Fingerprint anti-counterfeiting method, device and equipment

Abstract

The embodiment of the invention provides a fingerprint anti-counterfeiting method, device and equipment, and the method comprises the steps: collecting at least two frames of fingerprint images through a fingerprint sensor, and carrying out the matching recognition of the at least two frames of fingerprint images through the fingerprint anti-counterfeiting equipment, if the matching identification result is that the fingerprints in the at least two frames of fingerprint images are matched with the pre-stored fingerprints, performing anti-counterfeiting identification on the at least two frames of fingerprint images, and if the anti-counterfeiting identification result is that the fingerprints in the at least two frames of fingerprint images are fingerprints of real fingers, performing anti-counterfeiting identification on the at least two frames of fingerprint images. And if yes, determining that the fingerprints in the at least two frames of fingerprint images pass identity authentication, thereby realizing identification of the fingerprints of the real finger and the fingerprints of the fake finger, and improving the anti-counterfeiting effect of the fingerprints.

Description

[0001] This application is a divisional application of the original application with the application number 202011480329.4 and the original filing date of December 15, 2020, and the entire contents of the original application are incorporated herein by reference. TECHNICAL FIELD

[0002] Embodiments of the present application relate to the technical field of intelligent terminals, in particular to a fingerprint anti-counterfeiting method, device and equipment. BACKGROUND

[0003] Fingerprint recognition is an important identity recognition method, which has the characteristics of being simple and easy to use compared with deoxyribo nucleic acid (DNA) recognition and iris recognition, and has been widely applied in our life.

[0004] The fingerprint recognition scheme generally has the problem of weak anti-counterfeiting capability, and there are many attack scenarios in the existing related technology, which has a large security risk.

[0005] Among them, the fake fingerprint attack is to collect the user's fingerprint through various means and then make various fake fingerprints. Then the fake fingerprint attacks the user's fingerprint recognition device.

[0006] In the existing related technology, fingerprint recognition mainly classifies true and false fingerprints by judging the image difference between true and false fingerprints, so as to judge whether the fingerprint is true or false. However, by comparing the difference between the images, only part of the fake fingerprints with large differences can be intercepted. If the difference between the true and false fingerprint images is small, the anti-counterfeiting effect of the fingerprint is poor. SUMMARY

[0007] Embodiments of the present application provide a fingerprint anti-counterfeiting method, device and equipment, and the embodiments of the present application also provide a computer readable storage medium to realize the identification of the fingerprint of a real human finger and the fingerprint of a fake finger, and improve the anti-counterfeiting effect of the fingerprint.

[0008] In a first aspect, the embodiments of the present application provide a fingerprint anti-counterfeiting method, comprising: collecting at least two frames of fingerprint images through a fingerprint sensor; performing matching identification on the at least two frames of fingerprint images; if the result of the matching identification is that the fingerprint in the at least two frames of fingerprint images matches the pre-stored fingerprint, performing anti-counterfeiting identification on the at least two frames of fingerprint images; and if the result of the anti-counterfeiting identification is that the fingerprint in the at least two frames of fingerprint images is the fingerprint of a real human finger, determining that the fingerprint in the at least two frames of fingerprint images passes the identity authentication.

[0009] In the above-mentioned fingerprint anti-counterfeiting method, after the fingerprint anti-counterfeiting device acquires at least two frames of fingerprint images through a fingerprint sensor, it performs matching and recognition on the at least two frames of fingerprint images. If the matching and recognition result is that the fingerprints in the at least two frames of fingerprint images match the pre-stored fingerprints, then the at least two frames of fingerprint images are used for anti-counterfeiting recognition. If the anti-counterfeiting recognition result is that the fingerprints in the at least two frames of fingerprint images are the fingerprints of a real person's finger, then the fingerprints in the at least two frames of fingerprint images are determined to have passed identity authentication. In this way, it is possible to recognize the fingerprints of real people's fingers and fake fingers, thereby improving the anti-counterfeiting effect of fingerprints.

[0010] In one possible implementation, after performing anti-counterfeiting identification on the at least two fingerprint images, the method further includes: if the result of the anti-counterfeiting identification is that the fingerprint in the at least two fingerprint images is the fingerprint of a fake finger, then it is determined that the fingerprint in the at least two fingerprint images has not passed the identity authentication.

[0011] In one possible implementation, the anti-counterfeiting identification of the at least two fingerprint images includes: performing differential calculation on the at least two fingerprint images to obtain a fingerprint differential sequence in the time domain; identifying the fingerprint differential sequence to obtain the confidence level that the fingerprints in the at least two fingerprint images are fingerprints of a real human finger; and determining whether the fingerprints in the at least two fingerprint images are fingerprints of a real human finger based on the confidence level.

[0012] In one possible implementation, the step of identifying the fingerprint differential sequence to obtain the confidence level that the fingerprints in the at least two fingerprint images are from a real human finger includes: identifying the fingerprint differential sequence through a neural network to obtain the confidence level that the fingerprints in the at least two fingerprint images are from a real human finger.

[0013] In one possible implementation, the neural network includes a convolutional neural network and / or a fully connected network.

[0014] In one possible implementation, the anti-counterfeiting identification of the at least two fingerprint images includes: performing differential calculation on the at least two fingerprint images to obtain a fingerprint differential sequence in the time domain; fusing the fingerprint images with the fingerprint differential sequence; identifying the feature vector obtained after fusion to obtain the confidence level that the fingerprints in the at least two fingerprint images are fingerprints of a real human finger; and determining whether the fingerprints in the at least two fingerprint images are fingerprints of a real human finger based on the confidence level.

[0015] In one possible implementation, determining whether the fingerprints in the at least two fingerprint images are fingerprints of a real person's fingers based on the confidence level includes: determining that the fingerprints in the at least two fingerprint images are fingerprints of a real person's fingers when the confidence level is greater than or equal to a predetermined threshold; and determining that the fingerprints in the at least two fingerprint images are not fingerprints of a real person's fingers when the confidence level is less than the predetermined threshold.

[0016] Secondly, embodiments of this application provide a fingerprint anti-counterfeiting device, which is included in a fingerprint anti-counterfeiting equipment. This device has the function of implementing the behaviors of the fingerprint anti-counterfeiting equipment in the first aspect and its possible implementations. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the above functions. For example, an acquisition module or unit, a processing module or unit, etc.

[0017] Thirdly, embodiments of this application provide a fingerprint anti-counterfeiting device, comprising: one or more processors; a memory; multiple applications; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the fingerprint anti-counterfeiting device, cause the fingerprint anti-counterfeiting device to perform the following steps: acquiring at least two frames of fingerprint images through a fingerprint sensor; performing matching and recognition on the at least two frames of fingerprint images; if the result of the matching and recognition is that the fingerprints in the at least two frames of fingerprint images match pre-stored fingerprints, then performing anti-counterfeiting recognition on the at least two frames of fingerprint images; if the result of the anti-counterfeiting recognition is that the fingerprints in the at least two frames of fingerprint images are fingerprints of a real human finger, then determining that the fingerprints in the at least two frames of fingerprint images have passed identity authentication.

[0018] In one possible implementation, when the instruction is executed by the fingerprint anti-counterfeiting device, after the fingerprint anti-counterfeiting device performs the step of anti-counterfeiting identification of the at least two fingerprint images, it further performs the following steps: if the result of the anti-counterfeiting identification is that the fingerprint in the at least two fingerprint images is the fingerprint of a fake finger, then it is determined that the fingerprint in the at least two fingerprint images has not passed the identity authentication.

[0019] In one possible implementation, when the instruction is executed by the fingerprint anti-counterfeiting device, causing the fingerprint anti-counterfeiting device to perform the step of anti-counterfeiting identification of the at least two fingerprint images includes: performing differential calculation on the at least two fingerprint images to obtain a time-domain fingerprint differential sequence; identifying the fingerprint differential sequence to obtain the confidence level that the fingerprints in the at least two fingerprint images are fingerprints of a real human finger; and determining whether the fingerprints in the at least two fingerprint images are fingerprints of a real human finger based on the confidence level.

[0020] In one possible implementation, when the instruction is executed by the fingerprint anti-counterfeiting device, causing the fingerprint anti-counterfeiting device to perform the step of identifying the fingerprint differential sequence and obtaining the confidence level that the fingerprint in the at least two frames of fingerprint images is a real human finger includes: identifying the fingerprint differential sequence through a neural network to obtain the confidence level that the fingerprint in the at least two frames of fingerprint images is a real human finger.

[0021] In one possible implementation, when the instruction is executed by the fingerprint anti-counterfeiting device, the step of performing anti-counterfeiting identification on the at least two fingerprint images includes: performing differential calculation on the at least two fingerprint images to obtain a time-domain fingerprint differential sequence; fusing the fingerprint images with the fingerprint differential sequence; identifying the feature vector obtained after fusion to obtain the confidence level that the fingerprints in the at least two fingerprint images are fingerprints of a real human finger; and determining whether the fingerprints in the at least two fingerprint images are fingerprints of a real human finger based on the confidence level.

[0022] In one possible implementation, when the instruction is executed by the fingerprint anti-counterfeiting device, the step of determining whether the fingerprint in the at least two fingerprint images is a real human finger based on the confidence level includes: determining that the fingerprint in the at least two fingerprint images is a real human finger when the confidence level is greater than or equal to a predetermined threshold; and determining that the fingerprint in the at least two fingerprint images is not a real human finger when the confidence level is less than the predetermined threshold.

[0023] It should be understood that the second and third aspects of the embodiments of this application are consistent with the technical solutions of the first aspect of the embodiments of this application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation are similar, and will not be described again.

[0024] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the method provided in the first aspect.

[0025] Fifthly, embodiments of this application provide a computer program that, when executed by a computer, performs the method provided in the first aspect.

[0026] In one possible design, the program in the fifth aspect can be stored wholly or partially on a storage medium packaged with the processor, or it can be stored wholly or partially on a memory not packaged with the processor. Attached Figure Description

[0027] Figure 1A schematic diagram of the fingerprint images of a real and a fake finger provided in one embodiment of this application;

[0028] Figure 2 This is a schematic diagram of the structure of a fingerprint anti-counterfeiting device provided in one embodiment of this application;

[0029] Figure 3 A flowchart illustrating a fingerprint anti-counterfeiting method provided in one embodiment of this application;

[0030] Figure 4 A flowchart of a fingerprint anti-counterfeiting method provided in another embodiment of this specification;

[0031] Figure 5 A flowchart of a fingerprint anti-counterfeiting method provided in another embodiment of this specification;

[0032] Figure 6 This is a schematic diagram of the structure of a fingerprint anti-counterfeiting device provided in another embodiment of this application. Detailed Implementation

[0033] The terminology used in the implementation section of this application is for the purpose of explaining specific embodiments of this application only, and is not intended to limit this application.

[0034] In view of the problem that the fingerprint anti-counterfeiting effect is poor in the existing related technologies, the present application provides a fingerprint anti-counterfeiting method that can identify the fingerprints of real fingers and fake fingers, thereby improving the anti-counterfeiting effect of fingerprints.

[0035] Since the state of a fake finger changes little, while the state of a real finger changes greatly due to factors such as pore contraction, sweating, and / or blood flow, the changes in signal magnitude and differential signal distribution in the time series of fingerprint images can be used to distinguish between real and fake fingers.

[0036] Figure 1 This is a schematic diagram of the signal of a fingerprint image of a real and a fake finger provided in one embodiment of this application. Figure 1 The signals shown are from a time series of fingerprint images of real and fake fingers. From... Figure 1 It can be seen that the signal size of the fake finger changes less, while the signal size of the real finger changes more.

[0037] In addition, from the differential signal distribution map of the time series of fingerprint images of real and fake fingers, it can be seen that the differential signal changes of fake fingers are concentrated (mainly due to local finger force changes), while the differential signal changes of real fingers are dispersed (mainly due to pore contraction, sweating and / or blood flow).

[0038] The fingerprint anti-counterfeiting method provided in this application embodiment can be implemented by a fingerprint anti-counterfeiting device, which can be applied to electronic devices. The electronic devices can be fingerprint attendance machines, smartphones, tablets, wearable devices, in-vehicle devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., that require fingerprint authentication. This application embodiment does not impose any restrictions on the specific type of electronic device.

[0039] For example, Figure 2 This is a schematic diagram of the structure of a fingerprint anti-counterfeiting device provided in one embodiment of this application, as shown below. Figure 2 As shown, the fingerprint anti-counterfeiting device 200 may include a processor 201, a display screen 202, a fingerprint sensor 203, and a touch sensor 204.

[0040] In addition, the fingerprint anti-counterfeiting device 200 may also include an internal memory 205.

[0041] It is understood that the structure illustrated in the embodiments of this application does not constitute a specific limitation on the fingerprint anti-counterfeiting device 200. In other embodiments of this application, the fingerprint anti-counterfeiting device 200 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. Figure 2 The components shown can be implemented in hardware, software, or a combination of both.

[0042] Processor 201 may include one or more processing units, such as an application processor (AP), graphics processing unit (GPU), image signal processor (ISP), controller, digital signal processor (DSP), baseband processor, and / or neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0043] The controller can generate operation control signals based on the instruction opcode and timing signals to complete the control of instruction fetching and execution.

[0044] The processor 201 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 201 is a cache memory. This memory can store instructions or data that the processor 201 has just used or that are used repeatedly. If the processor 201 needs to use the instruction or data again, it can directly retrieve it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 201, and thus improves the efficiency of the system.

[0045] The display screen 202 is used to display images, videos, etc. The display screen 202 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a miniature LED, a microLED, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the fingerprint anti-counterfeiting device 200 may include one or N display screens 202, where N is a positive integer greater than 1.

[0046] Digital signal processors (DSPs) are used to process digital signals. Besides digital image signals, they can also process other digital signals. For example, when the fingerprint anti-counterfeiting device 200 selects a frequency point, the DSP performs Fourier transforms on the frequency energy.

[0047] NPU stands for Neural Network (NN) Computing Processor. By borrowing the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it can rapidly process input information and continuously learn on its own. NPUs can be used to enable intelligent cognitive applications in fingerprint anti-counterfeiting devices, such as image recognition, facial recognition, speech recognition, and text understanding.

[0048] Internal memory 205 can be used to store computer executable program code, including instructions. Internal memory 205 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as fingerprint recognition), etc. The data storage area may store data created during the use of the fingerprint anti-counterfeiting device 200 (such as fingerprint data), etc. Furthermore, internal memory 205 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc. Processor 201 executes various functional applications and data processing of the fingerprint anti-counterfeiting device 200 by running instructions stored in internal memory 205 and / or instructions stored in memory located in the processor.

[0049] The fingerprint sensor 203 is used to collect fingerprints. The fingerprint anti-counterfeiting device 200 can utilize the characteristics of the collected fingerprints to achieve fingerprint unlocking, access to application locks, fingerprint photography, fingerprint answering of calls, etc.

[0050] Touch sensor 204, also known as a "touch device," can be disposed on display screen 202. The touch sensor 204 and display screen 202 together form a touchscreen, also known as a "touchscreen." Touch sensor 204 is used to detect touch operations applied to or near it. Touch sensor 204 can transmit the detected touch operation to the application processor to determine the type of touch event. Visual output related to the touch operation can be provided through display screen 202. In other embodiments, touch sensor 204 may also be disposed on the surface of fingerprint anti-counterfeiting device 200, in a different location than display screen 202.

[0051] For ease of understanding, the following embodiments of this application will be described using the following methods: Figure 2 Taking the fingerprint anti-counterfeiting device 200 with the structure shown as an example, the fingerprint anti-counterfeiting method provided in this application embodiment will be specifically described in conjunction with the accompanying drawings and application scenarios.

[0052] Figure 3 A flowchart of a fingerprint anti-counterfeiting method provided in one embodiment of this application is shown below. Figure 3 As shown, the above fingerprint anti-counterfeiting method may include:

[0053] Step 301: The fingerprint anti-counterfeiting device 200 acquires at least two frames of fingerprint images through the fingerprint sensor 203.

[0054] In practical implementation, parameters such as the fingerprint hardware gain of the fingerprint sensor 203 can be fixed to ensure the consistency of the signal output by the fingerprint sensor 203 each time. Then, the fingerprint sensor 203 can continuously acquire at least two frames of fingerprint images, and the fingerprint anti-counterfeiting device 200 acquires the aforementioned at least two frames of fingerprint images.

[0055] Step 302: Match and identify the fingerprint images of at least two frames. Then, proceed to step 303 or step 306.

[0056] Step 303: If the matching and identification result is that the fingerprints in at least two fingerprint images match the pre-stored fingerprints, then perform anti-counterfeiting identification on the aforementioned at least two fingerprint images. Then proceed to step 304 or step 305.

[0057] Step 304: If the result of anti-counterfeiting identification is that the fingerprints in at least two frames of fingerprint images are the fingerprints of real people, then it is determined that the fingerprints in at least two frames of fingerprint images have passed the identity authentication.

[0058] Step 305: If the result of anti-counterfeiting identification is that the fingerprints in at least two fingerprint images are the fingerprints of fake fingers, then it is determined that the fingerprints in at least two fingerprint images have not passed the identity authentication.

[0059] Step 306: If the matching and recognition result is that the fingerprints in at least two fingerprint images do not match the pre-stored fingerprints, then it is determined that the fingerprints in at least two fingerprint images have failed the identity authentication.

[0060] Specifically, after the fingerprint anti-counterfeiting device 200 acquires at least two frames of fingerprint images, it first runs a fingerprint matching algorithm to match and identify the at least two frames of fingerprint images. If the fingerprints in the at least two frames of fingerprint images match the pre-stored fingerprints, then the at least two frames of fingerprint images are subjected to anti-counterfeiting identification. If the result of the anti-counterfeiting identification is the fingerprint of a real person's finger, then the matching is confirmed to be successful, and the fingerprints in the at least two frames of fingerprint images pass this identity authentication.

[0061] If the fingerprints in at least two fingerprint images do not match the pre-stored fingerprints, or if the fingerprints in at least two fingerprint images match the pre-stored fingerprints but the anti-counterfeiting identification result is a fake fingerprint, then the matching is determined to be a failure, and the fingerprints in at least two fingerprint images have not passed the identity authentication.

[0062] In the above fingerprint anti-counterfeiting method, after the fingerprint anti-counterfeiting device 200 collects at least two frames of fingerprint images through the fingerprint sensor 203, it performs matching and recognition on the at least two frames of fingerprint images. If the matching and recognition result is that the fingerprints in the at least two frames of fingerprint images match the pre-stored fingerprints, then the at least two frames of fingerprint images are used for anti-counterfeiting recognition. If the anti-counterfeiting recognition result is that the fingerprints in the at least two frames of fingerprint images are the fingerprints of real fingers, then the fingerprints in the at least two frames of fingerprint images are determined to have passed identity authentication. In this way, it is possible to recognize the fingerprints of real fingers and fake fingers, thereby improving the anti-counterfeiting effect of fingerprints.

[0063] Figure 4 A flowchart of a fingerprint anti-counterfeiting method provided in another embodiment of this specification is shown below. Figure 4 As shown in this manual Figure 3 In the illustrated embodiment, step 303 may include:

[0064] Step 401: If the matching recognition result is that the fingerprints in at least two fingerprint images match the pre-stored fingerprints, then perform differential calculation on the above at least two fingerprint images to obtain the time-domain fingerprint differential sequence.

[0065] Step 402: Identify the above fingerprint differential sequence to obtain the confidence level that the fingerprints in at least two frames of fingerprint images are those of real human fingers.

[0066] Specifically, the confidence level of identifying the fingerprint differential sequence in the above fingerprint images and obtaining the fingerprint of a real person in at least two fingerprint images can be obtained by: identifying the fingerprint differential sequence in the above fingerprint images through a neural network and obtaining the confidence level of identifying the fingerprint of a real person in at least two fingerprint images.

[0067] The aforementioned neural network may include convolutional neural networks and / or fully connected networks.

[0068] Step 403: Based on the confidence level mentioned above, determine whether the fingerprints in at least two fingerprint images are fingerprints of real human fingers.

[0069] Specifically, based on the aforementioned confidence level, determining whether a fingerprint in at least two fingerprint images is a fingerprint of a real person can be as follows: when the aforementioned confidence level is greater than or equal to a predetermined threshold, the fingerprint in at least two fingerprint images is determined to be a fingerprint of a real person; when the aforementioned confidence level is less than the predetermined threshold, the fingerprint in at least two fingerprint images is determined not to be a fingerprint of a real person.

[0070] The predetermined threshold can be set by the system based on performance and / or implementation requirements during the specific implementation. This embodiment does not limit the size of the predetermined threshold.

[0071] This embodiment utilizes the fact that there are differences between the fingerprints of a fake finger and a real finger when pressed. The signal of a fake finger changes less over time, and the differential signal changes are concentrated. In contrast, the signal of a real finger changes more over time due to factors such as sweating and / or blood flow, and the differential signal changes are dispersed. Therefore, this embodiment identifies the fingerprint differential sequence to obtain a confidence level, and then determines whether the fingerprint in the fingerprint image is a real finger based on the confidence level. This enables the identification of fingerprints from real and fake fingers, improving the anti-counterfeiting effect of fingerprints.

[0072] Figure 5 A flowchart of a fingerprint anti-counterfeiting method provided in another embodiment of this specification is shown below. Figure 5 As shown in this manual Figure 3 In the illustrated embodiment, step 303 may include:

[0073] Step 501: If the matching recognition result is that the fingerprints in at least two fingerprint images match the pre-stored fingerprints, then perform differential calculation on at least two fingerprint images to obtain a time-domain fingerprint differential sequence.

[0074] Step 502: Fuse the fingerprint image with the fingerprint differential sequence.

[0075] Step 503: Identify the feature vectors obtained after fusion to obtain the confidence that the fingerprints in at least two frames of fingerprint images are from real human fingers.

[0076] Specifically, the confidence level of fingerprints in at least two frames of fingerprint images that are from a real person can be obtained by identifying the feature vectors obtained after fusion through a neural network.

[0077] The aforementioned neural network may include convolutional neural networks and / or fully connected networks.

[0078] Step 504: Based on the confidence level mentioned above, determine whether the fingerprints in at least two fingerprint images are fingerprints of real human fingers.

[0079] Specifically, based on the aforementioned confidence level, determining whether a fingerprint in at least two fingerprint images is a fingerprint of a real person can be as follows: when the aforementioned confidence level is greater than or equal to a predetermined threshold, the fingerprint in at least two fingerprint images is determined to be a fingerprint of a real person; when the aforementioned confidence level is less than the predetermined threshold, the fingerprint in at least two fingerprint images is determined not to be a fingerprint of a real person.

[0080] The predetermined threshold can be set by the system based on performance and / or implementation requirements during the specific implementation. This embodiment does not limit the size of the predetermined threshold.

[0081] This embodiment utilizes the fact that there are differences between the fingerprints of a fake finger and a real finger when pressed. The signal of a fake finger changes less over time, and the differential signal changes are concentrated. In contrast, the signal of a real finger changes more over time due to factors such as sweating and / or blood flow, and the differential signal changes are dispersed. Therefore, this embodiment performs differential calculations on at least two frames of fingerprint images to obtain a fingerprint differential sequence in the time domain. Then, the fingerprint images and the fingerprint differential sequence are fused. The feature vector obtained after fusion is then identified to obtain a confidence score. Based on the confidence score, it is determined whether the fingerprint in the fingerprint image is a real finger fingerprint. This enables the identification of fingerprints from real and fake fingers, improving the anti-counterfeiting effect of fingerprints.

[0082] It is understood that some or all of the steps or operations in the above embodiments are merely examples, and other operations or variations thereof can be performed in the embodiments of this application. Furthermore, the steps may be performed in different orders as presented in the above embodiments, and it is not necessary to perform all the operations in the above embodiments.

[0083] It is understood that fingerprint anti-counterfeiting devices, in order to achieve the above-mentioned functions, include hardware and / or software modules that perform the respective functions. Based on the algorithm steps of the various examples described in the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application in conjunction with the embodiments, but such implementation should not be considered beyond the scope of this application.

[0084] This embodiment can divide the fingerprint anti-counterfeiting device into functional modules according to the above method embodiment. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0085] Figure 6 This is a schematic diagram of the structure of a fingerprint anti-counterfeiting device provided in another embodiment of this application. In the case where functional modules are divided according to their respective functions, Figure 6 A schematic diagram of a possible composition of the fingerprint anti-counterfeiting device 60 involved in the above embodiments is shown, such as...Figure 6 As shown, the fingerprint anti-counterfeiting device 60 may include: an acquisition unit 61 and a processing unit 62;

[0086] The acquisition unit 61 can be used to support the fingerprint anti-counterfeiting device 60 in executing step 301, etc., and / or in other processes of the technical solution described in the embodiments of this application;

[0087] The processing unit 62 can be used to support the fingerprint anti-counterfeiting device 60 in executing steps 302 to 306, as well as steps 401 to 403, steps 501 to 504, and / or other processes used in the technical solutions described in the embodiments of this application.

[0088] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0089] The fingerprint anti-counterfeiting device 60 provided in this embodiment is used to perform the above-described fingerprint anti-counterfeiting method, and therefore can achieve the same effect as the above method.

[0090] It should be understood that the fingerprint anti-counterfeiting device 60 can correspond to Figure 1 The fingerprint anti-counterfeiting device 200 shown. The function of the acquisition unit 61 can be determined by... Figure 2 The fingerprint sensor 203 and touch sensor 204 in the fingerprint anti-counterfeiting device 200 shown are used to implement the functions; the processing unit 62 can be implemented by... Figure 2 The processor 201 in the fingerprint anti-counterfeiting device 200 shown is implemented.

[0091] When using integrated units, the fingerprint anti-counterfeiting device 60 may include a processing module and a storage module.

[0092] The processing module can be used to control and manage the actions of the fingerprint anti-counterfeiting device 60. For example, it can be used to support the fingerprint anti-counterfeiting device 60 in executing the steps performed by the acquisition unit 61 and the processing unit 62. The storage module can be used to support the fingerprint anti-counterfeiting device 60 in storing program code and data, etc.

[0093] The processing module can be a processor or controller, which can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory. The communication module can specifically be a device that interacts with other electronic devices, such as radio frequency circuitry, a Bluetooth chip, and / or a Wi-Fi chip.

[0094] In one embodiment, when the processing module is a processor and the storage module is a memory, the fingerprint anti-counterfeiting device 60 involved in this embodiment can be a device with... Figure 2 The device with the structure shown.

[0095] This application also provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to execute this application. Figures 3-5 The method provided in the illustrated embodiment.

[0096] This application also provides a computer program product, which includes a computer program that, when run on a computer, causes the computer to execute this application. Figures 3-5 The method provided in the illustrated embodiment.

[0097] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, A and B simultaneously, or B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0098] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0099] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0100] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] The above description is merely a specific embodiment of this application. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application. The protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method of fingerprint forgery prevention, characterized by, comprising: acquiring at least two frames of fingerprint images through a fingerprint sensor; performing matching recognition on the at least two frames of fingerprint images; if a result of the matching recognition is that a fingerprint in the at least two frames of fingerprint images matches a pre-stored fingerprint, performing difference calculation on the at least two frames of fingerprint images to obtain a time-domain fingerprint difference sequence; performing anti-fake recognition on the at least two frames of fingerprint images according to the time-domain fingerprint difference sequence; if a result of the anti-fake recognition is that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger, determining that the fingerprint in the at least two frames of fingerprint images passes an identity authentication.

2. The method of claim 1, wherein, after the anti-fake recognition on the at least two frames of fingerprint images, further comprising: if a result of the anti-fake recognition is that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a fake finger, determining that the fingerprint in the at least two frames of fingerprint images fails the identity authentication.

3. The method of claim 1, wherein, the anti-fake recognition on the at least two frames of fingerprint images according to the time-domain fingerprint difference sequence comprises: performing recognition on the fingerprint difference sequence to obtain a confidence degree that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger; determining whether the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger according to the confidence degree.

4. The method of claim 3, wherein, the recognition on the fingerprint difference sequence to obtain the confidence degree that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger comprises: performing recognition on the fingerprint difference sequence through a neural network to obtain the confidence degree that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger.

5. The method of claim 4, wherein, the neural network comprises a convolutional neural network and / or a fully connected network.

6. The method of claim 1, wherein, the anti-fake recognition on the at least two frames of fingerprint images according to the time-domain fingerprint difference sequence comprises: fusing the fingerprint image and the fingerprint difference sequence; performing recognition on a feature vector obtained after the fusion to obtain the confidence degree that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger; determining whether the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger according to the confidence degree.

7. The method according to claim 3 or 6, characterized in that, the determination whether the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger according to the confidence degree comprises: when the confidence degree is greater than or equal to a predetermined threshold, determining that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger; when the confidence degree is less than the predetermined threshold, determining that the fingerprint in the at least two frames of fingerprint images is not a fingerprint of a real human finger.

8. A fingerprint anti-counterfeiting device, characterized in that, comprising: one or more processors; a memory; a plurality of application programs; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs comprise instructions which, when executed by the fingerprint anti-fake device, cause the fingerprint anti-fake device to perform the following steps: acquiring at least two frames of fingerprint images through a fingerprint sensor; performing matching recognition on the at least two frames of fingerprint images; if a result of the matching recognition is that a fingerprint in the at least two frames of fingerprint images matches a pre-stored fingerprint, performing difference calculation on the at least two frames of fingerprint images to obtain a time-domain fingerprint difference sequence; According to the fingerprint difference sequence in the time domain, the at least two frames of fingerprint images are subjected to anti-counterfeiting identification; If the result of the anti-counterfeiting identification is that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger, it is determined that the fingerprint in the at least two frames of fingerprint images passes the identity authentication.

9. The fingerprint security device according to claim 8, characterized in that When the instructions are executed by the fingerprint anti-counterfeiting device, the fingerprint anti-counterfeiting device further executes the following steps after executing the step of anti-counterfeiting identification on the at least two frames of fingerprint images: If the result of the anti-counterfeiting identification is that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a fake finger, it is determined that the fingerprint in the at least two frames of fingerprint images fails the identity authentication.

10. The fingerprint security device according to claim 8, characterized in that When the instructions are executed by the fingerprint anti-counterfeiting device, the fingerprint anti-counterfeiting device executes the step of anti-counterfeiting identification on the at least two frames of fingerprint images according to the fingerprint difference sequence in the time domain, which includes: identifying the fingerprint difference sequence to obtain a confidence degree that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger; determining whether the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger according to the confidence degree.

11. The fingerprint security device according to claim 10, characterized in that When the instructions are executed by the fingerprint anti-counterfeiting device, the fingerprint anti-counterfeiting device executes the step of identifying the fingerprint difference sequence to obtain a confidence degree that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger, which includes: identifying the fingerprint difference sequence by a neural network to obtain a confidence degree that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger.

12. The fingerprint security device according to claim 8, wherein, When the instructions are executed by the fingerprint anti-counterfeiting device, the fingerprint anti-counterfeiting device executes the step of anti-counterfeiting identification on the at least two frames of fingerprint images according to the fingerprint difference sequence in the time domain, which includes: fusing the fingerprint images with the fingerprint difference sequence; identifying a feature vector obtained after the fusion to obtain a confidence degree that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger; determining whether the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger according to the confidence degree.

13. The fingerprint security device according to claim 8 or 12, characterized in that, When the instructions are executed by the fingerprint anti-counterfeiting device, the fingerprint anti-counterfeiting device executes the step of determining whether the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger according to the confidence degree, which includes: when the confidence degree is greater than or equal to a predetermined threshold, determining that the fingerprint in the at least two frames of fingerprint images is a fingerprint of a real human finger; when the confidence degree is less than the predetermined threshold, determining that the fingerprint in the at least two frames of fingerprint images is not a fingerprint of a real human finger.

14. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, which, when executed on a computer, causes the computer to execute the method of any one of claims 1-7.

Images