, further identify it according to the second anti-counterfeiting index, and vice versa), etc.

[0173] In another possible implementation, a binary classification model may be trained based on the first anti-counterfeiting index value and the second anti-counterfeiting index value. The model training method has been described in the above embodiment and will not be elaborated here.

[0174] Furthermore, presetting the second anti-counterfeiting index value in the above step S121 may include the following steps:

[0175] Collecting a fifth fingerprint image of the target fingerprint, and obtaining fingerprint gradient information of each pixel point in the fifth fingerprint image;

[0176] Filter out effective fingerprint gradient information and its corresponding pixel points that meet preset conditions from the fingerprint gradient information of each pixel point;

[0177] Obtaining the effective gradient proportion of the target fingerprint based on the number of pixels corresponding to the effective fingerprint gradient information; and / or obtaining an average effective gradient value based on the effective fingerprint gradient information and the number of pixels corresponding to it;

[0178] Based on the effective gradient proportion and / or the average effective gradient value, a fitting parameter value of the target fingerprint is obtained.

[0179] Combination Figure 13a-Figure 13c As shown, Fig.13a is the original fingerprint image (i.e., the fifth fingerprint image), Fig.13b is the gradient map, Fig.13c For the effective area, the effective gradient and the effective gradient ratio can be calculated as follows in this embodiment:

[0180] Step 1: Extract fingerprint edge information through Sobel operator, take I as the original fingerprint image of size Row*Col, and calculate the image gradient Edge.

[0181]

[0182] In the formula, G x Represents the gradient information in the x direction, G y Represents the gradient information in the y direction.

[0183] In this embodiment, the fingerprint gradient information of each pixel in the fifth fingerprint image is obtained, and the fingerprint edge information in the image can be extracted by using a Sobel operator, and the fingerprint gradient information of the pixel can be obtained based on the fingerprint edge information.

[0184] As you can understand, the Sobel operator is an important processing method in the field of computer vision. It is mainly used to obtain the first-order gradient of digital images and is often used for edge detection. The Sobel operator can detect edges by adding the weighted difference of the grayscale values ​​of the four areas of up, down, left, and right of each pixel in the image to the extreme value at the edge.

[0185] Step 2: In the obtained gradient information Edge, further obtain the gradient value of each pixel point, record the gradient value greater than 50 as valid, and count all valid gradient values ​​and the average valid gradient value:

[0186]

[0187] In the formula, Edge i is the gradient information of the i-th pixel of the target fingerprint, Cnt(x≥n) represents the number of pixels where x is greater than or equal to n, GradMean represents the average effective gradient value, Represents all valid gradient values.

[0188] In this embodiment, a gradient value greater than or equal to 50 is recorded as a valid gradient value. It should be noted that, in addition to being greater than or equal to 50 as a valid gradient value that meets the preset conditions, those skilled in the art can also adaptively set the valid fingerprint gradient information that meets the preset conditions in combination with actual applications.

[0189] Step 3: Calculate the effective gradient ratio according to the following formula:

[0190]

[0191] In the formula, ValidRatio represents the effective gradient ratio, Cnt(Edge i ≥50) represents the number of pixels, and Row*Col represents all pixels in the image.

[0192] In summary, this embodiment obtains the information of the epidermis and dermis of the fingerprint based on the principle of consistency of the epidermis and dermis texture of the human finger, and can better distinguish between true and false fingerprints by controlling the ridges and valleys and contrast and other indicators under the two sets of time series, thereby achieving the purpose of anti-counterfeiting. Since the acoustic impedance of some materials may be close to that of the finger, it is not sufficient to use only the contrast and other indicators under a certain time series. The design scheme of this embodiment calculates the contrast and ridge-valley ratio between the two sets of time series, and then controls the threshold range of the ratio indicators between the two time series to judge the true and false fingers. The ratio indicator is added to the discrimination of true and false fingers, which improves the discrimination of true and false fingerprints and optimizes the anti-counterfeiting performance. ; and by comparing the texture change rate of fingerprints at different time sequences, the recognition effect of true and false fingerprints can be further improved. Specifically, the fingerprint texture features are represented based on the block fingerprint direction field at different time sequences. Compared with other direction field calculation methods, the pixel gradient in the neighborhood can better improve the accuracy of the pixel direction; and by extracting the image gradient information, in the entire fingerprint image, the true and false fingerprints are further identified based on the effective gradient strength ratio; in addition, the series of features proposed above can be sent as feature vectors to the SVM binary classification model for learning and training, and finally an anti-counterfeiting SVM model that can distinguish true and false fingerprints is obtained, thereby improving the fingerprint anti-counterfeiting effect.

[0193] The present application also provides a fingerprint anti-counterfeiting processing device. Fig.14 As shown, the fingerprint anti-counterfeiting processing device 140 includes a first acquisition module 141, a second acquisition module 142 and a determination module 143, wherein:

[0194] A first acquisition module 141, which is configured to acquire a fingerprint recognition request, wherein the fingerprint recognition request includes a fingerprint to be recognized;

[0195] A second acquisition module 142, which is configured to acquire a preset first anti-counterfeiting index value corresponding to the fingerprint to be identified or a binary classification model established based on the first anti-counterfeiting index value;

[0196] A determination module 143, which is configured to determine whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model;

[0197] The first anti-counterfeiting index value is a value preset based on the characteristic parameter value corresponding to the fingerprint to be identified as the target fingerprint obtained at different time sequences.

[0198] In one embodiment, a first setting module is further included, which is configured to pre-set a first anti-counterfeiting index value, specifically including:

[0199] An acquisition unit, configured to acquire, for each target fingerprint, epidermis layer characteristic parameter values ​​and dermis layer characteristic parameter values ​​corresponding to the target fingerprint at different time sequences;

[0200] The setting unit is configured to respectively set a first anti-counterfeiting index value corresponding to each target fingerprint based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value.

[0201] In one embodiment, a model building module is further included, which is configured to build the binary classification model, specifically including:

[0202] A training unit, configured to train a preset binary classification model based on the first anti-counterfeiting index value to obtain the binary classification model;

[0203] The determination module 143 is specifically configured to use the binary classification model to analyze and process the fingerprint to be identified, obtain a binary classification result, and determine whether the fingerprint to be identified is a forged fingerprint based on the binary classification result.

[0204] In one embodiment, the acquisition unit includes:

[0205] A first acquisition subunit is configured to acquire a first fingerprint image of the target fingerprint at a first time sequence, determine the ridge position and the valley position in the first fingerprint image, and obtain the ridge parameter value and the valley parameter value of the epidermis according to the ridge position and the valley position in the first fingerprint image; and,

[0206] A second acquisition subunit is configured to acquire a second fingerprint image of the target fingerprint at a second timing sequence having a preset timing difference from the first timing sequence, determine the ridge position and the valley position in the second fingerprint image, and obtain the ridge parameter value and the valley parameter value of the dermis layer according to the ridge position and the valley position in the second fingerprint image.

[0207] In one embodiment, the setting unit includes:

[0208] a contrast acquisition subunit, configured to acquire, for each target fingerprint, a fingerprint contrast of the epidermis layer based on the ridge parameter values ​​and the valley parameter values ​​of the epidermis layer, and acquire a fingerprint contrast of the dermis layer based on the ridge parameter values ​​and the valley parameter values ​​of the dermis layer;

[0209] an index value determination subunit, which is configured to determine the anti-counterfeiting index value in a first time sequence based on the fingerprint contrast of the epidermis layer, the ridge parameter value and the valley parameter value of the epidermis layer, and determine the anti-counterfeiting index value in a second time sequence based on the fingerprint contrast of the dermis layer, the ridge parameter value and the valley parameter value of the dermis layer;

[0210] The first setting subunit is configured to set a first anti-counterfeiting index value corresponding to the target fingerprint based on the anti-counterfeiting index value in the first time sequence and the anti-counterfeiting index value in the second time sequence.

[0211] In one embodiment, the setting unit includes:

[0212] a parameter ratio acquisition subunit, configured to determine, for each target fingerprint, a ridge parameter ratio between a first time series and a second time series based on a ridge parameter value of the epidermis layer and a ridge parameter value of the dermis layer; and determine a valley parameter ratio between the first time series and the second time series based on a valley parameter value of the epidermis layer and a valley parameter value of the dermis layer;

[0213] a contrast ratio acquisition subunit, configured to acquire a fingerprint contrast of the epidermis layer based on the ridge parameter value and the valley parameter value of the epidermis layer, and acquire a fingerprint contrast of the dermis layer based on the ridge parameter value and the valley parameter value of the dermis layer; and determine a contrast ratio between a first time series and a second time series based on the fingerprint contrast of the epidermis layer and the fingerprint contrast of the dermis layer;

[0214] The second setting subunit is configured to determine the anti-counterfeiting index values ​​between different time sequences based on the ridge parameter ratio, valley parameter ratio and contrast ratio between the first time sequence and the second time sequence, and to set the first anti-counterfeiting index value corresponding to the target fingerprint based on the anti-counterfeiting index values ​​between different time sequences.

[0215] In one embodiment, the acquisition unit includes:

[0216] A first gradient acquisition subunit is configured to collect a third fingerprint image of the target fingerprint at a third time sequence, obtain the gradient of each pixel point in the third fingerprint image in a preset number of directions, and respectively use the direction with the smallest gradient as the first gradient direction of each pixel point;

[0217] A first texture acquisition subunit is configured to determine a first texture direction of a pixel block where each pixel point is located based on a first gradient direction of each pixel point, and acquire a texture direction feature value of the epidermis layer based on the first texture direction of each pixel block; and,

[0218] A second gradient acquisition subunit is configured to collect a fourth fingerprint image of the target fingerprint at a fourth time sequence having a preset time sequence difference with the third time sequence, obtain the gradient of each pixel point in the fourth fingerprint image in a preset number of directions, and respectively use the direction with the smallest gradient as the second gradient direction of each pixel point;

[0219] The first texture acquisition subunit is configured to determine the second texture direction of the pixel block where each pixel point is located based on the second gradient direction of each pixel point, and acquire the texture direction feature value of the dermis layer based on the second texture direction of each pixel block.

[0220] In one embodiment, the setting unit includes:

[0221] The third setting subunit is configured to obtain, for each target fingerprint, a texture change rate of the target fingerprint based on the texture directional characteristic value of the epidermis layer and the texture directional characteristic value of the dermis layer, and to set a first anti-counterfeiting index value corresponding to the target fingerprint based on the texture change rate.

[0222] In one embodiment, the texture change rate of the target fingerprint is obtained based on the texture directional eigenvalues ​​of the epidermis layer and the texture directional eigenvalues ​​of the dermis layer, specifically: based on the texture directional eigenvalues ​​of the epidermis layer and the texture directional eigenvalues ​​of the dermis layer, pixel blocks that produce texture directional changes are obtained, and the pixel blocks are marked as superposition blocks; based on the ratio between the number of superposition blocks and the total number of pixel blocks, the texture change rate of the target fingerprint is determined.

[0223] In one embodiment, the device further comprises:

[0224] A third acquisition module, which is configured to acquire a preset second anti-counterfeiting index value, where the second anti-counterfeiting index value is preset based on a fitting parameter value corresponding to the fingerprint to be identified as a target fingerprint;

[0225] The determination module 143 is specifically configured to determine whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value; or to determine whether the fingerprint to be identified is a forged fingerprint based on a binary classification model established based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value.

[0226] In one embodiment, a second setting module is further included, configured to pre-set a second anti-counterfeiting index value, specifically including:

[0227] a fingerprint gradient acquisition unit, configured to collect a fifth fingerprint image of the target fingerprint and acquire fingerprint gradient information of each pixel point in the fifth fingerprint image;

[0228] A screening unit, which is configured to screen out valid fingerprint gradient information and its corresponding pixel points that meet preset conditions from the fingerprint gradient information of each pixel point;

[0229] An effective gradient acquisition unit, configured to acquire an effective gradient ratio of the target fingerprint based on the number of pixels corresponding to the effective fingerprint gradient information; and / or acquire an average effective gradient value based on the effective fingerprint gradient information and the number of pixels corresponding to it;

[0230] A fitting parameter acquisition unit is configured to acquire a fitting parameter value of the target fingerprint based on the effective gradient proportion and / or the average effective gradient value.

[0231] The above-mentioned device provided in the embodiment of the present application can be used to implement the technical solution of the fingerprint anti-counterfeiting processing method in the above-mentioned embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0232] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software calling through processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware. For example, the first acquisition module 141 can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the first acquisition module 141. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0233] The embodiment of the present application also provides a computer storage medium, wherein the computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the fingerprint anti-counterfeiting processing method.

[0234] The above-mentioned medium provided in the embodiment of the present application can be used to implement the technical solution of the fingerprint anti-counterfeiting processing method in the above-mentioned embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0235] The present application also provides a fingerprint anti-counterfeiting system. Fig.15 As shown, it includes a fingerprint anti-counterfeiting processing device 140 and an ultrasonic sensor device 150 for executing the above method. The fingerprint anti-counterfeiting processing device 140 is used to be electrically connected to the ultrasonic sensor device 150 to realize ultrasonic fingerprint anti-counterfeiting detection.

[0236] The present application also provides an electronic device, including the fingerprint anti-counterfeiting processing system. Fig.16 As shown, the electronic device may include: a transceiver 161 , a processor 162 , and a memory 163 .

[0237] The processor 162 executes the computer execution instructions stored in the memory, so that the processor 162 calls the above-mentioned fingerprint anti-counterfeiting processing system to execute the solution in the above-mentioned embodiment. The processor 162 can be a general-purpose processor, including a central processing unit CPU, a network processor (NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0238] The memory 163 is connected to the processor 162 via a system bus and completes communication between them. The memory 163 is used to store computer program instructions.

[0239] The transceiver 161 may be used to obtain tasks to be executed and configuration information of the tasks to be executed.

[0240] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The transceiver is used to realize the communication between the database access device and other computers (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) and may also include non-volatile memory.

[0241] The above-mentioned device provided in the embodiment of the present application can be used to execute the technical solution of the fingerprint anti-counterfeiting processing method in the above-mentioned embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0242] The embodiment of the present application also provides a chip for running instructions, which is used to execute the technical solution of the fingerprint anti-counterfeiting processing method of the above embodiment.

[0243] The embodiment of the present application further provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the technical solution of the fingerprint anti-counterfeiting processing method of the above embodiment.

[0244] An embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When at least one processor executes the computer program, the technical solution of the fingerprint anti-counterfeiting processing method of the above embodiment can be implemented.

[0245] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0246] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

[0247] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0248] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the methods of various embodiments of the present application.

[0249] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0250] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0251] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0252] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0253] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic control unit or a main control device.

[0254] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0255] It is to be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not intended to limit the scope of the embodiments of the present application. In the embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0256] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A fingerprint anti-counterfeiting processing method, characterized in that: include: Obtaining a fingerprint recognition request, wherein the fingerprint recognition request includes a fingerprint to be recognized; Obtaining a preset first anti-counterfeiting index value corresponding to the fingerprint to be identified or a binary classification model established based on the first anti-counterfeiting index value, and determining whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model; The first anti-counterfeiting index value is a value preset based on the characteristic parameter value corresponding to the fingerprint to be identified as the target fingerprint at different time sequences; the characteristic parameter value includes: a ridge parameter value and a valley parameter value, or a texture direction characteristic value; Presetting the first anti-counterfeiting index value includes: For each target fingerprint, obtaining the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value respectively corresponding to the target fingerprint at different time sequences; and setting the first anti-counterfeiting index value corresponding to each target fingerprint respectively based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value; Wherein, when the characteristic parameter value includes a ridge parameter value and a valley parameter value, the first anti-counterfeiting index value is determined according to the anti-counterfeiting index values ​​at different time sequences, or the first anti-counterfeiting index value is determined according to the index anti-counterfeiting values ​​between different time sequences; the anti-counterfeiting index values ​​at different time sequences are determined according to the ridge parameter value, the valley parameter value and the fingerprint contrast, the anti-counterfeiting index values ​​between different time sequences are determined according to the ridge parameter ratio, the valley parameter ratio and the contrast ratio between different time sequences, and the fingerprint contrast is the difference between the ridge parameter value and the valley parameter value; or, When the characteristic parameter value includes a texture direction characteristic value, the first anti-counterfeiting index value is determined based on the texture change rate of the target fingerprint, and the texture change rate of the target fingerprint is obtained based on the texture direction characteristic value of the epidermis layer and the texture direction characteristic value of the dermis layer.

2. The method according to any one of claim 1, characterized in that: Establishing the binary classification model includes: Training a preset binary classification model based on the first anti-counterfeiting index value to obtain the binary classification model; Then, determining whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model includes: The binary classification model is used to analyze and process the fingerprint to be identified, obtain a binary classification result, and determine whether the fingerprint to be identified is a forged fingerprint based on the binary classification result.

3. The method according to claim 1 or 2, characterized in that: When the characteristic parameter values ​​include: ridge parameter values ​​and valley parameter values, the step of obtaining the epidermis characteristic parameter values ​​and the dermis characteristic parameter values ​​corresponding to the target fingerprint at different time sequences includes: Acquire a first fingerprint image of the target fingerprint at a first time sequence, determine the ridge position and the valley position in the first fingerprint image, and obtain the ridge parameter value and the valley parameter value of the epidermis according to the ridge position and the valley position in the first fingerprint image; and, A second fingerprint image of the target fingerprint at a second timing sequence having a preset timing difference from the first timing sequence is collected, the ridge position and the valley position in the second fingerprint image are determined, and the ridge parameter value and the valley parameter value of the dermis layer are obtained according to the ridge position and the valley position in the second fingerprint image.

4. The method according to claim 3, characterized in that: The step of setting the first anti-counterfeiting index value corresponding to each target fingerprint based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value comprises: For each target fingerprint, based on the ridge parameter value and the valley parameter value of the epidermis layer, a fingerprint contrast of the epidermis layer is obtained, and based on the ridge parameter value and the valley parameter value of the dermis layer, a fingerprint contrast of the dermis layer is obtained; Determine the anti-counterfeiting index value in a first time sequence based on the fingerprint contrast of the epidermis layer, the ridge parameter value and the valley parameter value of the epidermis layer, and determine the anti-counterfeiting index value in a second time sequence based on the fingerprint contrast of the dermis layer, the ridge parameter value and the valley parameter value of the dermis layer; Based on the anti-counterfeiting index value in the first time sequence and the anti-counterfeiting index value in the second time sequence, a first anti-counterfeiting index value corresponding to the target fingerprint is set.

5. The method according to claim 3, characterized in that: The step of setting the first anti-counterfeiting index value corresponding to each target fingerprint based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value comprises: For each target fingerprint, determining a ridge parameter ratio between a first time series and a second time series based on the ridge parameter value of the epidermis layer and the ridge parameter value of the dermis layer; and determining a valley parameter ratio between the first time series and the second time series based on the valley parameter value of the epidermis layer and the valley parameter value of the dermis layer; Acquire a fingerprint contrast of the epidermis layer based on the ridge parameter values ​​and the valley parameter values ​​of the epidermis layer, and acquire a fingerprint contrast of the dermis layer based on the ridge parameter values ​​and the valley parameter values ​​of the dermis layer; and determine a contrast ratio between a first time series and a second time series based on the fingerprint contrast of the epidermis layer and the fingerprint contrast of the dermis layer; Based on the ridge parameter ratio, valley parameter ratio and contrast ratio between the first time sequence and the second time sequence, the anti-counterfeiting index values ​​between different time sequences are determined, and the first anti-counterfeiting index value corresponding to the target fingerprint is set based on the anti-counterfeiting index values ​​between different time sequences.

6. The method according to claim 1 or 2, characterized in that: When the characteristic parameter value includes a texture direction characteristic value, the step of obtaining the epidermis characteristic parameter value and the dermis characteristic parameter value corresponding to the target fingerprint at different time sequences includes: Collecting a third fingerprint image of the target fingerprint at a third time sequence, obtaining the gradient of each pixel point in the third fingerprint image in a preset number of directions, and taking the direction with the smallest gradient as the first gradient direction of each pixel point; Based on the first gradient direction of each pixel point, determining the first texture direction of the pixel block where each pixel point is located, and acquiring the texture direction feature value of the epidermis layer based on the first texture direction of each pixel block; and, Collecting a fourth fingerprint image of the target fingerprint at a fourth time sequence having a preset time sequence difference with the third time sequence, obtaining the gradient of each pixel point in the fourth fingerprint image in a preset number of directions, and taking the direction with the smallest gradient as the second gradient direction of each pixel point; Based on the second gradient direction of each pixel point, the second texture direction of the pixel block where each pixel point is located is determined, and the texture direction feature value of the dermis layer is obtained based on the second texture direction of each pixel block.

7. The method according to claim 6, characterized in that The step of setting the first anti-counterfeiting index value corresponding to each target fingerprint based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value comprises: For each target fingerprint, the texture change rate of the target fingerprint is obtained based on the texture direction feature value of the epidermis layer and the texture direction feature value of the dermis layer, and the first anti-counterfeiting index value corresponding to the target fingerprint is set based on the texture change rate.

8. The method according to claim 7, characterized in that The acquiring the texture change rate of the target fingerprint based on the texture direction feature value of the epidermis layer and the texture direction feature value of the dermis layer includes: Based on the texture direction feature value of the epidermis layer and the texture direction feature value of the dermis layer, a pixel block producing a texture direction change is acquired, and the pixel block is marked as a superposition block; Based on the ratio between the number of the superimposed blocks and the total number of pixel blocks, the texture change rate of the target fingerprint is determined.

9. The method according to claim 1, characterized in that: Also includes: Acquire a preset second anti-counterfeiting index value, where the second anti-counterfeiting index value is preset based on a fitting parameter value corresponding to the fingerprint to be identified as a target fingerprint; Then, determining whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model includes: Determining whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value; Alternatively, a binary classification model established based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value is used to determine whether the fingerprint to be identified is a forged fingerprint.

10. The method according to claim 9, characterized in that Presetting the second anti-counterfeiting index value includes: Collecting a fifth fingerprint image of the target fingerprint, and obtaining fingerprint gradient information of each pixel point in the fifth fingerprint image; Filter out effective fingerprint gradient information and its corresponding pixel points that meet preset conditions from the fingerprint gradient information of each pixel point; Obtaining the effective gradient proportion of the target fingerprint based on the number of pixels corresponding to the effective fingerprint gradient information; and / or obtaining an average effective gradient value based on the effective fingerprint gradient information and the number of pixels corresponding to it; Based on the effective gradient proportion and / or the average effective gradient value, a fitting parameter value of the target fingerprint is obtained.

11. A fingerprint anti-counterfeiting processing device, characterized in that: include: A first acquisition module, configured to acquire a fingerprint recognition request, wherein the fingerprint recognition request includes a fingerprint to be recognized; A second acquisition module, which is configured to acquire a preset first anti-counterfeiting index value corresponding to the fingerprint to be identified or a binary classification model established based on the first anti-counterfeiting index value; a determination module, configured to determine whether the fingerprint to be identified is a forged fingerprint based on the first anti-counterfeiting index value or the binary classification model; The first anti-counterfeiting index value is a value preset based on the characteristic parameter value corresponding to the fingerprint to be identified as the target fingerprint at different time sequences; the characteristic parameter value includes: a ridge parameter value and a valley parameter value, or a texture direction characteristic value; The first setting module is configured to pre-set a first anti-counterfeiting index value, specifically including: An acquisition unit, configured to acquire, for each target fingerprint, epidermis layer characteristic parameter values ​​and dermis layer characteristic parameter values ​​corresponding to the target fingerprint at different time sequences; A setting unit, configured to respectively set a first anti-counterfeiting index value corresponding to each of the target fingerprints based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value; Wherein, when the characteristic parameter value includes a ridge parameter value and a valley parameter value, the first anti-counterfeiting index value is determined according to the anti-counterfeiting index values ​​at different time sequences, or the first anti-counterfeiting index value is determined according to the index anti-counterfeiting values ​​between different time sequences; the anti-counterfeiting index values ​​at different time sequences are determined according to the ridge parameter value, the valley parameter value and the fingerprint contrast, the anti-counterfeiting index values ​​between different time sequences are determined according to the ridge parameter ratio, the valley parameter ratio and the contrast ratio between different time sequences, and the fingerprint contrast is the difference between the ridge parameter value and the valley parameter value; or, When the characteristic parameter value includes a texture direction characteristic value, the first anti-counterfeiting index value is determined based on the texture change rate of the target fingerprint, and the texture change rate of the target fingerprint is obtained based on the texture direction characteristic value of the epidermis layer and the texture direction characteristic value of the dermis layer.

12. A computer storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the fingerprint anti-counterfeiting processing method according to any one of claims 1 to 10.

13. A fingerprint anti-counterfeiting system, characterized in that: It comprises an ultrasonic sensor device and a fingerprint anti-counterfeiting processing device for executing the fingerprint anti-counterfeiting processing method according to any one of claims 1 to 10, wherein the fingerprint anti-counterfeiting processing device is used to be electrically connected to the ultrasonic sensor device to realize ultrasonic fingerprint anti-counterfeiting detection.

14. An electronic device, characterized in that: A fingerprint anti-counterfeiting processing system comprising the fingerprint anti-counterfeiting processing system as claimed in claim 13.

Images