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

Abstract

The invention provides a fingerprint anti-counterfeiting processing method and device, a medium, a system and equipment, and relates to the field of fingerprint identification, and the method comprises the steps: obtaining a fingerprint identification request which comprises a to-be-identified fingerprint; obtaining a preset first anti-counterfeiting index value corresponding to the fingerprint to be identified or a dichotomy 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 dichotomy model; wherein the first anti-counterfeiting index value is a preset value based on the characteristic parameter value corresponding to the to-be-identified fingerprint as the target fingerprint under different time sequences. Through the method, the forged fingerprints can be efficiently identified, and the security of fingerprint identification is improved.

Description

[0001] This application claims priority to a Chinese application filed with the Patent Office of the People's Republic of China on August 24, 2023, with application number 202311089410.3, entitled "Method, Device, Medium, System, and Device for Finger-Level Anti-Counterfeiting," the entire contents of which are incorporated herein by reference. Technical Field: This application relates to finger-level identification technology, and more particularly to a method, device, medium, system, and device for finger-level anti-counterfeiting. Background: Finger-level identification is a technology that determines the identity of a system based on information provided by the system response and has been widely used in various electrical devices. Current finger-level recognition technology primarily relies on identifying the ridges and valleys of a finger for anti-counterfeiting purposes. This makes it vulnerable to 25D and 3D fake finger-levels. These fake finger-levels simulate the ridges and valleys of a finger, creating an acoustic impedance difference when attached to a screen, resulting in information consistent with a genuine finger-level image. This allows these fake finger-levels to pass through finger-level anti-counterfeiting systems, significantly reducing user safety. This application provides a method, apparatus, medium, system, and device for finger-level anti-counterfeiting to address the low security of current finger-level anti-counterfeiting systems. In a first aspect, the present application provides a method for processing finger-level anti-counterfeiting, comprising: obtaining a finger-level identification request, the finger-level identification request including a finger to be identified; obtaining a pre-set first security indicator value corresponding to the finger to be identified, or a binary classification model established based on the first security indicator value, and determining whether the finger to be identified is a counterfeit finger based on the first security indicator value or the binary classification model; wherein the first security indicator value is a pre-set value based on characteristic parameter values ​​corresponding to the finger to be identified as a target finger at different time sequences. In one embodiment, pre-setting the first security indicator value comprises: obtaining, for each target finger, epidermal layer characteristic parameter values ​​and dermal layer characteristic parameter values ​​corresponding to the target finger at different time sequences; and setting the first security indicator value corresponding to each target finger based on the epidermal layer characteristic parameter values ​​and the dermal layer characteristic parameter values.In one embodiment, 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 finger to be identified is a counterfeit finger based on the first anti-counterfeiting index value or the binary classification model includes: using the binary classification model to analyze and process the finger to be identified to obtain a binary classification result, and determining whether the finger to be identified is a counterfeit finger based on the binary classification result. In one embodiment, obtaining the epidermal layer characteristic parameter values ​​and the dermal layer characteristic parameter values ​​corresponding to the target finger level at different time sequences includes: acquiring a first finger-level image of the target finger level at a first time sequence, determining the ridge position and the valley position in the first finger-level image, and acquiring the ridge parameter value and the valley parameter value of the epidermal layer according to the ridge position and the valley position in the first finger-level image; and acquiring a second finger-level image of the target finger level at a second time sequence having a preset time sequence difference from the first time sequence, determining the ridge position and the valley position in the second finger-level image, and acquiring 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 finger-level image. In one embodiment, the setting of the first anti-counterfeiting index value corresponding to each target finger level based on the characteristic parameter value of the epidermis layer and the characteristic parameter value of the dermis layer includes: for each target finger level, obtaining the finger level contrast of the epidermis layer based on the ridge parameter value and the valley parameter value of the epidermis layer, and obtaining the finger level contrast of the dermis layer based on the ridge parameter value and the valley parameter value of the dermis layer; determining the anti-counterfeiting index value in a first time sequence based on the finger level contrast of the epidermis layer, the ridge parameter value and the valley parameter value of the epidermis layer, and determining the anti-counterfeiting index value in a second time sequence based on the finger level contrast of the dermis layer, the ridge parameter value and the valley parameter value of the dermis layer; and setting the first anti-counterfeiting index value corresponding to the target finger level based on the anti-counterfeiting index value in the first time sequence and the anti-counterfeiting index value in the second time sequence.In one embodiment, the setting of the first anti-counterfeiting index value corresponding to each target finger level based on the characteristic parameter value of the epidermis layer and the characteristic parameter value of the dermis layer includes: for each target finger level, determining the ridge parameter ratio between the first time series and the second time series based on the ridge parameter value of the epidermis layer and the ridge parameter value of the dermis layer; and, determining the 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; obtaining the finger level contrast of the epidermis layer based on the ridge parameter value and the valley parameter value of the epidermis layer, and obtaining the finger level contrast of the dermis layer based on the ridge parameter value and the valley parameter value of the dermis layer; and, determining the contrast ratio between the first time series and the second time series based on the fingerprint contrast of the epidermis layer and the fingerprint contrast of the dermis layer; determining the anti-counterfeiting index value between different time series based on the ridge parameter ratio, valley parameter ratio and contrast ratio between the first time series and the second time series, and setting the first anti-counterfeiting index value corresponding to the target finger level based on the anti-counterfeiting index value between different time series. In one embodiment, the obtaining of the epidermal layer characteristic parameter values ​​and the dermal layer characteristic parameter values ​​corresponding to the target finger level at different time sequences includes: acquiring a third finger-level image of the target finger level at a third time sequence, obtaining the gradient of each pixel point in the third finger-level image in a preset number of directions, and taking the direction with the smallest gradient as the first gradient direction of each pixel point; determining the first level direction of the pixel block where each pixel point is located based on the first gradient direction of each pixel point, and obtaining the level direction characteristic value of the epidermal layer based on the first level direction of each pixel block; and, acquiring a fourth finger-level image of the target finger level at a fourth time sequence having a preset time sequence difference from the third time sequence, obtaining the gradient of each pixel point in the fourth finger-level image in a preset number of directions, and taking the direction with the smallest gradient as the second gradient direction of each pixel point; determining the second level direction of the pixel block where each pixel point is located based on the second gradient direction of each pixel point, and obtaining the level direction characteristic value of the dermis layer based on the second level direction of each pixel block.In one embodiment, setting the first anti-counterfeiting indicator value corresponding to each target finger level based on the characteristic parameter value of the epidermis layer and the characteristic parameter value of the dermis layer includes: for each target finger level, obtaining the physical change rate of the target finger level based on the physical direction characteristic value of the epidermis layer and the physical direction characteristic value of the dermis layer, and setting the first anti-counterfeiting indicator value corresponding to the target finger level based on the physical change rate. In one embodiment, obtaining the physical change rate of the target finger level based on the physical direction characteristic value of the epidermis layer and the physical direction characteristic value of the dermis layer includes: obtaining pixel blocks that produce physical direction changes based on the physical direction characteristic value of the epidermis layer and the physical direction characteristic value of the dermis layer, and marking the pixel blocks as superimposed blocks; and determining the physical change rate of the target finger level based on the ratio between the number of superimposed blocks and the total number of pixel blocks. In one embodiment, the method further includes: obtaining a preset second anti-counterfeiting index value, wherein the second anti-counterfeiting index value is preset based on the fitting parameter value corresponding to the finger to be identified as the target finger; then determining whether the finger to be identified is a counterfeit finger based on the first anti-counterfeiting index value or the binary classification model includes: determining whether the finger to be identified is a counterfeit finger based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value; or, determining whether the finger to be identified is a counterfeit finger based on a binary classification model established based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value. In one embodiment, a second anti-counterfeiting index value is pre-set, including: collecting a fifth finger-level image of the target finger-level, and obtaining finger-level gradient information of each pixel point in the fifth finger-level image; screening out valid finger-level gradient information and its corresponding pixel points that meet preset conditions from the finger-level gradient information of each pixel point; obtaining the effective gradient ratio of the target finger-level based on the number of pixel points corresponding to the effective finger-level gradient information; and / or obtaining the average effective gradient value based on the effective finger-level gradient information and its corresponding number of pixel points; obtaining the fitting parameter value of the target finger-level based on the effective gradient ratio and / or the average effective gradient value.According to a second aspect of the present application, a finger-level anti-counterfeiting processing device is provided, comprising: a first acquisition module configured to obtain a finger-level identification request, wherein the finger-level identification request includes a finger to be identified; a second acquisition module configured to obtain a preset first security indicator value corresponding to the finger to be identified, or a binary classification model established based on the first security indicator value; and a determination module configured to determine whether the finger to be identified is a counterfeit finger based on the first security indicator value or the binary classification model; wherein the first security indicator value is a preset value based on characteristic parameter values ​​corresponding to the finger to be identified as a target finger at different time sequences. According to a third aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the finger-level anti-counterfeiting processing method. According to a fourth aspect of the present application, a finger-level anti-counterfeiting system is provided, comprising an ultrasonic sensor device and the finger-level anti-counterfeiting processing device, wherein the finger-level anti-counterfeiting processing device is electrically connected to the ultrasonic sensor device to implement ultrasonic finger-level anti-counterfeiting detection. According to a fifth aspect of the present application, an electronic device is provided, comprising the aforementioned finger-level anti-counterfeiting processing system. The finger-level anti-counterfeiting processing method, apparatus, medium, system, and device provided herein take into account that the finger-level characteristic parameters of counterfeit fingers vary more significantly than those of authentic fingers at different time sequences. When obtaining a finger-level identification request, a pre-set first anti-counterfeiting index value or a corresponding binary classification model corresponding to the target finger is obtained to perform anti-counterfeiting identification on the target finger. This anti-counterfeiting index value is set based on the finger-level characteristic data obtained for the target finger at different time sequences. During finger-level identification, counterfeit fingers can be efficiently identified, effectively improving the security of finger-level identification. BRIEF DESCRIPTION OF THE DRAWINGS To more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required in the embodiments or the prior art description. Obviously, the drawings described below represent some embodiments of the present application. Those skilled in the art can derive other drawings based on these drawings without inventive effort.FIG1 is a schematic diagram of a possible application scenario provided by an embodiment of the present application; FIG2a is a schematic diagram of an ultrasonic signal transmission model; FIG2b is a schematic diagram of an ultrasonic signal receiving model; FIG3a is a schematic diagram of an ultrasonic signal receiving model when a real finger presses; FIG3b is one of the schematic diagrams of an ultrasonic signal receiving model when a mold or a fake finger presses; FIG3c is a schematic diagram of an echo signal when a real finger presses; FIG3d is a schematic diagram of an echo signal when a mold or a fake finger presses; FIG4 is a comparison of echo signals at different finger levels; FIG5 is a comparison of epidermal contrast at different finger levels; FIG6 is a flow chart of a finger-level anti-counterfeiting processing method provided by an embodiment of the present application; FIG7 is a flow chart of step S602 in FIG6; FIG8a is a schematic diagram of finger-level directions in an embodiment of the present application; FIG8b is a schematic diagram of pixel blocks in an embodiment of the present application; FIG8c is a schematic diagram of level direction calculation in an embodiment of the present application; FIG9a is a schematic diagram of a finger-level image and direction field of a fake finger in a third time sequence; FIG9b is a schematic diagram of a finger-level image and direction field of a fake finger in a fourth time sequence; Figure 10a is a schematic diagram of a finger-level image and direction field of a strip-level head in the third time sequence; Figure 10b is a schematic diagram of a finger-level image and direction field of a strip-level head in the fourth time sequence; Figure 11 is a second schematic diagram of an ultrasonic signal receiving model when a mold or fake finger is pressed; Figure 12 is a flow chart of another finger-level anti-counterfeiting processing method provided in an embodiment of the present application; Figure 13a is a schematic diagram of an original finger-level image in an embodiment of the present application; Figure 13b is a gradient map corresponding to the original finger-level image in an embodiment of the present application; Figure 13c is a map of the effective area corresponding to the original finger-level image in an embodiment of the present application; Figure 14 is a schematic diagram of the structure of a finger-level anti-counterfeiting processing device provided in an embodiment of the present application; Figure 15 is a schematic diagram of the structure of a finger-level anti-counterfeiting processing system provided in an embodiment of the present application; and Figure 16 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only a portion of the embodiments of the present application, but not all of them.All other embodiments derived by persons of ordinary skill in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application. Before describing the embodiments of this application, the following terms are explained: Ridges and valleys: Both ridges and valleys belong to finger-level paths, representing raised or recessed paths, respectively, and are represented in finger-level data as areas with higher and lower signal intensities. Contrast: The difference between ridges and valleys in finger-level data represents finger-level signal strength. The embodiments of this application are described below in conjunction with application scenarios. The finger-level anti-counterfeiting processing method provided in the embodiments of this application can be applied to ultrasonic finger-level unlocking applications. More specifically, it can be applied to ultrasonic finger-level recognition applications in smart electronic devices, such as personal electronic devices like mobile phones and computers. It can also be used in other electronic devices such as financial payment, access control systems, and identity verification. Ultrasonic finger-level recognition generates a visual image of the finger-level by acquiring the intensity of sound waves reflected by the screen, finger, and air. Unlike optical imaging, the piezoelectric transducer within an ultrasonic sensor generates ultra-high-frequency sound waves that can penetrate the skin's epidermis. The reflected wave energy is measured to form an image, making it less susceptible to surface details and enabling identification even on soiled or wet hands. Compared to related capacitive and optical finger recognition technologies, ultrasonic finger recognition offers advantages in security (anti-counterfeiting) and accuracy. However, ultrasonic finger recognition technology is also more susceptible to 25D and 3D fake finger detection. These fake finger detections simulate the ridges and valleys of a finger, creating an acoustic impedance difference when attached to the screen. This produces information consistent with a genuine finger image and can be bypassed by identification and anti-counterfeiting systems, significantly reducing user safety. Therefore, the present invention provides a method, apparatus, medium, system, and device for finger-level anti-counterfeiting.FIG1 is a schematic diagram of an application scenario of ultrasonic finger-level recognition provided by the present application. As shown in FIG1 , the ultrasonic sensing 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 respectively electrically connected to a central controller 15. The ultrasonic piezoelectric sensor 11 may be a PVDF ultrasonic array sensor for excitation of the ultrasonic array and reception of echo signals. The analog-to-digital converter 12 may be a high-precision analog-to-digital converter for converting analog echo signal intensity into digital signals. The digital signals are then transmitted to the data processing center 14 via the storage unit 13 for preliminary processing of the finger-level data. The processed finger-level data are then transmitted to the server 20. The anti-counterfeiting server 20 further processes the data using a finger-level processing algorithm to perform functions such as finger-level registration and finger-level recognition and unlocking. The ultrasonic signal transmission and reception model (for a real finger) is shown in Figures 2a and 2b. This embodiment of the present application takes into account that, in practical applications, a real finger consists of both the epidermis and dermis, whereas a mold or fake finger cannot distinguish between the dermis and epidermis. Therefore, finger level simulation is typically performed by simulating the thickness of the epidermis and dermis. Referring to Figures 3a-3d, let the coupling layer thickness be d0, the speed of sound in the coupling layer be c0, and the screen thickness be ignored. The thickness from the dermis to the epidermis of the finger is d1, and the speed of sound is c1. Then, the time it takes for the sensor to receive the echo from the epidermis is t, and the time it takes for the sensor to receive the echo from the dermis is t1. The speed of sound waves in the fake finger material is C2, and the thickness of the fake finger is m, then the time to receive its deep-level echo is t2. If c1 = C2, the echo signal received at t1 or t2 is the surface level of the pressed object. If c1 < c2, then the deep-level echo signal has not been received at time q. If. C1 When q > c2, the deep-layer echo signal has already passed. When c1 < c2 or c1 > c2, the deep-layer echo signal differs from the surface-layer echo signal. Therefore, the difference in echo signals received at different time sequences can be used to distinguish between real and fake fingers. The calculation formulas for power, 4, and q are as follows: d[ ti — tn + 2 * -

[0002] C 1 Furthermore, there are significant differences in acoustic impedance between real fingers and other materials used to make fake fingers. Consequently, sound speed varies across different materials, affecting the fingerprint echo signal. This not only results in differences in fingerprint signal magnitude, but also in the physical characteristics of the real and fake fingers. As shown in Figure 4, these differences are due to differences in material acoustic parameters. Signal magnitudes for different materials can vary at the same time sequence, and the timing of the maximum echo signal can also vary. Furthermore, the contrast (averaging a large amount of data) of the epidermis between real fingers and fake fingers made of different materials varies significantly, as shown in Figure 5. Compared to finger-level processing algorithms in related arts, this embodiment, upon receiving a finger-level identification request, performs anti-counterfeiting identification on the target finger by obtaining a pre-set security index value or a corresponding binary classification model. This security index value is set based on pre-acquired finger-level feature data of the target finger at different time sequences. During the identification process, the security index value or binary classification model, determined by using finger-level features and their variations at different time sequences, can effectively improve the security of finger-level identification. Furthermore, by calculating the ridge-valley parameters and contrast values ​​of the target finger at different time sequences, and calculating the ridge-valley ratio and contrast ratio between the time sequences; and comparing the rate of change of the finger's texture at different time sequences based on the finger's texture direction field at different time sequences, genuine and fake fingers can be distinguished. Furthermore, by identifying the finger to be identified in combination with a second anti-counterfeiting index value set based on the target finger's fitting parameters, the effectiveness of distinguishing genuine from fake fingers can be further improved. The following uses the anti-counterfeiting server 20 used in the above-mentioned application scenario as an example to describe the technical solution of this application in detail in conjunction with specific embodiments. These specific embodiments may be combined with each other, and identical or similar concepts or processes may not be described in detail in certain embodiments. Figure 6 is a flow diagram of a finger anti-counterfeiting processing method provided by an embodiment of the present application, including steps S601-S603. Step S601: Obtain a finger identification request, wherein the finger identification request includes the finger to be identified.Taking the screen unlocking of a mobile phone as an example, a user presses their finger at the corresponding position of the phone's finger level acquisition module to trigger a finger level identification request. The anti-counterfeiting server obtains the user's finger level to be identified and performs subsequent finger level anti-counterfeiting identification. The finger level to be identified may include finger level feature data at two different time sequences. These different time sequences may correspond to two different time sequences with target finger level feature parameter values, and the timing difference between the two different time sequences may be between 1100ns and 2000ns. Step S602: Obtain a pre-set first anti-counterfeiting indicator value corresponding to the finger level to be identified, or a binary classification model established based on the first anti-counterfeiting indicator value. The first anti-counterfeiting indicator value is a pre-set value based on the feature parameter values ​​corresponding to the finger level to be identified at the different time sequences obtained as the target finger level. In related art, the finger image of the finger to be identified is typically matched with stored authenticated finger images. Finger features in the finger to be identified and the various finger images are compared, such as the consistency or similarity between ridge and valley features, to determine whether the finger to be identified is an authenticated finger. This process is easily exploited by highly simulated fake fingers, failing to achieve effective anti-counterfeiting effectiveness. In this embodiment, after receiving a finger identification request, a first security indicator value corresponding to the finger to be identified is obtained, and a binary classification model is established based on this first security indicator value. This first security indicator value or the corresponding binary classification model is then used in subsequent steps for finger anti-counterfeiting identification. This first security indicator value or the corresponding binary classification model is pre-set based on the feature parameter values ​​corresponding to the target finger at different time sequences. This takes into account the characteristic variations of a genuine finger at different time sequences, thereby enhancing anti-counterfeiting effectiveness against fake fingers. It is understood that the target finger is the finger to be identified, i.e., the finger level of the genuine finger corresponding to the finger to be identified.The first security indicator value is a pre-set value based on the characteristic parameter values ​​corresponding to the target finger level at different time sequences. For example, if the characteristic parameter value is a ridge parameter value, the ridge parameter value at the 1100 ns T finger level is 143.7, and the ridge parameter value at the 1900 ns T finger level is 143.9. Those skilled in the art can, based on actual applications, set a reasonable range of ridge parameter values ​​at different time sequences, such as 143.5 to 144.0, and / or set a range of ridge parameter variations between different time sequences, such as 0.2 to 0.5. It should be noted that those skilled in the art can adaptively set the value range of the first security indicator value based on actual applications and a large number of genuine finger level samples. The above numerical ranges are provided in this embodiment for illustrative purposes only and are not specifically limited. In some embodiments, in addition to the identification of authenticated fingers (i.e., target fingers) imitating fake fingers, there are also some scenarios involving the identification of non-authenticated or non-imitation fingers in actual applications. For example, a finger identification request initiated by a user who has not undergone finger authentication is possible. To improve the system's finger identification efficiency, this embodiment may also perform initial identification of the finger to be identified after step S601 and before step S602. This process can be implemented based on existing technologies. The similarity between the finger to be identified and the stored authenticated fingers is determined, and the finger with the highest similarity is selected. If the similarity is greater than or equal to a similarity threshold, the process proceeds to step S602 to obtain the corresponding first security index value, i.e., the first security index value set based on the selected finger. If the similarity is lower than the similarity threshold, the finger to be identified is significantly different from the authenticated finger, indicating that it is a non-authenticated or non-imitation finger, and the finger identification can be directly rejected. Step S603: Determine whether the finger to be identified is a counterfeit finger based on the first security index value or the binary classification model. In one embodiment, the characteristic value corresponding to the first security index value of the finger to be identified is obtained and compared with the first security index value. If it is within the range corresponding to the first security index value, it is indicated as the target finger; otherwise, it is a counterfeit finger.For example, the first security indicator value is set based on the ridge parameter value of the target finger at 1100 ns and the ridge parameter value of the finger at 1900 ns. The ridge parameter variation range between different time sequences is set between 0.2 and 0.5. By obtaining the ridge parameter value of the finger to be identified at 1100 ns and the ridge parameter value of the finger at 1900 ns, it is determined whether the ridge parameter variation of the finger to be identified at these two time sequences is within the range of 0.2 to 0.5. In another embodiment, to further improve finger level recognition efficiency, the first security indicator value can also be used to train a binary classification model. During finger level recognition, the finger level feature data of the finger to be identified at different time sequences is input into the binary classification model. Based on the output of the binary classification model, it is determined whether the finger to be identified is the target finger or a counterfeit finger. As can be seen, this embodiment utilizes pre-set first security index values ​​or corresponding binary classification models based on target finger feature data at different time sequences for anti-counterfeiting identification of the target finger. Compared to related techniques that rely solely on static finger ridge and valley features, which are susceptible to being misinterpreted by highly imitative fake fingers, this embodiment considers finger feature data at different time sequences, effectively improving anti-counterfeiting effectiveness against fake fingers and thereby ensuring the security of the finger recognition process. In one embodiment, the pre-setting of the first security index value in step S602, as shown in FIG7 , may include the following steps: Step S602a: For each target finger, obtain the epidermal layer feature parameter values ​​and dermal layer feature parameter values ​​corresponding to the target finger at different time sequences; Step S602b: Based on the epidermal layer feature parameter values ​​and dermal layer feature parameter values, set the first security index value corresponding to each target finger. It will be understood that in this embodiment, each target finger refers to all authenticated fingers of the anti-counterfeiting server.As the number of fake fingertips increases, the effectiveness of anti-counterfeiting measures based solely on single-frame fingertips data or fingertips processing is poor. In this embodiment, considering human biometrics, a real finger consists of an epidermis and a dermis. The characteristic parameters of the epidermis and dermis are usually consistent or have negligible differences. However, fake fingers do not have these layers and can usually only mimic the depth (i.e., thickness) of the real epidermis. Due to differences in acoustic impedance, these layers can easily vary significantly at different time sequences. Therefore, this embodiment obtains the corresponding epidermis and dermis characteristic parameter values ​​at different time sequences and sets a first anti-counterfeiting index value based on these values. This effectively distinguishes between real and fake fingers, achieving anti-counterfeiting purposes. In one embodiment, establishing the binary classification model may include the following steps: training a preset binary classification model based on the first security index value to obtain the binary classification model; then, determining whether the finger to be identified is a counterfeit finger based on the first security index value or the binary classification model in step S603 may include the following steps: analyzing and processing the finger to be identified using the binary classification model to obtain a binary classification result, and determining whether the finger to be identified is a counterfeit finger based on the binary classification result. In this embodiment, the preset binary classification model may be a support vector machine (SVM) model, whose basic model is a linear classifier with maximum margin defined in a feature space, and the optimal separating hyperplane is determined by maximizing the margin. In some embodiments, when verifying a finger to be identified, in order to further improve the anti-counterfeiting accuracy of the finger, 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 finger fitting parameters mentioned later. These various anti-counterfeiting index values ​​can be used to train an SVM model. When performing finger identification, the feature data corresponding to the finger to be identified is input into the trained model. Based on the binary classification output result, it can be quickly determined whether the finger to be identified is a counterfeit finger.In one embodiment, considering that the ridge-valley parameters of the epidermis and the ridge-valley parameters of the dermis of a finger have certain characteristics and variation patterns, the ridge-valley parameter value of the finger level can be used to set a first anti-counterfeiting index value. The above steps of obtaining the epidermis characteristic parameter values ​​and the dermis characteristic parameter values ​​corresponding to the target finger level at different time sequences can include the following steps: acquiring a first finger-level image of the target finger level at a first time sequence, determining the ridge position and the valley position in the first finger-level image, and acquiring the ridge parameter value and the valley parameter value of the epidermis based on the ridge position and the valley position in the first finger-level image; and acquiring a second finger-level image of the target finger level at a second time sequence having a preset time sequence difference from the first time sequence, determining the ridge position and the valley position in the second finger-level image, and acquiring the ridge parameter value and the valley parameter value of the dermis based on the ridge position and the valley position in the second finger-level image. In this embodiment, ultrasound can be used to collect finger-level images at different time sequences. For example, a finger-level image of the epidermis can be collected at 1100 ns, and a finger-level image of the dermis can be collected at 1900 ns. The ridge and valley positions in the finger-level images are calculated, and then all ridge and valley values ​​in the finger-level images are counted. The ridge / valley parameter values ​​at different time sequences are obtained using a mean value algorithm. In applications where the epidermis characteristic parameter values ​​at different time sequences include ridge / valley parameter values, at least the following two implementations can be used to set the corresponding first anti-counterfeiting value. Method 1: In the above steps, the first anti-counterfeiting index value corresponding to each target finger level is set based on the characteristic parameter value of the epidermis layer and the characteristic parameter value of the dermis layer, which may include the following steps: for each target finger level, based on the ridge parameter value and the valley parameter value of the epidermis layer, the finger level contrast of the epidermis layer is obtained, and based on the ridge parameter value and the valley parameter value of the dermis layer, the finger level contrast of the dermis layer is obtained; based on the finger level contrast of the epidermis layer, the ridge parameter value and the valley parameter value of the epidermis layer, the anti-counterfeiting index value in the first time sequence is determined, and based on the finger level contrast of the dermis layer, the ridge parameter value and the valley parameter value of the dermis layer, the anti-counterfeiting index value in the second time sequence is determined; based on the anti-counterfeiting index value in the first time sequence and the anti-counterfeiting index value in the second time sequence, the first anti-counterfeiting index value corresponding to the target finger level is set.In this embodiment, the first security indicator value is determined based on the ridge / valley parameter values ​​and finger level contrast at different time sequences. The finger level contrast = ridge parameter value minus valley parameter value, which can represent the finger level signal strength. In one example, the first security indicator value is set based on the security indicator value at the first time sequence and the security indicator value at the second time sequence. The first security indicator value can include the ridge / valley parameter value at the first time sequence and the finger level contrast threshold. During finger level identification, the ridge / valley parameter value and finger level contrast of the finger to be identified at the first time sequence are compared with the corresponding thresholds. If both values ​​are within the threshold range, identification is successful; otherwise, the finger to be identified is determined to be counterfeit. Method 2: In the above steps, the first anti-counterfeiting index value corresponding to each target finger level is set based on the characteristic parameter value of the epidermis layer and the characteristic parameter value of the dermis layer, which may include the following steps: for each target finger level, based on the ridge parameter value of the epidermis layer and the ridge parameter value of the dermis layer, determining the ridge parameter ratio between the first time series and the second time series; and, based on the valley parameter value of the epidermis layer and the valley parameter value of the dermis layer, determining the valley parameter ratio between the first time series and the second time series; obtaining the finger level contrast of the epidermis layer based on the ridge parameter value and the valley parameter value of the epidermis layer, and obtaining the finger level contrast of the dermis layer based on the ridge parameter value and the valley parameter value of the dermis layer; and, determining the contrast ratio between the first time series and the second time series based on the fingerprint-contrast of the epidermis layer and the fingerprint-contrast of the dermis layer; determining the anti-counterfeiting index value between different time series based on the ridge parameter ratio, valley parameter ratio and contrast ratio between the first time series and the second time series, and setting the first anti-counterfeiting index value corresponding to the target finger level based on the anti-counterfeiting index value between different time series. Compared to the first method described above, because the acoustic impedance of some materials may be close to that of a finger, using only indicators such as contrast at a specific time series is insufficient. This embodiment calculates the contrast and ridge-to-valley ratio of two time series, then controls the threshold range of the ratio between these two time series to distinguish between genuine and fake fingers. Incorporating the ratio indicator into the identification process improves the distinction between genuine and fake fingers, thereby optimizing anti-counterfeiting performance.Specifically, this embodiment sets the first security indicator value based on the security indicator values ​​between different time series (referred to as inter-time series), that is, based on the changes in finger-level characteristic parameters between different time series. Specifically, the inter-time series contrast ratio = the finger-level contrast of the dermis in the second time series / the finger-level contrast of the epidermis in the first time series, and the inter-time series ridge / valley parameter ratio = the ridge (valley) parameter value of the dermis in the second time series / the ridge (valley) parameter value of the epidermis in the first time series. Because the finger-level characteristic data of the dermis and epidermis layers of a genuine finger are consistent, their contrast ratios and ridge-valley parameter ratios between time series typically have small differences. In this embodiment, the first security indicator value is set based on the inter-time series contrast ratio and ridge-valley parameter ratio. When the finger to be identified exceeds the corresponding threshold range, it is identified as a counterfeit finger. In some embodiments, the first security indicator value can be determined using both the first and second methods described above. That is, the first security indicator value is determined based on the security indicator values ​​at different time series and the security indicator values ​​between different time series. When performing finger-level identification, it's necessary to simultaneously compare the finger-level information to be identified with the security index values ​​at different time sequences, as well as the security index values ​​between time sequences, to further enhance anti-counterfeiting effectiveness. In another embodiment, since sound propagation is time-dependent (the longer the time), the longer the sound wave travels, and the sound wave signal is reflected after initially reaching the epidermis. A portion of the sound wave that passes through the epidermis continues to travel deeper, and upon reaching the dermis, it is reflected again. Therefore, the echo signals received at different times can represent the texture at different depths. This embodiment, based on the consistency of the texture of the epidermis and dermis at the human finger level, generates finger-level images at different time sequences during a single press, and compares these texture differences to enhance finger-level anti-counterfeiting performance.Specifically, the above steps of obtaining the epidermal layer characteristic parameter values ​​and the dermal layer characteristic parameter values ​​corresponding to the target finger level at different time sequences may include the following steps: acquiring a third finger-level image of the target finger level at a third time sequence, acquiring the gradient of each pixel point in the third finger-level image in a preset number of directions, and taking the direction with the smallest gradient as the first gradient direction of each pixel point; determining the first level direction of the pixel block where each pixel point is located based on the first gradient direction of each pixel point, and acquiring the level direction characteristic value of the epidermal layer based on the first level direction of each pixel block; and acquiring a fourth finger-level image of the target finger level at a fourth time sequence having a preset time sequence difference from the third time sequence, acquiring the gradient of each pixel point in the fourth finger-level image in a preset number of directions, and taking the direction with the smallest gradient as the second gradient direction of each pixel point; determining the second level direction of the pixel block where each pixel point is located based on the second gradient direction of each pixel point, and acquiring the level direction characteristic value of the dermis layer based on the second level direction of each pixel block. In this embodiment, the finger-level directional feature value is calculated and compared with common directional operator convolutions to find the direction algorithm that maximizes or minimizes the convolution result, which is used as the direction of the point. Specifically, a gradient calculation is performed on pixels within a preset neighborhood (e.g., a 5 x 5 neighborhood) of a single pixel point. The minimum gradient direction is used as the direction of the pixel point. The direction is then determined by block. The finger-level image is divided into a preset number of pixel blocks (e.g., 8 x 8 large blocks). The direction is expanded from the pixel point direction to the block direction to obtain a relatively accurate finger-level direction field. The directional feature values ​​at different time sequences can be used to determine the first security index value. Alternatively, in subsequent steps, the changes in the directions of each block at different time sequences can be compared to obtain the directional change rate of the pixel blocks at different time sequences to further determine the security index value. For ease of understanding, referring to Figures 8a-8c, the finger-level direction is defined as shown in Figure 8a. In Figure 8a, the numbers 0 to 7 represent eight different directions. With a certain pixel point x as the center, the finger-level direction is divided into eight directions within its 5 x 5 neighborhood. The entire finger-level image can be divided into 8 x 8 pixel blocks, and the level direction of each pixel block is marked, as shown in Figure 8b, to facilitate comparison of its level changes.The steps of obtaining the gradient of each pixel in the third / fourth finger-level image (hereinafter referred to as image) in a preset number of directions and taking the direction with the minimum gradient as the first / second gradient direction of each pixel may be as follows:

[0003] Step 1: Take a pixel point x in the image, take the values ​​of the surrounding 5 x 5 neighborhood pixels, and calculate the gradients in eight directions.

[0004] Step 2: Combined with Figure 8c, the gradient of three parallel lines in a certain direction is calculated. The formula is as follows:

[0005] Gradi Among them, Gradi represents the gradient of the pixel in the i-th direction, and i=0,l,7,0 represents the neighborhood pixel in the i-th direction.

[0006] Step 3: Take the minimum gradient within the 5 x 5 neighborhood of each pixel as the gradient direction of the point. The formula is as follows: After obtaining the gradient direction of the pixel point, this embodiment determines the gradation direction of the pixel block where each pixel point is located according to the gradient direction of the pixel point, and obtains the gradation direction feature value of the epidermis / dermis layer based on the gradation direction of each pixel block. Specifically,

[0007] Step 4: Extend the point direction calculation to block direction calculation, and count the direction with the highest frequency in each block as the level direction of the block. The formula is as follows:

[0008] BlcokOF = max(Cnkradi), where CntGradi represents the frequency or number of occurrences of the i-th direction. 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, the first, second, third, fourth, etc., are used to distinguish similar objects and have no other special meaning. Compared to the above method, which uses parameters such as ridge and valley parameters between the epidermis and dermis to set the first security indicator value, this embodiment considers the changes in the physical characteristics between the epidermis and dermis to set the first security indicator value. Specifically, the above step of determining the first security indicator value based on the characteristic parameter values ​​of the epidermis and the characteristic parameter values ​​of the dermis may include the following steps: for each target finger level, based on the physical direction characteristic value of the epidermis and the physical direction characteristic value of the dermis, obtaining the physical change rate of the target finger level, and setting the first security indicator value corresponding to the target finger level based on the physical change rate. It should be noted that those skilled in the art may adaptively set the first security indicator value based on the physical change rate in accordance with actual applications. For example, if the physical change rate of the target finger is 0.36, the first security indicator value may be set to a physical change rate within 0.4. Furthermore, in the above steps, obtaining the physical change rate of the target finger based on the physical direction characteristic values ​​of the epidermis layer and the dermis layer may include the following steps: obtaining pixel blocks that produce physical direction changes based on the physical direction characteristic values ​​of the epidermis layer and the dermis layer, and marking the pixel blocks as superimposed blocks; and determining the physical change rate of the target finger based on the ratio between the number of superimposed blocks and the total number of pixel blocks. Taking the epidermal layer-level directional feature value OF0 at the third time sequence (e.g., the first frame of finger-level data) as a reference, OF0 represents the directional field at the third time sequence. Calculate the directional field OFj of the finger-level image at a different time sequence (e.g., the fourth time sequence with a time sequence difference), and compare the change rate between its directional field and OF0: Where, DiffoF represents the change in the direction of the pixel block generated between the third timing and the fourth timing, COUNT (Diff OFo} > l and Diff OFoV 7) represents the pixel block that experiences a change in the directional orientation, i.e., when the directional orientation change of the pixel block is greater than 1 and less than 7. 64 represents the total number of pixel blocks. Through experimental comparison, the directional fields of the true and false fingers were obtained in the first frame (1100 ns) and subsequent frames (e.g., 1900 ns). The false finger was pressed with a diagonal bar. The finger images and their directional fields of different frames were captured, as shown in Figures 9a and 9b. It can be clearly seen that the finger image acquired at 1900 ns is superimposed with the bar header directional orientation following the false finger. This demonstrates the rationality of the proposed method of determining true and false fingers based on finger directional orientation changes at different time sequences. Statistics show that the number of blocks experiencing directional orientation changes between the 1900 ns and 1100 ns false fingers is 51, and the superposition ratio at 1900 ns is 2 = 0.7968. The stripe header of the oblique stripe level is shown in Figures 10a and 10b 64. The number of blocks where the physical change occurs between the 1900 ns and 1100 ns finger levels is 2. Therefore, the superposition rate at 1900 ns is λ = 0.0313. In other words, the physical change caused by the stripe header is only 0.0313. In some embodiments, the physical change rates under more time sequences can be obtained to improve the finger level anti-counterfeiting effect. In some embodiments, a first anti-counterfeiting indicator value can be set based on data such as ridge and valley parameter values ​​and physical change data under different time sequences in the above embodiments. Specifically, this first anti-counterfeiting indicator value includes an anti-counterfeiting indicator value (threshold value) set based on various characteristic parameter values. When identifying the finger to be identified, the parameter data corresponding to each anti-counterfeiting indicator value is obtained and compared with the respective threshold values. If all comparisons pass, the finger to be identified can be determined to be a genuine target finger. Otherwise, it is a counterfeit of the target finger. Alternatively, for different security indicator values, corresponding ratios are set to set the first security indicator value. During finger-level recognition, parameter data corresponding to each security indicator value is obtained and multiplied by the corresponding ratio to obtain a final value. A determination is then made as to whether the final value falls within the numerical range corresponding to the first security indicator value. In other examples, other methods may be used to set the first security indicator value, which will not be further described in this embodiment.This embodiment further considers the different contact conditions between real fingers and fake fingers during finger-level acquisition. Fake fingers require external pressure, and due to differences in material, hardness, and pressure, fake fingers are more likely to exhibit weak edges during acquisition. This means that there is less high-frequency signal in this area, manifesting as a small gradient value. Fake fingers made of hard materials, due to their certain hardness, are less likely to change shape, making it more difficult to achieve complete contact with the screen when pressed. Fake fingers made of soft materials are more likely to deform when pressed, resulting in wrinkles and difficulty achieving a smooth contact with the screen. Because ultrasonic finger measurements use acoustic impedance differences to influence echo size, resulting in ridges and valleys, areas of poor contact with the screen may contain air trapped between the fake finger and the screen, as shown in Figure 11. This can result in weak edges in these areas. In view of this, the embodiment of the present application provides another finger-level anti-counterfeiting processing method to further improve the finger-level anti-counterfeiting effect. As shown in FIG12 , in addition to the above steps S601-S603, the method further includes step S121, and step S603 is further divided into step S603a. oStep S121: Obtain a preset second security index value, where the second security index value is preset based on the fitting parameter value corresponding to the finger to be identified as the target finger. Step S603a: Determine whether the finger to be identified is a counterfeit based on the first security flag value and the second security index value; or determine whether the finger to be identified is a counterfeit using a binary classification model established based on the first security flag value and the second security index value. In this embodiment, the fitting parameter value can be used to indicate the degree of fit between the finger and a finger level acquisition device (e.g., an ultrasonic sensor device). In one implementation, determining whether the finger to be identified is a counterfeit based on the first security index value and the second security index value can be performed by obtaining parameter data corresponding to the finger to be identified and the first and second security index values, respectively, and comparing them. If both values ​​compare favorably, the finger to be identified is determined to be an authentic finger corresponding to the target finger. Otherwise, the finger is determined to be a counterfeit finger corresponding to the target finger. In other possible implementations, corresponding anti-counterfeiting ratios may be set for the first and second security indicator values ​​(similar to the aforementioned identification method for the first security indicator value containing multiple types of security indicator values), and the identification order for the first and second security indicator values ​​may be determined (for example, first determining whether the to-be-identified finger is a forgery indicator based on the first security indicator value; if it is not, further identification is performed based on the second security indicator, and vice versa). In another possible implementation, a binary classification model may be trained based on the first and second security indicator values. The model training method has been described in the above embodiment and will not be further elaborated here.Furthermore, presetting the second anti-counterfeiting indicator value in step S121 may include the following steps: capturing a fifth finger-level image of the target finger-level, obtaining finger-level gradient information for each pixel in the fifth finger-level image; screening valid finger-level gradient information and its corresponding pixels that meet preset conditions from the finger-level gradient information for each pixel; obtaining an effective gradient percentage for the target finger-level based on the number of pixels corresponding to the valid finger-level gradient information; and / or obtaining an average effective gradient value based on the valid finger-level gradient information and its corresponding number of pixels; and obtaining a fitting parameter value for the target finger-level based on the effective gradient percentage and / or the average effective gradient value. With reference to Figures 13a-13c, Figure 13a shows the original finger-level image (i.e., the fifth finger-level image), Figure 13b shows the gradient map, and Figure 13c shows the effective area. In this embodiment, the effective gradient and effective gradient percentage may be calculated as follows:

[0009] Step 1: Extract finger-level edge information through Sobel operator, take I as the original finger-level image of size Row*Co1, and calculate the image gradient Edgeo Wherein, Gx represents the gradient information in the x-direction, and Gy represents the gradient information in the y-direction. In this embodiment, the finger-level gradient information of each pixel in the fifth finger-level image is obtained, and the finger-level edge information in the image can be extracted by the Sobel operator, and the finger-level gradient information of the pixel is obtained based on the finger-level edge information. It can be understood that 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 a digital image and is often used for edge detection. The Sobel operator can detect the edge by taking the weighted difference of the grayscale values ​​of the four areas of the upper, lower, left, and right of each pixel in the image and reaching an extreme value at the edge. Step 2: In the obtained gradient information Edge, the gradient value of each pixel is further obtained, and the gradient value greater than 50 is recorded as valid. All valid gradient values ​​and the average valid gradient value are counted:

[0010] GradMean = In the formula, Edge tis the gradient information of the i-th pixel at the target level, Cnt(x²n) represents the number of pixels where x is greater than or equal to n, GradMean represents the average effective gradient value, and zhanjie represents all effective gradient values. In this embodiment, gradient values ​​greater than or equal to 50 are recorded as effective gradient values. It should be noted that in addition to being considered as a valid gradient value that meets the preset conditions when greater than or equal to 50, those skilled in the art may also adaptively set the effective level gradient information that meets the preset conditions based on actual applications.

[0011] Step 3: Calculate the effective gradient ratio according to the following formula:

[0012] ValidRatio = Where ValidRatio represents the effective gradient ratio, Cnt(Edgei > 50) represents the number of pixels, and Row * Col represents all pixels in the image. In summary, this embodiment obtains information about the epidermal and dermal layers of a finger based on the principle of physical consistency between the epidermis and dermis of a human finger. By controlling indicators such as ridges, valleys, and contrast in two time series, it can effectively distinguish between genuine and fake fingers, achieving anti-counterfeiting purposes. Because the acoustic impedance of some materials may be similar to that of a finger, using only indicators such as contrast in a certain time series is not sufficient. This embodiment's design calculates the contrast and ridge-valley ratio between the two time series, then controls the threshold range of these two ratio indicators for distinguishing between genuine and fake fingers. Incorporating this ratio indicator into the discrimination of genuine and fake fingers improves the discrimination between genuine and fake fingers, thereby optimizing anti-counterfeiting performance. Furthermore, by comparing the rate of change of the physical level of the finger at different time series, the identification of genuine and fake fingers is further enhanced. Specifically, the physical characteristics of the finger level are represented based on the block-by-block finger level direction field at different time series. Compared with other direction field calculation methods, the pixel gradient within the neighborhood can better improve the accuracy of the pixel point direction. Furthermore, by extracting image gradient information, in the entire finger level image, The ratio of effective gradient strength is used to further identify true and false finger levels; in addition, the series of features proposed above can be sent as feature vectors into the SVM binary classification model for learning and training, and finally an anti-counterfeiting SVM model that can distinguish true and false finger levels is obtained, thereby improving the finger level anti-counterfeiting effect. The embodiment of the present application also provides a finger-level anti-counterfeiting processing device. As shown in Figure 14, the finger-level anti-counterfeiting processing device 140 includes a first acquisition module 141, a second acquisition module 142 and a determination module 143, wherein the first acquisition module 141 is configured to obtain a finger-level identification request, wherein the finger-level identification request includes a finger to be identified; the second acquisition module 142 is configured to obtain a preset first anti-counterfeiting index value corresponding to the finger to be identified or a binary classification model established based on the first anti-counterfeiting index value; the determination module 143 is configured to determine whether the finger to be identified is a counterfeit finger based on the first anti-counterfeiting index value or the binary classification model; wherein the first anti-counterfeiting index value is a preset value based on the characteristic parameter value corresponding to the finger to be identified as the target finger at different time sequences.In one embodiment, the system further includes a first setting module configured to pre-set a first security indicator value. The module specifically includes: an acquisition unit configured to obtain, for each target finger level, the epidermal layer characteristic parameter value and the dermal layer characteristic parameter value corresponding to the target finger level at different time sequences; and a setting unit configured to set the first security indicator value corresponding to each target finger level based on the epidermal layer characteristic parameter value and the dermal layer characteristic parameter value. In one embodiment, the system further includes a model building module configured to build the binary classification model. The module specifically includes: a training unit configured to train a preset binary classification model based on the first security indicator value to obtain the binary classification model. The determination module 143 is specifically configured to use the binary classification model to analyze and process the finger level to be identified, obtain a binary classification result, and determine whether the finger level to be identified is a counterfeit finger level based on the binary classification result. In one embodiment, the acquisition unit includes: a first acquisition subunit, which is configured to acquire a first finger-level image of the target finger level at a first time sequence, determine the ridge position and valley position in the first finger-level image, and acquire the ridge parameter value and valley parameter value of the epidermis based on the ridge position and valley position in the first finger-level image; and a second acquisition subunit, which is configured to acquire a second finger-level image of the target finger level at a second time sequence having a preset time sequence difference from the first time sequence, determine the ridge position and valley position in the second finger-level image, and acquire the ridge parameter value and valley parameter value of the dermis based on the ridge position and valley position in the second finger-level image.In one embodiment, the setting unit includes: a contrast acquisition subunit, which is configured to acquire the finger level contrast of the epidermis layer for each target finger level based on the ridge parameter value and the valley parameter value of the epidermis layer, and acquire the finger level contrast of the dermis layer based on the ridge parameter value and the valley parameter value of the dermis layer; an index value determination subunit, which is configured to determine the anti-counterfeiting index value in a first time sequence based on the finger level 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 finger level contrast of the dermis layer, the ridge parameter value and the valley parameter value of the dermis layer; a first setting subunit, which is configured to set the first anti-counterfeiting index value corresponding to the target finger level based on the anti-counterfeiting index value in the first time sequence and the anti-counterfeiting index value in the second time sequence. In one embodiment, the setting unit includes: a parameter ratio acquisition subunit, which is configured to determine, for each target finger level, a ridge parameter ratio between a first time series and a second time series based on the ridge parameter value of the epidermal layer and the ridge parameter value of the dermal layer; and, based on the valley parameter value of the epidermal layer and the valley parameter value of the dermal layer, determine a valley parameter ratio between the first time series and the second time series; a contrast ratio acquisition subunit, which is configured to acquire a finger-level contrast of the epidermal layer based on the ridge parameter value and the valley parameter value of the epidermal layer, and acquire a finger-level contrast of the dermal layer based on the ridge parameter value and the valley parameter value of the dermal layer; and, based on the finger-level contrast of the epidermal layer and the finger-level contrast of the dermal layer, determine a contrast ratio between the first time series and the second time series; a second setting subunit, which is configured to determine anti-counterfeiting index values ​​between different time series based on the ridge parameter ratio, the valley parameter ratio and the contrast ratio between the first time series and the second time series, and set the first anti-counterfeiting index value corresponding to the target finger level based on the anti-counterfeiting index values ​​between different time series.In one embodiment, the acquisition unit includes: a first gradient acquisition subunit, which is configured to acquire a third finger-level image of the target finger at a third time sequence, acquire the gradient of each pixel point in the third finger-level image in a preset number of directions, and respectively use the direction with the minimum gradient as the first gradient direction of each pixel point; a first gradation acquisition subunit, which is configured to determine the first gradation direction of the pixel block where each pixel point is located based on the first gradient direction of each pixel point, and acquire the gradation direction characteristic value of the epidermis layer based on the first gradation direction of each pixel block; and, a second gradient acquisition subunit, which is configured to acquire a fourth finger-level image of the target finger at a fourth time sequence with a preset time sequence difference from the third time sequence, acquire the gradient of each pixel point in the fourth finger-level image in a preset number of directions, and respectively use the direction with the minimum gradient as the second gradient direction of each pixel point; the first gradation acquisition subunit, which is configured to determine the second gradation direction of the pixel block where each pixel point is located based on the second gradient direction of each pixel point, and acquire the gradation direction characteristic value of the dermis layer based on the second gradation direction of each pixel block. In one embodiment, the setting unit includes: a third setting subunit configured to, for each target finger, obtain a physical change rate of the target finger based on the physical direction characteristic value of the epidermis layer and the physical direction characteristic value of the dermis layer, and set a first anti-counterfeiting indicator value corresponding to the target finger based on the physical change rate. In one embodiment, obtaining the physical change rate of the target finger based on the physical direction characteristic value of the epidermis layer and the physical direction characteristic value of the dermis layer specifically comprises: obtaining pixel blocks that produce physical direction changes based on the physical direction characteristic value of the epidermis layer and the physical direction characteristic value of the dermis layer, and marking the pixel blocks as superimposed blocks; and determining the physical change rate of the target finger based on a ratio between the number of superimposed blocks and the total number of pixel blocks.In one embodiment, the device further includes: a third acquisition module, which is configured to obtain a preset second anti-counterfeiting index value, where the second anti-counterfeiting index value is preset based on the fitting parameter value corresponding to the finger to be identified as the target finger; the determination module 143 is specifically configured to determine whether the finger to be identified is a counterfeit finger based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value; or, determine whether the finger to be identified is a counterfeit fingerprint based on a binary classification model established based on the first anti-counterfeiting mark value and the second anti-counterfeiting index value. In one embodiment, the device further includes a second setting module, which is configured to pre-set the second anti-counterfeiting index value, and specifically includes: a finger gradient acquisition unit, which is configured to collect a fifth finger image of the target finger and obtain finger gradient information of each pixel point in the fifth finger image; a screening unit, which is configured to screen out valid fingerprint 1 gradient information and its corresponding pixel points that meet preset conditions from the finger gradient information of each pixel point; an effective gradient acquisition unit, It is configured to obtain the effective gradient ratio of the target finger level based on the number of pixels corresponding to the effective finger level gradient information; and / or to obtain the average effective gradient value based on the effective finger level gradient information and the number of pixels corresponding to it; and a fitting parameter acquisition unit is configured to obtain the fitting parameter value of the target finger level based on the effective gradient ratio and / or the average effective gradient value. The above-mentioned device provided in the embodiments of the present application can be used to implement the technical solutions of the finger level anti-counterfeiting processing methods in the above-mentioned embodiments. Its implementation principles and technical effects are similar and will not be further described here. It should be understood that the division of the various modules of the above-mentioned device is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into a single physical entity or physically separated. Moreover, these modules can be implemented entirely in software called by processing components; or entirely in hardware; or some modules can be implemented in software called by processing components, and some modules can be implemented in hardware.For example, the first acquisition module 141 can be a separate processing element, or it can be integrated into a chip of the aforementioned device. Furthermore, it can be stored in the form of program code in the memory of the aforementioned device, and invoked and executed by a processing element of the aforementioned device. The implementation of the other modules is similar. Furthermore, all or part of these modules can be integrated together, or implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. During implementation, each step of the aforementioned method or each of the aforementioned modules can be completed by hardware integrated logic circuits in the processor element or by software instructions. Correspondingly, embodiments of the present application also provide a computer storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When executed by a processor, the computer-executable instructions are used to implement the aforementioned finger-level anti-counterfeiting processing method. The aforementioned medium provided in embodiments of the present application can be used to implement the technical solution of the finger-level anti-counterfeiting processing method in the aforementioned embodiments. Its implementation principles and technical effects are similar and will not be further elaborated here. The present application also provides a corresponding finger-level anti-counterfeiting system, as shown in FIG15 . The system includes a finger-level anti-counterfeiting processing device 140 and an ultrasonic sensor device 150 for performing the above-described method. The finger-level anti-counterfeiting processing device 140 is electrically connected to the ultrasonic sensor device 150 to implement ultrasonic finger-level anti-counterfeiting detection. The present application also provides an electronic device including the finger-level anti-counterfeiting processing system. As shown in FIG16 , the electronic device may include a transceiver 161, a processor 162, and a memory 163. The processor 162 executes computer-executable instructions stored in the memory, causing the processor 162 to invoke the finger-level anti-counterfeiting processing system to implement the solution in the above-described 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 gate or transistor logic devices, or discrete hardware components. The memory 163 is connected to the processor 162 via a system bus and communicates with the processor 162. The memory 163 is used to store computer program instructions.Transceiver 161 can be used to obtain pending tasks and their configuration information. The system bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, among others. System buses can be divided into address buses, data buses, and control buses. For ease of illustration, the figure uses only a single thick line, but this does not imply a single bus or bus type. The transceiver is used to facilitate communication between the database access device and other computers (e.g., clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) or non-volatile memory. The aforementioned device provided in the embodiments of the present application can be used to implement the technical solutions of the finger-level anti-counterfeiting processing method described in the aforementioned embodiments. The implementation principles and technical effects are similar and will not be further elaborated here. The embodiments of the present application also provide a chip for executing instructions, which is used to implement the technical solutions of the finger-level anti-counterfeiting processing method described in the aforementioned embodiments. The present application also provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on a computer, the computer executes the technical solution of the method for level-one anti-counterfeiting described in the above-mentioned embodiments. The present application also provides a computer program product comprising 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 the at least one processor executes the computer program, the computer program implements the technical solution of the method for level-one anti-counterfeiting described in the above-mentioned embodiments. In the several embodiments provided herein, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical functional division. In actual implementation, other division methods may be used. For example, multiple modules may be combined or integrated into another system, or some features may be omitted or not implemented.Furthermore, the coupling, direct coupling, or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices, or modules, and may be electrical, mechanical, or other forms. Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of these modules may be selected to implement the solutions of this embodiment based on actual needs. Furthermore, the functional modules in various embodiments of this application may be integrated into a single processing unit, each module may exist physically as a separate unit, or two or more modules may be integrated into a single unit. These modular units may be implemented in hardware or in the form of hardware plus software functional units. These integrated modules implemented as software functional modules may be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include instructions for causing a computer device (such as a personal computer, server, or network device) or processor to execute some of the steps of the methods of various embodiments of this application. It should be understood that the processor described above may be a central processing unit (CPU), 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 present invention may be directly executed by a hardware processor, or by a combination of hardware and software modules in the processor.The memory may include high-speed RAM memory and may also include non-volatile memory (NVM), such as at least one disk memory, and may also be a USB flash drive, a mobile hard drive, a read-only memory, a disk, or a .k;o bus. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of this application are not limited to only one bus or one type of bus. The aforementioned 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 storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and storage medium can be located in an application-specific integrated circuit (ASIC). Of course, the processor and storage medium can also exist as discrete components in an electronic control unit or a main control device. Those skilled in the art will appreciate that all or part of the steps of implementing the aforementioned method embodiments can be performed by hardware associated with 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 performed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.It should be understood that the various numbers used in the embodiments of this application are merely for ease of description and are not intended to limit the scope of the embodiments of this application. In the embodiments of this application, the order of the sequence numbers of the aforementioned processes does not imply a precedence in execution. The execution order of each process is determined by its function and inherent logic and does not constitute any limitation on the implementation of the embodiments of this application. Finally, it should be noted that the aforementioned embodiments are intended only to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the aforementioned embodiments, those skilled in the art will understand that the technical solutions described in the aforementioned embodiments may be modified or some or all of the technical features may be replaced with equivalents. Such modifications or replacements do not deviate from the essence of the corresponding technical solutions within the scope of the embodiments of this application.

Claims

Claims 1. A finger-level anti-counterfeiting processing method, characterized in that: include: A finger identification request is obtained, wherein the finger identification request includes a finger to be identified; a first pre-set anti-counterfeiting index value corresponding to the finger to be identified or a binary classification model established based on the first anti-counterfeiting index value is obtained, and based on the first anti-counterfeiting index value or the binary classification model, whether the finger to be identified is a counterfeit finger is determined; wherein the first anti-counterfeiting index value is a pre-set value based on the characteristic parameter value corresponding to the finger to be identified as a target finger at different time sequences.

2. The method according to claim 1, characterized in that Presetting a first anti-counterfeiting index value includes: for each target finger level, obtaining an epidermis layer characteristic parameter value and a dermis layer characteristic parameter value respectively corresponding to the target finger level at different time sequences; and setting a first anti-counterfeiting index value corresponding to each target finger level based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value.

3. The method according to any one of claim 2, 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 finger to be identified is a counterfeit finger based on the first anti-counterfeiting index value or the binary classification model includes: using the binary classification model to analyze and process the finger to be identified, obtaining a binary classification result, and determining whether the finger to be identified is a counterfeit finger based on the binary classification result.

4. The method according to claim 2 or 3, characterized in that The method of obtaining the epidermal layer characteristic parameter values ​​and the dermal layer characteristic parameter values ​​corresponding to the target finger level at different time sequences includes: acquiring a first finger-level image of the target finger level at a first time sequence, determining the ridge position and the valley position in the first finger-level image, and acquiring the ridge parameter value and the valley parameter value of the epidermal layer according to the ridge position and the valley position in the first finger-level image; and, acquiring a second finger-level image of the target finger level at a second time sequence having a preset time sequence difference with the first time sequence, determining the ridge position and the valley position in the second finger-level image, and acquiring 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 finger-level image.

5. The method according to claim 4, characterized in that The first protection level corresponding to each target finger level is set based on the epidermis layer characteristic parameter value and the dermis layer characteristic parameter value. The pseudo index value includes: for each target finger level, based on the ridge parameter value and the valley parameter value of the epidermis layer, obtaining the finger level contrast of the epidermis layer, and based on the ridge parameter value and the valley parameter value of the dermis layer, obtaining the finger level contrast of the dermis layer; based on the finger level contrast of the epidermis layer, the ridge parameter value and the valley parameter value of the epidermis layer, determining the anti-counterfeiting index value in the first time sequence, and based on the finger level contrast of the dermis layer, the ridge parameter value and the valley parameter value of the dermis layer, determining the anti-counterfeiting index value in the second time sequence; based on the anti-counterfeiting index value in the first time sequence and the anti-counterfeiting index value in the second time sequence, setting the first anti-counterfeiting index value corresponding to the target finger level.

6. The method according to claim 4, characterized in that The method of setting the first anti-counterfeiting index value corresponding to each target finger level based on the characteristic parameter value of the epidermis layer and the characteristic parameter value of the dermis layer, respectively, includes: for each target finger level, determining the ridge parameter ratio between the first time series and the second time series based on the ridge parameter value of the epidermis layer and the ridge parameter value of the dermis layer; and, determining the 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; obtaining the finger level contrast of the epidermis layer based on the ridge parameter value and the valley parameter value of the epidermis layer, and obtaining the finger level contrast of the dermis layer based on the ridge parameter value and the valley parameter value of the dermis layer; and, determining the contrast ratio between the first time series and the second time series based on the fingerprint contrast of the epidermis layer and the fingerprint contrast of the dermis layer; determining the anti-counterfeiting index value between different time series based on the ridge parameter ratio, the valley parameter ratio and the contrast ratio between the first time series and the second time series, and setting the first anti-counterfeiting index value corresponding to the target finger level based on the anti-counterfeiting index value between different time series.

7. The method according to claim 2 or 3, characterized in that The method of obtaining the epidermis layer characteristic parameter values ​​and the dermis layer characteristic parameter values ​​corresponding to the target finger level at different time sequences includes: collecting a third finger level image of the target finger level at a third time sequence, obtaining the gradient of each pixel point in the third finger level 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 level direction of the pixel block where each pixel point is located, and obtaining the level direction characteristic value of the epidermis layer based on the first level direction of each pixel block; and, A fourth finger-level image of the target finger at a fourth time sequence having a preset time sequence difference with the third time sequence is collected, and the gradient of each pixel point in the fourth finger-level image in a preset number of directions is obtained, and the direction with the smallest gradient is used as the second gradient direction of each pixel point; based on the second gradient direction of each pixel point, the second level direction of the pixel block where each pixel point is located is determined, and the level direction characteristic value of the dermis layer is obtained based on the second level direction of each pixel block.

8. The method according to claim 7, characterized in that The method of setting the first anti-counterfeiting index value corresponding to each target finger level based on the characteristic parameter value of the epidermis layer and the characteristic parameter value of the dermis layer, includes: for each target finger level, based on the level direction characteristic value of the epidermis layer and the level direction characteristic value of the dermis layer, obtaining the level change rate of the target finger level, and setting the first anti-counterfeiting index value corresponding to the target finger level based on the level change rate.

9. The method according to claim 8, characterized in that The method of obtaining the physical change rate of the target finger based on the physical direction characteristic value of the epidermis layer and the physical direction characteristic value of the dermis layer includes: obtaining pixel blocks that produce physical direction changes based on the physical direction characteristic value of the epidermis layer and the physical direction characteristic value of the dermis layer, and marking the pixel blocks as superposition blocks; determining the physical change rate of the target finger based on the ratio between the number of superposition blocks and the total number of pixel blocks.

10. The method according to claim 1, characterized in that: Also includes: Obtaining a preset second anti-counterfeiting index value, wherein the second anti-counterfeiting index value is preset based on the fitting parameter value corresponding to the finger to be identified as the target finger; then determining whether the finger to be identified is a counterfeit finger based on the first anti-counterfeiting index value or the binary classification model, including: determining whether the finger to be identified is a counterfeit finger 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 finger to be identified is a counterfeit finger.

11. The method according to claim 10, characterized in that Presetting the second anti-counterfeiting index value includes: collecting a fifth finger-level image of the target finger, obtaining finger-level gradient information of each pixel point in the fifth finger-level image; screening out valid finger-level gradients that meet preset conditions from the finger-level gradient information of each pixel point; Information and its corresponding pixel points; based on the number of pixel points corresponding to the effective finger level gradient information, obtain the effective gradient ratio of the target finger level; and / or, based on the effective finger level gradient information and its corresponding pixel points, obtain the average effective gradient value; based on the effective gradient ratio and / or the average effective gradient value, obtain the fitting parameter value of the target finger level.

12. A finger-level anti-counterfeiting processing device, characterized in that: include: A first acquisition module is configured to obtain a finger level identification request, wherein the finger level identification request includes a finger to be identified; a second acquisition module is configured to obtain a preset first anti-counterfeiting index value corresponding to the finger to be identified or a binary classification model established based on the first anti-counterfeiting index value; a determination module is configured to determine whether the finger to be identified is a counterfeit finger based on the first anti-counterfeiting index value or the binary classification model; wherein the first anti-counterfeiting index value is a preset value based on the characteristic parameter value corresponding to the finger to be identified as a target finger at different time sequences.

13. 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 finger-level anti-counterfeiting processing method according to any one of claims 1 to 11.

14. A finger-level anti-counterfeiting system, characterized in that: It comprises an ultrasonic sensor device and a finger-level anti-counterfeiting processing device for executing the finger-level anti-counterfeiting processing method according to any one of claims 1 to 11, wherein the finger-level anti-counterfeiting processing device is electrically connected to the ultrasonic sensor device to realize ultrasonic finger-level anti-counterfeiting detection.

15. An electronic device, characterized in that it comprises the finger-level anti-counterfeiting processing system as claimed in claim 14.

Images