Fingerprint recognition method, fingerprint recognition device, electronic device and storage medium

Abstract

The embodiments of the present application provide a fingerprint recognition method, a fingerprint recognition device, an electronic device, and a storage medium. The fingerprint recognition method includes: when the fingerprint recognition area is touched by the fingerprint to be recognized, collecting a continuous first frame fingerprint image and a second frame fingerprint image; comparing the first frame fingerprint image and the second frame fingerprint image to determine the changes in the first frame fingerprint image and the second frame fingerprint image, and determining whether the fingerprint to be recognized is a real fingerprint based on the changes in the first frame fingerprint image and the second frame fingerprint image. This embodiment continuously collects two frames of fingerprint images during each fingerprint recognition, and determines whether the fingerprint to be recognized is a fake fingerprint based on the changes in the two fingerprint images, thereby eliminating the interference of fake fingerprints and improving the security of fingerprint recognition.

Description

Technical Field

[0001] The present application relates to the field of fingerprint recognition technology, and more specifically, to a fingerprint recognition method, a fingerprint recognition device, an electronic device, and a storage medium. Background Art

[0002] Under-screen fingerprint recognition technology is a technology that uses light emitted by the screen to illuminate the finger and then reflect back to the optical fingerprint sensor under the screen. The sensor converts the light signal into an electrical signal, and finally outputs it as a fingerprint image for feature point comparison with the preset fingerprint template.

[0003] As an optical sensor, a fingerprint sensor can accurately capture a 2D image of the object being captured, but it cannot inherently distinguish between genuine and fake fingerprints. Typical fingerprint anti-counterfeiting methods rely on algorithms to identify differences between real and fake fingerprints. For example, by comparing background grayscale, if the background grayscale of a captured single image doesn't match that of a preset template, the fingerprint is considered fake. This static single-image comparison method is easily defeated by increasingly realistic fingerprint counterfeiting methods. Summary of the Invention

[0004] In response to the shortcomings of existing methods, this application proposes a fingerprint recognition method, a fingerprint recognition device, an electronic device and a storage medium to solve the technical problem that fingerprint recognition devices in the prior art are susceptible to fingerprint counterfeiting methods.

[0005] In a first aspect, an embodiment of the present application provides a fingerprint recognition method, the fingerprint recognition method comprising:

[0006] When the fingerprint recognition area is touched by the fingerprint to be recognized, a first frame of fingerprint image and a second frame of fingerprint image are captured continuously;

[0007] Comparing the first fingerprint image frame and the second fingerprint image frame to determine a change between the first fingerprint image frame and the second fingerprint image frame;

[0008] Determine whether the fingerprint to be identified is a real fingerprint according to changes between the first frame fingerprint image and the second frame fingerprint image.

[0009] Optionally, the fingerprint recognition method further includes: comparing the second frame fingerprint image or the second frame fingerprint image with a fingerprint template to determine whether the fingerprint to be recognized matches the fingerprint template; if so, the fingerprint recognition passes; otherwise, the fingerprint recognition fails.

[0010] Optionally, it is characterized in that collecting a continuous first frame fingerprint image and a second frame fingerprint image includes: collecting the first frame fingerprint image with a first exposure time, collecting the second frame fingerprint image with a second exposure time, and the first exposure time is less than the second exposure time.

[0011] Optionally, comparing the first fingerprint image frame and the second fingerprint image frame to determine a change between the first fingerprint image frame and the second fingerprint image frame includes:

[0012] Selecting n first monitoring areas, where the first monitoring areas are located in the first area of ​​the first fingerprint image and the second fingerprint image, and each of the first monitoring areas in the first fingerprint image is located at the same position as one of the first monitoring areas in the second fingerprint image;

[0013] Comparing the difference between the valleys and ridges in the first monitoring area in the first fingerprint image frame and the valleys and ridges in the first monitoring area in the second fingerprint image frame to determine the change in ridge continuity;

[0014] m second monitoring areas are selected, where the second monitoring areas are located in the second areas of the first fingerprint image frame and the second fingerprint image frame, and each of the second monitoring areas in the first fingerprint image frame is located at the same position as one of the second monitoring areas in the second fingerprint image frame, wherein the second areas are located outside the first area, and m and n are both integers greater than or equal to 2;

[0015] The ridge line position difference in the second monitoring area in the first frame fingerprint image and the second monitoring area in the second frame fingerprint image is compared to determine the ridge line offset.

[0016] Optionally, comparing the difference between valleys and ridges in the first monitoring area in the first fingerprint image frame and the first monitoring area in the second fingerprint image frame to determine a change in ridge continuity includes:

[0017] Determine a ridge signal amount in the first monitoring area in the first frame of fingerprint image as a first signal amount, and calculate a valley-ridge difference value in the first monitoring area in the first frame of fingerprint image as a first valley-ridge difference value;

[0018] Determine a ridge signal amount in the first monitoring area in the second frame of fingerprint image as a second signal amount, and calculate a valley-ridge difference value in the first monitoring area in the second frame of fingerprint image as a second valley-ridge difference value;

[0019] The difference between the first signal quantity and the second signal quantity is compared and the first valley-ridge difference value and the second valley-ridge difference value are compared to determine the change in ridge continuity.

[0020] Optionally, determining whether the fingerprint to be identified is a real fingerprint according to changes between the first fingerprint image frame and the second fingerprint image frame includes:

[0021] If the ratio of the first signal amount to the second signal amount is equal to the ratio of the first exposure time to the second exposure time, and the average variance of the first valley-ridge difference is equal to the average variance of the second valley-ridge difference, then it is determined that the fingerprint to be identified is a false fingerprint;

[0022] If the ratio of the first signal amount to the second signal amount is less than the ratio of the first exposure time to the second exposure time, and the average variance of the second valley-ridge difference is less than the average variance of the first valley-ridge difference, it is determined that the fingerprint to be identified is a real fingerprint.

[0023] Optionally, comparing the ridge line position difference between the second monitoring area in the first fingerprint image frame and the second monitoring area in the second fingerprint image frame to determine the ridge line offset includes:

[0024] Determine a ridge line offset in each of the second monitoring areas in the first frame of fingerprint image as a first offset;

[0025] Determine a ridge line offset in each of the second monitoring areas in the second fingerprint image frame as a second offset;

[0026] An offset value between each first offset and the second offset corresponding to each first offset is determined, and whether the fingerprint to be identified is a real fingerprint is determined according to each offset value.

[0027] Optionally, determining an offset value between each first offset and the second offset corresponding to each first offset, and determining whether the fingerprint to be identified is a real fingerprint according to each offset value includes:

[0028] Determine an offset value Δx in the X direction and an offset value Δy in the Y direction of each first offset and a second offset corresponding to each first offset;

[0029] Each of the offset values ​​is analyzed. If the offset directions of the offset values ​​Δx are the same and the offset directions of the offset values ​​Δy are the same, then the fingerprint to be identified is determined to be a false fingerprint; if the offset directions of at least one of the offset values ​​Δx are different, and / or the offset directions of at least one of the offset values ​​Δy are different, then the fingerprint to be identified is determined to be a real fingerprint.

[0030] In a second aspect, an embodiment of the present application provides a fingerprint recognition device, comprising:

[0031] An image acquisition module is configured to acquire a first frame of fingerprint image and a second frame of fingerprint image when the fingerprint recognition area is touched by the fingerprint to be recognized;

[0032] The comparison module is configured to compare the first frame fingerprint image and the second frame fingerprint image to determine the changes between the first frame fingerprint image and the second frame fingerprint image, and determine whether the fingerprint to be identified is a real fingerprint based on the changes between the first frame fingerprint image and the second frame fingerprint image.

[0033] Optionally, the fingerprint recognition device further includes: an identification module, which compares the second frame fingerprint image or the second frame fingerprint image with a fingerprint template to determine whether the fingerprint to be identified matches the fingerprint template; if so, the fingerprint recognition passes; otherwise, the fingerprint recognition fails.

[0034] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-mentioned fingerprint recognition method.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned fingerprint recognition method when executed by an electronic device.

[0036] The beneficial technical effects brought about by the technical solutions provided in the embodiments of the present application include:

[0037] The fingerprint recognition method, fingerprint recognition device, electronic device, and storage medium provided in this embodiment continuously capture two frames of fingerprint images during each fingerprint recognition and determine whether the fingerprint to be recognized is a false fingerprint based on changes in the two fingerprint images. This can eliminate interference from false fingerprints and improve the security of fingerprint recognition.

[0038] Additional aspects and advantages of the present application will be given in part in the following description, which will become apparent from the following description, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0040] Figure 1 A schematic diagram of a fingerprint recognition method according to an embodiment of the present invention;

[0041] Figure 2 are the first fingerprint image and the second fingerprint image of the real fingerprint and the fake fingerprint, where Figure 2 (a) is the first frame of fingerprint image of the real fingerprint, Figure 2 (b) is the second frame fingerprint image of the real fingerprint. Figure 2(c) is the first frame fingerprint image of the fake fingerprint. Figure 2 (d) is the second fingerprint image of the fake fingerprint;

[0042] Figure 3 This is a schematic diagram of the principle of continuous change of fingerprints in the fingerprint recognition method provided in an embodiment of the present application, wherein: Figure 3 (a) is a schematic diagram of the acquisition of the first frame of fingerprint image of a real fingerprint. Figure 3 (b) is a schematic diagram of collecting the second frame of fingerprint image of a real fingerprint;

[0043] Figure 4 for Figure 1 Schematic diagram of the process of step S2 in the fingerprint recognition method shown;

[0044] Figure 5 This is a schematic diagram of the continuous change of true and false fingerprints in the fingerprint recognition method provided in the embodiment of the present application, wherein: Figure 5 (a1) is the first frame of the real fingerprint image, Figure 5 (a2) is Figure 5 (a1) Enlarged view of the part in the box; Figure 5 (b1) is the second frame fingerprint image of the real fingerprint, Figure 5 (b2) is Figure 5 (b1) Enlarged view of the part in the box; Figure 5 (c1) is the first frame fingerprint image of the fake fingerprint, Figure 5 (c2) is Figure 5 (c1) Enlarged view of the part in the box; Figure 5 (d1) is the second fingerprint image of the fake fingerprint, Figure 5 (d2) is Figure 5 (d1) Enlarged view of the part in the box;

[0045] Figure 6 This is a schematic diagram of the dynamic offset comparison of true and false fingerprints in the fingerprint recognition method provided in the embodiment of the present application, wherein: Figure 6 (a1) is the first frame of the real fingerprint image, Figure 6 (a2) is Figure 6 A partial enlarged view of position ① in (a1), Figure 6 (a3) Figure 6 A partial enlarged view of position ② in (a1); Figure 6 (b1) is the second frame fingerprint image of the real fingerprint, Figure 6 (b2) is Figure 6 A partial enlarged view of position ① in (a1), Figure 6 (b3) is Figure 6 Partially enlarged view of position ② in (b1); Figure 6 (c1) is the first frame fingerprint image of the fake fingerprint, Figure 6 (c2) is Figure 6 A partial enlarged view of position ① in (c1), Figure 6 (c3) is Figure 6 Partially enlarged view of position ② in (c1);

[0046] Figure 6 (d1) is the second frame fingerprint image of the fake fingerprint, Figure 6 (d2) is Figure 6 A partial enlarged view of position ① in (d1), Figure 6 (d3) is Figure 6 Partially enlarged view of position ② in (d1);

[0047] Figure 7 A schematic diagram of a first monitoring area and a second monitoring area selected in the fingerprint recognition method provided in an embodiment of the present application;

[0048] Figure 8 This is a flow chart of step S22 in the fingerprint recognition method provided in an embodiment of the present application;

[0049] Figure 9 A schematic diagram of ridge continuity recognition in the fingerprint recognition method provided in an embodiment of the present application;

[0050] Figure 10 A line graph showing the ridge continuity recognition results in the fingerprint recognition method provided in an embodiment of the present application;

[0051] Figure 11 This is a flow chart of step S24 in the fingerprint recognition method provided in an embodiment of the present application;

[0052] Figure 12 A schematic diagram illustrating identification of ridge offset in the fingerprint identification method provided in an embodiment of the present application;

[0053] Figure 13 A schematic diagram of another fingerprint recognition method provided in an embodiment of the present application;

[0054] Figure 14 A schematic diagram of the framework structure of a fingerprint recognition device provided in an embodiment of the present application;

[0055] Figure 15 A schematic diagram of the framework structure of an electronic device provided in an embodiment of the present application.

[0056] Reference numerals:

[0057] 100- fingerprint recognition device; 101- image acquisition module; 102- comparison module; 103- recognition module;

[0058] 200 - electronic device; 201 - processor; 202 - bus; 203 - memory; 204 - communication unit; 205 - input unit; 206 - output unit. DETAILED DESCRIPTION

[0059] The following describes the embodiments of the present application in conjunction with the accompanying drawings. It should be understood that the embodiments described below in conjunction with the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0060] Those skilled in the art will understand that, unless otherwise stated, the singular forms "a", "an", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of this application refers to the presence of the described features, integers, steps, operations, elements, etc., but does not exclude the implementation of other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the technical field. It should be understood that when we say that an element is "connected" or "coupled" to another element, the element can be directly connected or coupled to the other element, or it can refer to the establishment of a connection relationship between the element and the other element through an intermediate element. In addition, the "connection" or "coupling" used here can include wireless connection or wireless coupling. The term "and / or" used here refers to at least one of the items defined by the term, for example, "A and / or B" can be implemented as "A", or as "B", or as "A and B".

[0061] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0062] As an optical sensor, a fingerprint sensor can accurately capture a 2D image of the object being captured, but it cannot inherently distinguish between genuine and fake fingerprints. Typical fingerprint anti-counterfeiting methods rely on algorithms to identify differences between real and fake fingerprints. For example, by comparing background grayscale, if the background grayscale of a captured single image doesn't match that of a preset template, the fingerprint is considered fake. This static single-image comparison method is easily defeated by increasingly realistic fingerprint counterfeiting methods.

[0063] The fingerprint recognition method, fingerprint recognition device, electronic device and storage medium provided in this application are intended to solve the above technical problems in the prior art.

[0064] The following is a detailed description of the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems with specific embodiments. It should be noted that the following embodiments can refer to, draw on, or combine with each other, and the same terms, similar features, and similar implementation steps in different embodiments will not be repeated.

[0065] like Figure 1 As shown, this embodiment provides a fingerprint recognition method, which includes:

[0066] S1: When the fingerprint recognition area is touched by the fingerprint to be recognized, a first frame of fingerprint image and a second frame of fingerprint image are continuously collected.

[0067] S2: Compare the first fingerprint image frame and the second fingerprint image frame to determine the change between the first fingerprint image frame and the second fingerprint image frame.

[0068] S3: Determine whether the fingerprint to be identified is a real fingerprint based on the changes between the first fingerprint image frame and the second fingerprint image frame.

[0069] The fingerprint recognition method provided in this embodiment continuously captures two frames of fingerprint images during each fingerprint recognition, and determines whether the fingerprint to be recognized is a false fingerprint based on the changes in the two fingerprint images, thereby eliminating the interference of false fingerprints and improving the security of fingerprint recognition.

[0070] Specifically, in the fingerprint recognition method provided in this embodiment, step S1 includes: acquiring a first frame of fingerprint image with a first exposure time t1, and acquiring a second frame of fingerprint image with a second exposure time t2, where the first exposure time t1 is shorter than the second exposure time t2.

[0071] like Figure 2 As shown, Figure 2 In the figure (a) and (b) are the first and second frames of fingerprint images of a real fingerprint, respectively. (c) and (d) are the first and second frames of fingerprint images of a 2D fake fingerprint made from the same real finger as (a). It should be noted that the real fingerprint in this application is the fingerprint collected directly from the real finger. Figure 2 As can be seen from the figure, the characteristic points of the real and fake fingerprints are the same, with the same valley and ridge orientation. However, the overall quality of the real fingerprint images (a) and (b) is poor, with the second fingerprint image being of better quality than the first. However, the two fingerprint images of the fake fingerprint are essentially identical.

[0072] like Figure 3 As shown, the fingerprint of a real finger consists of raised ridges and sunken valleys. During the fingerprint recognition process, the ridges are in contact with the collection surface of the fingerprint collection device 100, while the valleys are not. Therefore, the reflection and refraction of light by the ridges and valleys in the fingerprint are different, so that the fingerprint collection device 100 collects a fingerprint image with alternating light and dark. In the fingerprint image, the dark lines correspond to the ridges, while the light lines correspond to the valleys. However, due to the distribution of sweat pores or breakpoints on the ridges, that is, Figure 3The positions corresponding to the two bright spots in the ridge region in (a) are shown. Therefore, the ridges in the fingerprint image may appear discontinuous.

[0073] Specifically, the fingerprint collection device 100 is an OLED display with an under-screen fingerprint recognition function. The first exposure time is t1, the second exposure time is t2, and the entire fingerprint collection time is t1+t2.

[0074] like Figure 3 As shown in the figure, during the entire fingerprint collection process, the finger presses the fingerprint collection area of ​​the OLED display. When the finger just presses the display (for example, within the first exposure time t1), the ridge of the finger does not fully contact the screen, and a breakpoint is formed at the sweat pore or the signal is weak, resulting in discontinuity of the ridge. Figure 2 The ridges in (a) appear alternating between light and dark. The low valley-ridge difference signal results in a small difference in brightness between valleys and ridges, resulting in poor fingerprint image quality. However, as the finger's pressure on the display increases, oil and sweat fill the gaps, and the ridges become continuous (uniformly dark). The valley-ridge difference signal increases, resulting in a better-continuous second-frame fingerprint image than the first, and improved image quality.

[0075] Combine Figure 2 and Figure 3 , it can be seen that the continuity of the ridges of the real fingerprint in the second frame of fingerprint image is better than that in the first frame of fingerprint image, while the continuity of the fake fingerprint basically does not change.

[0076] like Figure 4 As shown, in the fingerprint recognition method provided in this embodiment, step S2 includes:

[0077] S21: n first monitoring areas are selected, where the first monitoring areas are located in the first area of ​​the first fingerprint image and the second fingerprint image, and each first monitoring area in the first fingerprint image is located at the same position as a first monitoring area in the second fingerprint image.

[0078] Specifically, if Figure 5 As shown, this is because the pressing force in the central area of ​​the fingerprint image is more uniform, which can better reflect the continuous change of the ridges. Therefore, it is more appropriate to select the first monitoring area at a position closer to the central area in the fingerprint image, that is, the middle area of ​​the fingerprint image is used as the first area.

[0079] S22: Compare the difference between the valleys and ridges in the first monitoring area in the first fingerprint image frame and the first monitoring area in the second fingerprint image frame to determine the change in ridge continuity.

[0080] S23: m second monitoring areas are selected, and the second monitoring areas are located in the second areas of the first frame fingerprint image and the second frame fingerprint image, and each second monitoring area in the first frame fingerprint image is located in the same position as a second monitoring area in the second frame fingerprint image, wherein the second area is located outside the first area, and m and n are both integers greater than or equal to 2.

[0081] Specifically, if Figure 6 As shown, the second area is located outside the first area, meaning that the second monitoring area is selected at the edge of the fingerprint image. This is because it is impossible to maintain constant pressure when a finger presses the acquisition surface of a fingerprint image acquisition device. In normal pressing habits, the pressure is low when the finger first contacts the acquisition surface and then increases. The fingerprint deformation reflected in the image, namely the deformation of the ridge line, varies with the pressure.

[0082] Specifically, for a real finger (real fingerprint), what appears in the fingerprint image is that when position ① on the same ridge line is offset 2 to 3 pixels diagonally upward, position ② is offset 2 to 3 pixels diagonally downward; while on the same ridge line in the fake fingerprint image, position ① is offset 2 to 3 pixels diagonally upward, and position ② is also offset 2 to 3 pixels diagonally upward, that is, the 2D fake fingerprint has no elastic deformation, only overall slippage.

[0083] Specifically, take m and n as an example, Figure 7 As shown, Figure 7 The box M in the figure is the boundary between the first and second areas, where the area inside box M is the first area, and the area outside box M is the second area. A1 to A4 are the four first monitoring areas located within the first area, and B1 to B4 are the four second monitoring areas located within the second area. To more accurately distinguish genuine and fake fingerprints, the four first monitoring areas should be relatively dispersed and evenly distributed in the first area, and the four second monitoring areas should be relatively dispersed and evenly distributed in the second area. In one specific embodiment, the center points of the four first monitoring areas are sequentially connected to form a rectangle, and the center points of the four second monitoring areas are also sequentially connected to form a rectangle.

[0084] S24: Compare the ridge line position difference in the second monitoring area in the first fingerprint image frame and the second monitoring area in the second fingerprint image frame to determine the ridge line offset.

[0085] In the fingerprint recognition method provided in this embodiment, through multiple judgments on the changes in ridge continuity and the ridge line offset, it is possible to accurately identify real fingerprints or fake fingerprints, thereby greatly improving the security of fingerprint recognition.

[0086] like Figure 8 As shown, in the fingerprint recognition method provided in this embodiment, step S21 includes:

[0087] S221: Determine a ridge signal amount in a first monitoring area in a first frame of fingerprint image as a first signal amount, and calculate a valley-ridge difference in the first monitoring area in the first frame of fingerprint image as a first valley-ridge difference.

[0088] S222: Determine the ridge signal amount in the first monitoring area in the second frame of fingerprint image as the second signal amount, and calculate the valley-ridge difference in the first monitoring area in the second frame of fingerprint image as the second valley-ridge difference.

[0089] S223: Compare the difference between the first signal quantity and the second signal quantity and compare the first valley-ridge difference and the second valley-ridge difference to determine the change in ridge continuity.

[0090] Specifically, if the ratio of the first signal amount to the second signal amount is equal to the ratio of the first exposure time to the second exposure time, and the average variance of the first valley-ridge difference is equal to the average variance of the second valley-ridge difference, then the fingerprint to be identified is determined to be a false fingerprint; if the ratio of the first signal amount to the second signal amount is less than the ratio of the first exposure time to the second exposure time, and the average variance of the second valley-ridge difference is less than the average variance of the first valley-ridge difference, then the fingerprint to be identified is determined to be a real fingerprint.

[0091] Specifically, if Figure 9 As shown, the signal quantity analysis and valley-ridge difference analysis are as follows: if the valley-ridge signal quantity of the two frames of fingerprint images is only proportional to the image acquisition time (signal2 / signal1=t2 / t1), and the valley-ridge fluctuation trend in the two frames of fingerprint images is consistent, it indicates that it is a false fingerprint; if the ratio of the valley-ridge signal quantity of the two frames of fingerprint images is greater than the image acquisition time ratio (signal2 / signal1>t2 / t1), and the valley-ridge difference fluctuation gap in the second frame of fingerprint image decreases, it indicates that the quality of the fingerprint image is gradually improving and it is a real fingerprint.

[0092] Specifically, if Figure 9 As shown, the calculation of the valley-ridge difference in the first monitoring area of ​​the first frame of the fingerprint image is used as an example to illustrate the first valley-ridge difference. Specifically, in the direction perpendicular to the ridge line, the grayscale average of the ridge and valley is calculated to calculate the valley-ridge difference; the valley-ridge difference of all pixels along the ridge line is calculated. This is because when the finger presses the screen, the valley (corresponding to Figure 9 The bright lines between adjacent dark lines in the middle do not touch the screen, so the grayscale of the valley is relatively uniform, while the ridge has uneven grayscale due to the sweat pores. Therefore, the more uniform the fluctuation of the valley-ridge difference along the ridge line, the better the fingerprint image quality.

[0093] Specifically, if Figure 9As shown, taking the first monitoring area A3 as an example, the grayscale of each pixel on the ridge (dark line) and the valley (bright line) is determined, and then the grayscale difference between each pixel on the ridge and the adjacent pixel on the valley is determined. For ease of calculation, the grayscale difference can also be calculated by subtracting the average grayscale of the valley from the grayscale of each pixel on the ridge. The first grayscale difference of the first monitoring area A3 in the first frame of the fingerprint image after the above calculation is the first grayscale difference of the first monitoring area A3, and the second grayscale difference of the first monitoring area A3 in the second frame of the fingerprint image after the above calculation is the second grayscale difference of the first monitoring area A3.

[0094] Specifically, the line graph of the grayscale difference corresponding to each pixel on the ridge line is as follows: Figure 10 As shown by Figure 10 It can be seen that the smaller the fluctuation of the grayscale difference, the smaller the average variance of each grayscale difference, that is, the more uniform the grayscale of the ridge line, the better the ridge continuity, that is, the better the quality of the fingerprint image. Therefore,

[0095] like Figure 11 As shown, in the fingerprint recognition method provided in this embodiment, step S24 includes:

[0096] S241: Determine the ridge line offset in each second monitoring area in the first frame of fingerprint image as the first offset.

[0097] S242: Determine the ridge line offset in each second monitoring area in the second frame of fingerprint image as the second offset.

[0098] S243: Determine an offset value between each first offset and a second offset corresponding to each first offset, and determine whether the fingerprint to be identified is a real fingerprint according to each offset value.

[0099] Specifically, if Figure 12 As shown, step S243 includes: determining the offset value Δx in the X direction and the offset value Δy in the Y direction of each first offset and the second offset corresponding to each first offset; analyzing each offset value, if the offset direction of each offset value Δx is the same and the offset direction of each offset value Δy is the same, then determining that the fingerprint to be identified is a false fingerprint; if at least one of the offset values ​​Δx has a different offset direction, and / or at least one of the offset values ​​Δy has a different offset direction, then determining that the fingerprint to be identified is a real fingerprint. Figure 12 As shown, if the offset values ​​Δx1 and Δx2 have different offset directions, it is determined that the fingerprint image originates from a real fingerprint.

[0100] Alternatively, as Figure 13As shown, the fingerprint recognition method provided by this embodiment further includes: comparing the first frame fingerprint image or the second frame fingerprint image with the fingerprint template to determine whether the fingerprint to be recognized matches the fingerprint template. If they match, the fingerprint recognition passes, otherwise the fingerprint recognition fails. It should be noted that this step can be performed before step S2, or after step S2, or as Figure 13 The steps shown are performed simultaneously with step S2. Unlocking can only be performed if the fingerprint to be identified is a real fingerprint and is compared with the fingerprint template. This can eliminate false fingerprints and improve the security of fingerprint identification.

[0101] Based on the same inventive concept, the present application also provides a fingerprint recognition device, such as Figure 14 As shown, the fingerprint recognition device 100 provided in this embodiment includes an image acquisition module 101 and a recognition module 103 .

[0102] The image acquisition module 101 is configured to acquire a first frame of fingerprint image and a second frame of fingerprint image when the fingerprint recognition area is touched by the fingerprint to be recognized.

[0103] Specifically, the image acquisition module 101 acquires a first frame of fingerprint image with a first exposure time, and acquires a second frame of fingerprint image with a second exposure time, where the first exposure time is shorter than the second exposure time.

[0104] like Figure 2 As shown, Figure 2 (a) and (b) are the first and second fingerprint images of a real fingerprint (the fingerprint to be identified is from a real finger), respectively. (c) and (d) are the first and second fingerprint images of a 2D fake fingerprint made from the same real finger as (a). The first exposure time is t1, the second exposure time is t2, and the entire fingerprint acquisition time is t1+t2. Figure 2 As can be seen from the figure, the characteristic points of the real and fake fingerprints are the same, with the same valley and ridge orientation. However, the overall quality of the real fingerprint images (a) and (b) is poor, with the second fingerprint image being of better quality than the first. However, the two fingerprint images of the fake fingerprint are essentially identical.

[0105] pass Figure 2 Comparing the details in (a) to (d), we can see that the ridge continuity of the second fingerprint image is better than that of the first, while the continuity of the fake fingerprint remains essentially unchanged. This is because real fingers are not smooth and have many sweat pores on their surface, resulting in uneven ridges.

[0106] like Figure 3 As shown in the figure, when the finger presses the screen, the ridge line does not fully contact the screen, and a breakpoint is formed at the sweat pore or the signal is weak, resulting in discontinuity of the ridge line (i.e. Figure 2The ridges in the image are alternating between light and dark), and the valley-ridge difference signal is low (the difference between the brightness of the valleys and ridges is small). As the real finger presses the screen for longer, oil and sweat fill the gaps, the ridges become continuous (the ridges are uniformly dark), and the valley-ridge difference signal increases. Therefore, the second frame of the real finger's fingerprint image has better continuity than the first frame.

[0107] The comparison module 102 is configured to compare the first fingerprint image frame and the second fingerprint image frame to determine the changes between the first fingerprint image frame and the second fingerprint image frame, and determine whether the fingerprint to be identified is a real fingerprint based on the changes between the first fingerprint image frame and the second fingerprint image frame.

[0108] Specifically, the comparison module 102 is configured to select n first monitoring areas, and compare the ridge continuity changes in the first monitoring area in the first frame fingerprint image and the first monitoring area in the second frame fingerprint image; and select m second monitoring areas, and compare the ridge line offsets in the second monitoring area in the first frame fingerprint image and the second monitoring area in the second frame fingerprint image; wherein the second monitoring area is located outside the first monitoring area, and m and n are both integers greater than or equal to 2.

[0109] Specifically, if Figure 5 As shown, the first monitoring area is a position closer to the center area in the fingerprint image. This is because the pressing force in the center area of ​​the fingerprint image is more uniform, which can better reflect the continuous change of the ridges.

[0110] Specifically, if Figure 6 As shown, the second area is located outside the first area, that is, the second monitoring area is selected at the edge of the fingerprint image. This is because it is impossible to maintain the same pressure when the finger presses the collection surface of the fingerprint image acquisition device. In normal pressing habits, the pressing pressure is small when it first contacts the collection surface, and then it becomes larger. The fingerprint deformation reflected in the image, that is, the deformation amount of the ridge line, is different under different pressing pressures. For a real finger (real fingerprint), what is reflected in the fingerprint image is that when position ① on the same ridge line is offset 2 to 3 pixels diagonally upward, position ② is offset 2 to 3 pixels diagonally downward. On the same ridge line in the fake fingerprint image, position ① is offset 2 to 3 pixels diagonally upward, and position ② is also offset 2 to 3 pixels diagonally upward. In other words, the 2D fake fingerprint has no elastic deformation, only overall slippage.

[0111] Therefore, through multiple judgments on the changes in ridge continuity and ridge line deviation, real fingerprints or fake fingerprints can be accurately identified, greatly improving the security of fingerprint recognition.

[0112] The fingerprint recognition device 100 provided in this embodiment continuously captures two frames of fingerprint images during each fingerprint recognition and determines whether the fingerprint to be recognized is a false fingerprint based on the changes in the two fingerprint images, thereby eliminating the interference of false fingerprints and improving the security of the fingerprint recognition device.

[0113] Specifically, how the comparison module 102 compares the ridge continuity changes in the first monitoring area in the first frame fingerprint image and the first monitoring area in the second frame fingerprint image, and how the comparison module 102 compares the ridge line offset in the second monitoring area in the first frame fingerprint image and the second monitoring area in the second frame fingerprint image, please refer to the above-mentioned embodiment of the fingerprint recognition method, which will not be repeated here.

[0114] like Figure 14 As shown, the fingerprint recognition device provided in this embodiment also includes a recognition module 103. The recognition module 103 is configured to compare the second fingerprint image frame or the second fingerprint image frame with the fingerprint template to determine whether the fingerprint to be recognized matches the fingerprint template. If they match, the fingerprint recognition passes; otherwise, the fingerprint recognition fails. Unlocking can only be performed if the fingerprint to be recognized is determined to be a genuine fingerprint and passes the comparison with the fingerprint template. Therefore, false fingerprints can be excluded, thereby improving the security of the fingerprint recognition device.

[0115] Based on the same inventive concept, the embodiment of the present application further provides an electronic device, such as Figure 15 As shown, the electronic device 200 includes a memory 203, a processor 201 and a computer program stored in the memory 203. The processor 201 executes the computer program to implement the fingerprint recognition method in the above embodiment, which has the beneficial effects of the fingerprint recognition method in the above embodiment and will not be repeated here.

[0116] In an optional embodiment, the present application provides an electronic device 200, such as Figure 15 As shown, Figure 15 The electronic device 200 shown includes a processor 201 and a memory 203 , wherein the processor 201 and the memory 203 are communicatively connected to each other, for example, via a bus 202 .

[0117] The processor 201 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor 201 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0118] The bus 202 may include a path for transmitting information between the above components. The bus 202 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 202 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 13 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0119] The memory 203 can be a ROM (Read-Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (random access memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0120] Optionally, the electronic device 200 may further include a communication unit 204. The communication unit 204 may be used to receive and transmit signals. The communication unit 204 may allow the electronic device 200 to communicate with other devices wirelessly or by wire to exchange data. It should be noted that in actual applications, the number of communication units 204 is not limited to one.

[0121] Optionally, the electronic device 200 may further include an input unit 205. The input unit 205 may be configured to receive input digital, character, image, and / or sound information, or to generate key signal input related to user settings and function control of the electronic device 200. The input unit 205 may include, but is not limited to, one or more of a touch screen, a physical keyboard, function keys (such as a volume control key, a power key, etc.), a trackball, a mouse, a joystick, a camera, a microphone, and the like.

[0122] Optionally, the electronic device 200 may further include an output unit 206. The output unit 206 may be used to output or display information processed by the processor 201. The output unit 206 may include, but is not limited to, one or more of a display device, a speaker, a vibration device, and the like.

[0123] Although Figure 13 The electronic device 200 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0124] Optionally, the memory 203 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 201. The processor 201 is used to execute the application code stored in the memory 203 to implement any fingerprint recognition method provided in the embodiments of the present application.

[0125] Optionally, the electronic device 200 includes but is not limited to a mobile phone with a fingerprint recognition function, an access control system with a fingerprint recognition function, a clocking-in system with a fingerprint recognition function, etc.

[0126] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. The computer-readable storage medium is characterized in that when the computer program is executed by an electronic device, any fingerprint recognition method in the above embodiments is implemented.

[0127] By applying the embodiments of the present application, at least the following beneficial effects can be achieved:

[0128] The fingerprint recognition method, fingerprint recognition device, electronic device, and storage medium provided in this embodiment continuously capture two frames of fingerprint images during each fingerprint recognition and determine whether the fingerprint to be recognized is a false fingerprint based on changes in the two fingerprint images. This can eliminate interference from false fingerprints and improve the security of fingerprint recognition.

[0129] Those skilled in the art will appreciate that the steps, measures, and schemes in the various operations, methods, and processes discussed in this application may be interchanged, modified, combined, or deleted. Furthermore, other steps, measures, and schemes in the various operations, methods, and processes discussed in this application may also be interchanged, modified, rearranged, decomposed, combined, or deleted. Furthermore, steps, measures, and schemes in the prior art that are similar to those disclosed in this application may also be interchanged, modified, rearranged, decomposed, combined, or deleted.

[0130] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0131] It should be understood that, although the various steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, the order of implementation of these steps is not limited to the order indicated by the arrows. Unless otherwise clearly stated herein, in some implementation scenarios of the embodiments of the present application, the steps in each process can be performed in other orders as required. Moreover, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages may be executed at the same time, or may be executed at different times in different scenarios at the execution time. The execution order of these sub-steps or stages may be flexibly configured as required, and the embodiments of the present application do not limit this.

[0132] The above is only part of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of the present application, other similar implementation methods based on the technical ideas of the present application also fall within the protection scope of the embodiments of the present application.

Claims

1. A fingerprint recognition method, characterized in that: include: When the fingerprint recognition area is touched by the fingerprint to be recognized, a first frame of fingerprint image and a second frame of fingerprint image are captured continuously; Comparing the first fingerprint image frame and the second fingerprint image frame to determine a change between the first fingerprint image frame and the second fingerprint image frame; Determining whether the fingerprint to be identified is a real fingerprint according to changes between the first fingerprint image frame and the second fingerprint image frame; The fingerprint recognition method specifically includes: Determine the ridge signal amount in the first monitoring area of ​​the first frame of fingerprint image as the first signal amount, and calculate the valley-ridge difference in the first monitoring area of ​​the first frame of fingerprint image as the first valley-ridge difference; determine the ridge signal amount in the first monitoring area of ​​the second frame of fingerprint image as the second signal amount, and calculate the valley-ridge difference in the first monitoring area of ​​the second frame of fingerprint image as the second valley-ridge difference; compare the difference between the first signal amount and the second signal amount and compare the first valley-ridge difference with the second valley-ridge difference to determine the change in ridge continuity; If the ratio of the first signal amount to the second signal amount is equal to the ratio of the first exposure time to the second exposure time, and the average variance of the first valley-ridge difference is equal to the average variance of the second valley-ridge difference, then it is determined that the fingerprint to be identified is a false fingerprint; If the ratio of the first signal amount to the second signal amount is smaller than the ratio of the first exposure time to the second exposure time, and the average variance of the second valley-ridge difference is smaller than the average variance of the first valley-ridge difference, then the fingerprint to be identified is determined to be a genuine fingerprint; The first frame of fingerprint image is collected with a first exposure time, and the second frame of fingerprint image is collected with a second exposure time.

2. The fingerprint recognition method according to claim 1, characterized in that: Also includes: The first frame of fingerprint image or the second frame of fingerprint image is compared with a fingerprint template to determine whether the fingerprint to be identified matches the fingerprint template. If they match, the fingerprint identification passes; otherwise, the fingerprint identification fails.

3. The fingerprint recognition method according to claim 2, characterized in that: The first exposure duration is shorter than the second exposure duration.

4. The fingerprint recognition method according to claim 3, characterized in that: Comparing the first fingerprint image frame and the second fingerprint image frame to determine a change between the first fingerprint image frame and the second fingerprint image frame includes: Selecting n first monitoring areas, where the first monitoring areas are located in the first area of ​​the first fingerprint image and the second fingerprint image, and each of the first monitoring areas in the first fingerprint image is located at the same position as one of the first monitoring areas in the second fingerprint image; Comparing the difference between the valleys and ridges in the first monitoring area in the first fingerprint image frame and the valleys and ridges in the first monitoring area in the second fingerprint image frame to determine the change in ridge continuity; m second monitoring areas are selected, where the second monitoring areas are located in the second areas of the first fingerprint image frame and the second fingerprint image frame, and each of the second monitoring areas in the first fingerprint image frame is located at the same position as one of the second monitoring areas in the second fingerprint image frame, wherein the second areas are located outside the first area, and m and n are both integers greater than or equal to 2; The ridge line position difference in the second monitoring area in the first frame fingerprint image and the second monitoring area in the second frame fingerprint image is compared to determine the ridge line offset.

5. The fingerprint recognition method according to claim 4, characterized in that: The step of determining whether the fingerprint to be identified is a real fingerprint according to the change between the first fingerprint image frame and the second fingerprint image frame further includes: Determine a ridge line offset in each of the second monitoring areas in the first frame of fingerprint image as a first offset; Determine a ridge line offset in each of the second monitoring areas in the second fingerprint image frame as a second offset; An offset value between each first offset and the second offset corresponding to each first offset is determined, and whether the fingerprint to be identified is a real fingerprint is determined according to each offset value.

6. The fingerprint recognition method according to claim 5, characterized in that: Determining an offset value between each first offset and the second offset corresponding to each first offset, and determining whether the fingerprint to be identified is a real fingerprint according to each offset value, includes: Determine an offset value Δx in the X direction and an offset value Δy in the Y direction of each first offset and a second offset corresponding to each first offset; Each of the offset values ​​is analyzed. If the offset directions of the offset values ​​Δx are the same and the offset directions of the offset values ​​Δy are the same, then the fingerprint to be identified is determined to be a false fingerprint; if the offset directions of at least one of the offset values ​​Δx are different, and / or the offset directions of at least one of the offset values ​​Δy are different, then the fingerprint to be identified is determined to be a real fingerprint.

7. A fingerprint recognition device, characterized in that: include: An image acquisition module is configured to acquire a first frame of fingerprint image and a second frame of fingerprint image when the fingerprint recognition area is touched by the fingerprint to be recognized; a comparison module configured to compare the first fingerprint image frame and the second fingerprint image frame to determine a change between the first fingerprint image frame and the second fingerprint image frame, and determine whether the fingerprint to be identified is a real fingerprint based on the change between the first fingerprint image frame and the second fingerprint image frame; The comparison module is specifically configured to determine a ridge signal amount in a first monitoring area in the first frame of fingerprint image as a first signal amount, and calculate a valley-ridge difference in the first monitoring area in the first frame of fingerprint image as a first valley-ridge difference; Determine a ridge signal amount in the first monitoring area in the second frame of fingerprint image as a second signal amount, and calculate a valley-ridge difference value in the first monitoring area in the second frame of fingerprint image as a second valley-ridge difference value; Comparing the difference between the first signal amount and the second signal amount and comparing the first valley-ridge difference and the second valley-ridge difference to determine the change in ridge continuity; if the ratio of the first signal amount to the second signal amount is equal to the ratio of the first exposure time to the second exposure time, and the average variance of the first valley-ridge difference is equal to the average variance of the second valley-ridge difference, then determining that the fingerprint to be identified is a false fingerprint; if the ratio of the first signal amount to the second signal amount is less than the ratio of the first exposure time to the second exposure time, and the average variance of the second valley-ridge difference is less than the average variance of the first valley-ridge difference, then determining that the fingerprint to be identified is a real fingerprint; The first frame of fingerprint image is collected with a first exposure time, and the second frame of fingerprint image is collected with a second exposure time.

8. The fingerprint recognition device according to claim 7, characterized in that: Also includes: The recognition module compares the second frame fingerprint image or the second frame fingerprint image with the fingerprint template to determine whether the fingerprint to be recognized matches the fingerprint template. If they match, the fingerprint recognition passes; otherwise, the fingerprint recognition fails.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the fingerprint recognition method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium is characterized in that when the computer program is executed by an electronic device, the fingerprint recognition method according to any one of claims 1 to 6 is implemented.

Images