Fingerprint unlocking method and device based on forged fingerprint feature recognition

Abstract

The invention relates to the field of fingerprint forgery detection, and discloses a fingerprint unlocking method and device based on forgery fingerprint feature recognition, and the method comprises the steps: obtaining a fingerprint optical image obtained through an optical fingerprint unlocking assembly; determining a fingerprint boundary feature of the fingerprint optical image according to the fingerprint optical image through a fingerprint boundary feature recognition model, and determining a first counterfeiting probability corresponding to the fingerprint optical image according to the fingerprint boundary feature; determining a fingerprint blank feature of the fingerprint optical image according to the fingerprint optical image, and determining a second counterfeiting probability corresponding to the fingerprint optical image according to the fingerprint blank feature; and when the first forgery probability is greater than or equal to a preset first forgery probability, or when the first forgery probability is smaller than the preset first forgery probability and the second forgery probability is greater than or equal to a preset second forgery probability, judging that the fingerprint corresponding to the fingerprint optical image is a forgery fingerprint. According to the invention, the identification capability of the electronic equipment on forged fingerprints can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of fingerprint forgery detection, and more specifically, to a fingerprint unlocking method and device based on forged fingerprint feature recognition. Background Art

[0002] Fake fingerprints pose a huge security risk to society, especially in unlocking electronic devices. With the popularity of devices such as smartphones, tablets, and laptops, fingerprint recognition has become one of the mainstream biometric authentication methods. Criminals may obtain the fingerprint information of the target user and use it to create a highly simulated fingerprint model, thereby easily unlocking the device, stealing personal privacy data, financial information, and even performing malicious operations. This may not only lead to privacy leakage and property loss of users, but may also cause more serious social problems, such as identity theft and online fraud.

[0003] At present, the ability of electronic devices to recognize forged fingerprints is still significantly insufficient. First, the fingerprint recognition systems of many devices are overly dependent on a single biometric feature in their design, such as simple 2D image comparison or low-resolution sensors, which allows forged fingerprints to easily bypass the fingerprint recognition system of electronic devices through surface contact. Secondly, electronic device manufacturers have not invested enough in the security of fingerprint devices, resulting in slow updates of recognition algorithms and an inability to respond to new developments in forgery technology in a timely manner. Due to the above reasons, the security vulnerabilities of electronic devices in insufficient recognition capabilities when facing forged fingerprints have further exacerbated the social risks that forged fingerprints may bring. Summary of the invention

[0004] The purpose of this application is to provide a fingerprint unlocking method and device based on forged fingerprint feature recognition, which solves the technical problem of insufficient recognition ability of electronic devices for forged fingerprints and achieves the technical effect of improving the recognition ability of electronic devices for forged fingerprints.

[0005] A fingerprint unlocking method based on forged fingerprint feature recognition provided by an embodiment of the present application comprises: acquiring a fingerprint optical image acquired by an optical fingerprint unlocking component; determining a fingerprint boundary feature of the fingerprint optical image according to the fingerprint optical image through a fingerprint boundary feature recognition model, and determining a first forgery probability corresponding to the fingerprint optical image according to the fingerprint boundary feature; determining a fingerprint blank feature of the fingerprint optical image according to the fingerprint optical image through a blank feature recognition model, and determining a second forgery probability corresponding to the fingerprint optical image according to the fingerprint blank feature; when the first forgery probability is greater than or equal to a preset first forgery probability, or when the first forgery probability is less than the preset first forgery probability and when the second forgery probability is greater than or equal to the preset second forgery probability, or when the first forgery probability is greater than or equal to a preset third forgery probability and when the second forgery probability is greater than or equal to a preset fourth forgery probability, determining that the fingerprint corresponding to the fingerprint optical image is a forged fingerprint; wherein the preset third forgery probability is less than the preset first forgery probability, and the preset fourth forgery probability is less than the preset second forgery probability.

[0006] In a possible implementation, the fingerprint boundary features include boundary features corresponding to the concave, convex, incomplete, and sharp boundaries of the fingerprint optical image, and the fingerprint blank features include fingerprint blank features corresponding to the number and area of ​​fingerprint blank regions of the fingerprint optical image.

[0007] In another possible implementation, a fingerprint blank feature of the fingerprint optical image is determined according to the fingerprint optical image through a blank feature recognition model, and a second forgery probability corresponding to the fingerprint optical image is determined according to the fingerprint blank feature, including: determining multiple fingerprint blank areas of the fingerprint optical image according to the fingerprint optical image through the blank feature recognition model, adjusting the brightness and contrast of each fingerprint blank area and performing post-filtering processing, binarizing each fingerprint blank area, and identifying fine line patterns in each fingerprint blank area through wavelet transform; determining the fingerprint blank feature according to the number and area of ​​the multiple fingerprint blank areas and the fine line patterns in each fingerprint blank area, and determining the second forgery probability corresponding to the fingerprint optical image according to the fingerprint blank feature.

[0008] In another possible implementation, the method further includes: identifying fingerprint connection areas of adjacent fingerprint lines of the fingerprint optical image around each fingerprint blank area of ​​the fingerprint optical image, and determining fingerprint connection features of the fingerprint optical image according to the fingerprint blank area and the fingerprint connection areas around the fingerprint blank area through a fingerprint connection recognition model, and determining a fifth forgery probability corresponding to the fingerprint optical image according to the fingerprint connection features; when the first forgery probability is less than a preset first forgery probability and when the fifth forgery probability is greater than or equal to a preset fifth forgery probability, or when the first forgery probability is greater than or equal to a preset third forgery probability and when the fifth forgery probability is greater than or equal to a preset sixth forgery probability, determining that the fingerprint corresponding to the fingerprint optical image is a forged fingerprint; wherein the preset sixth forgery probability is less than the preset fifth forgery probability.

[0009] In another possible implementation, the method further includes: determining a first number of fingerprint lines connected to each fingerprint connection area, and determining a second number of fingerprint lines intersecting each fingerprint blank area, and determining a ratio of the first number to the second number as a fingerprint connection area adjustment factor, and adjusting the fifth forgery probability by multiplying the fingerprint connection area adjustment factor on the fifth forgery probability.

[0010] In another possible implementation, the method further includes: determining a completed fingerprint line of the fingerprint in each fingerprint blank area of ​​the fingerprint optical image by a region growing algorithm, and determining that the first forgery probability is greater than or equal to the preset first forgery probability when a misalignment distance between a completed fingerprint line in at least one fingerprint blank area and a blank fingerprint line around the fingerprint blank area is greater than a preset misalignment distance.

[0011] In another possible implementation, the method further includes: determining, according to the fingerprint optical image, the number of fingerprint intersections and the total number of fingerprint lines of the fingerprint optical image through a fingerprint line intersection recognition algorithm, and determining a ratio of the number of fingerprint line intersections to the total number of fingerprint lines as a fingerprint intersection area adjustment factor, and adjusting the fifth forgery probability by multiplying the fifth forgery probability by the fingerprint connection area adjustment factor and the fingerprint intersection area adjustment factor.

[0012] An embodiment of the present application also provides a fingerprint unlocking device based on forged fingerprint feature recognition, comprising a unit for executing any of the methods described above.

[0013] An embodiment of the present application also provides a fingerprint unlocking device based on forged fingerprint feature recognition, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.

[0014] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above items is implemented.

[0015] An embodiment of the present application also provides a computer program product, including a computer program, which implements the steps of any of the methods described above when executed by a processor.

[0016] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0017] The embodiment of the present application provides a fingerprint unlocking method based on forged fingerprint feature recognition, the method comprising: obtaining a fingerprint optical image obtained by an optical fingerprint unlocking component; determining the fingerprint boundary feature of the fingerprint optical image according to the fingerprint optical image through a fingerprint boundary feature recognition model, and determining a first forgery probability corresponding to the fingerprint optical image according to the fingerprint boundary feature; determining the fingerprint blank feature of the fingerprint optical image according to the fingerprint optical image through a blank feature recognition model, and determining a second forgery probability corresponding to the fingerprint optical image according to the fingerprint blank feature; when the first forgery probability is greater than or equal to a preset first forgery probability, or when the first forgery probability is less than the preset first forgery probability and when the second forgery probability is greater than or equal to the preset second forgery probability, or when the first forgery probability is greater than or equal to a preset third forgery probability and when the second forgery probability is greater than or equal to a preset fourth forgery probability, judging that the fingerprint corresponding to the fingerprint optical image is a forged fingerprint; wherein the preset third forgery probability is less than the preset first forgery probability, and the preset fourth forgery probability is less than the preset second forgery probability. The method in the embodiment of the present application can evaluate the forgery probability of a fingerprint according to the fingerprint boundary feature and the fingerprint blank feature in the fingerprint, ensure the recognition efficiency and recognition accuracy of forged fingerprints, and improve the recognition effect of forged fingerprints. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1 A schematic diagram of a flow chart of a fingerprint unlocking method based on forged fingerprint feature recognition provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of the acquisition of a forged optical fingerprint image in an embodiment of the present application;

[0021] Figure 3A schematic diagram of an optical fingerprint image provided in an embodiment of the present application;

[0022] Figure 4 A schematic diagram of processing a blank area of ​​a fingerprint using the method in an embodiment of the present application;

[0023] Figure 5 A schematic diagram of identifying a fingerprint connection area according to a method in an embodiment of the present application;

[0024] Figure 6 A schematic diagram of identifying the intersection state of fingerprints according to the method in an embodiment of the present application;

[0025] Figure 7 A schematic diagram of the logical structure of a fingerprint unlocking device based on forged fingerprint feature recognition provided by an embodiment of the present application;

[0026] Figure 8 A schematic diagram of the physical structure of a fingerprint unlocking device based on forged fingerprint feature recognition provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0028] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0029] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0030] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0031] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0032] Currently, electronic equipment manufacturers do not invest enough in the security of fingerprint devices, resulting in slow updates of recognition algorithms and an inability to respond promptly to new developments in counterfeiting technology.

[0033] Based on the above reasons, the embodiment of the present application provides a fingerprint unlocking method based on forged fingerprint feature recognition, the method comprising: obtaining a fingerprint optical image obtained by an optical fingerprint unlocking component; determining the fingerprint boundary feature of the fingerprint optical image according to the fingerprint optical image through a fingerprint boundary feature recognition model, and determining the first forgery probability corresponding to the fingerprint optical image according to the fingerprint boundary feature; determining the fingerprint blank feature of the fingerprint optical image according to the fingerprint optical image through a blank feature recognition model, and determining the second forgery probability corresponding to the fingerprint optical image according to the fingerprint blank feature; when the first forgery probability is greater than or equal to the preset first forgery probability, or when the first forgery probability is less than the preset first forgery probability and when the second forgery probability is greater than or equal to the preset second forgery probability, or when the first forgery probability is greater than or equal to the preset third forgery probability and when the second forgery probability is greater than or equal to the preset fourth forgery probability, the fingerprint corresponding to the fingerprint optical image is judged to be a forged fingerprint; wherein the preset third forgery probability is less than the preset first forgery probability, and the preset fourth forgery probability is less than the preset second forgery probability. The method in the embodiment of the present application can evaluate the forgery probability of the fingerprint according to the fingerprint boundary feature and the fingerprint blank feature in the fingerprint, ensure the recognition efficiency and recognition accuracy of the forged fingerprint, and improve the recognition effect of the forged fingerprint.

[0034] In some scenarios, a fingerprint unlocking method based on forged fingerprint feature recognition in an embodiment of the present application can be applied to fingerprint unlocking of mobile phones, tablet computers, and laptop computers. It can efficiently identify forged fingerprints during fingerprint unlocking and ensure the accuracy of forged fingerprint recognition.

[0035] The following is a detailed description of a fingerprint unlocking method based on forged fingerprint feature recognition provided by an embodiment of the present application with reference to specific examples.

[0036] Figure 1 A schematic diagram of a fingerprint unlocking method based on forged fingerprint feature recognition provided by an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes S110 to S130, and S110 to S130 are described in detail below.

[0037] S110: Acquire a fingerprint optical image acquired by an optical fingerprint unlocking component.

[0038] The method in the embodiment of the present application can first collect an optical fingerprint image through an optical fingerprint unlocking component, and identify the optical fingerprint image to determine whether the fingerprint corresponding to the optical fingerprint image is a forged fingerprint.

[0039] Exemplarily, the optical fingerprint unlocking component may be an optical fingerprint unlocking component of an electronic device to which the present method is applied, thereby enabling the electronic device to recognize forged fingerprints through the method in the embodiments of the present application.

[0040] S120, using a fingerprint boundary feature recognition model, based on the fingerprint optical image, determine the fingerprint boundary feature of the fingerprint optical image, and determine a first forgery probability corresponding to the fingerprint optical image according to the fingerprint boundary feature. Using a blank feature recognition model, based on the fingerprint optical image, determine the fingerprint blank feature of the fingerprint optical image, and determine a second forgery probability corresponding to the fingerprint optical image according to the fingerprint blank feature.

[0041] Since the fingerprint boundary features of the fingerprint optical image are relatively obvious, after acquiring the fingerprint optical image, the fingerprint boundary features of the fingerprint optical image can be first determined according to the fingerprint optical image through a fingerprint boundary feature recognition model, and a first forgery probability corresponding to the fingerprint optical image can be determined according to the fingerprint boundary features. The first forgery probability represents the fingerprint forgery probability obtained by boundary detection in the fingerprint optical image.

[0042] The real fingerprint has good elasticity and is in even contact with the surface of the object, while the forged fingerprint is easy to have blank areas in the forged fingerprint because the material of the forged fingerprint film itself is hard and the flexibility and elasticity of the forged fingerprint film are limited. Therefore, the blank area in the fingerprint can also be used as a basis for identifying forged fingerprints. After obtaining the fingerprint optical image, the blank feature recognition model can be further used to determine the fingerprint blank feature of the fingerprint optical image based on the fingerprint optical image, and the second forgery probability corresponding to the fingerprint optical image can be determined based on the fingerprint blank feature. The second forgery probability represents the fingerprint forgery probability obtained by detecting the blank area in the fingerprint optical image.

[0043] In the embodiment of the present application, Figure 2 Schematic diagram of the acquisition of forged optical fingerprint images in the embodiment of the present application, as shown in FIG. Figure 2As shown, a forged fingerprint can be first made, and a forged optical fingerprint image of the forged fingerprint can be collected by an electronic device, and the forged optical fingerprint image can be labeled, and then the fingerprint boundary feature recognition model and the blank feature recognition model can be trained through a deep learning model, and then the training of the fingerprint boundary feature recognition model and the blank feature recognition model can be realized.

[0044] Figure 3 A schematic diagram of an optical fingerprint image provided in an embodiment of the present application, such as Figure 3 As shown, the method in the embodiment of the present application is working, as Figure 3 As shown in Figure a, the fingerprint boundary feature recognition model can be used to identify Figure 3 The fingerprint boundary features of the fingerprint optical image in Figure a are identified. The fingerprint boundary features can be Figure 3 The fingerprint boundary features corresponding to the image marked in the rectangular box in Figure a.

[0045] like Figure 3 As shown, the method in the embodiment of the present application is working, as Figure 3 As shown in Figure b, the blank feature recognition model can be used to identify Figure 3 The fingerprint blank feature of the fingerprint optical image in Figure b is used for identification. The fingerprint blank feature can be Figure 3 The fingerprint blank feature corresponding to the image marked in the rectangular box in Figure b.

[0046] S130: When the first forgery probability is greater than or equal to the preset first forgery probability, or when the first forgery probability is less than the preset first forgery probability and when the second forgery probability is greater than or equal to the preset second forgery probability, or when the first forgery probability is greater than or equal to the preset third forgery probability and when the second forgery probability is greater than or equal to the preset fourth forgery probability, it is determined that the fingerprint corresponding to the fingerprint optical image is a forged fingerprint. The preset third forgery probability is less than the preset first forgery probability, and the preset fourth forgery probability is less than the preset second forgery probability.

[0047] After obtaining the first forgery probability and the second forgery probability, when the first forgery probability is greater than or equal to the preset first forgery probability, it means that the first forgery probability obtained based on the fingerprint boundary feature is larger, and then the fingerprint corresponding to the fingerprint optical image can be judged as a forged fingerprint based solely on the first forgery probability.

[0048] After obtaining the first forgery probability and the second forgery probability, when the first forgery probability is less than the preset first forgery probability, and when the second forgery probability is greater than or equal to the preset second forgery probability, it means that the first forgery probability obtained based on the fingerprint boundary feature is smaller and the second forgery probability obtained based on the fingerprint blank feature is larger, and then the fingerprint corresponding to the fingerprint optical image can be judged as a forged fingerprint based solely on the second forgery probability.

[0049] After obtaining the first forgery probability and the second forgery probability, when the first forgery probability is greater than or equal to the preset third forgery probability, and when the second forgery probability is greater than or equal to the preset fourth forgery probability, the preset third forgery probability is less than the preset first forgery probability, and the preset fourth forgery probability is less than the preset second forgery probability, it means that the first forgery probability obtained according to the fingerprint boundary feature and the second forgery probability obtained according to the fingerprint blank feature are both within a relatively large numerical range, and neither can be judged as a forged fingerprint based on the first forgery probability and the second forgery probability alone, and the fingerprint corresponding to the fingerprint optical image can be judged as a forged fingerprint based on the first forgery probability and the second forgery probability in combination.

[0050] The beneficial effect of the above implementation method is that the fingerprint boundary features of the fingerprint optical image are relatively obvious. When the first forgery probability obtained by the fingerprint boundary features is relatively large, the fingerprint corresponding to the fingerprint optical image can be judged as a forged fingerprint based solely on the first forgery probability, which can reduce the calculation amount of forged fingerprint recognition and ensure the recognition accuracy and efficiency of forged fingerprints.

[0051] The beneficial effect of the above implementation method is that the first forgery probability obtained based on the fingerprint boundary feature is smaller, and the second forgery probability obtained based on the fingerprint blank feature is larger, and then the fingerprint corresponding to the fingerprint optical image can be judged as a forged fingerprint based solely on the second forgery probability, which can ensure the recognition accuracy of forged fingerprints.

[0052] The beneficial effect of the above implementation method is that when it is impossible to judge that the fingerprint is a forged fingerprint based on the first forgery probability and the second forgery probability alone, the fingerprint corresponding to the fingerprint optical image can be judged as a forged fingerprint based on the first forgery probability and the second forgery probability, which can further ensure the recognition accuracy of forged fingerprints.

[0053] In some implementations, the fingerprint boundary features include boundary features corresponding to the concave, convex, incomplete, and sharp boundaries of the fingerprint optical image, and the fingerprint blank features include fingerprint blank features corresponding to the number and area of ​​fingerprint blank regions of the fingerprint optical image.

[0054] like Figure 3 As shown in the area framed in Figure a, in the production of forged fingerprints, "artificial traces" often appear near the fingerprint boundary. The "artificial traces" are defects caused by operations such as cutting and trimming during the formation of the fingerprint film. The fingerprint boundary features may include boundary features corresponding to the concave, convex, incomplete, and sharp boundaries of the fingerprint optical image, and the forged fingerprint can be identified based on the concave, convex, incomplete, and sharp boundaries of the fingerprint optical image.

[0055] like Figure 3As shown in the area framed in Figure b, since the material of the forged fingerprint film itself is relatively hard and the flexibility and elasticity of the forged fingerprint film are limited, the fingerprint blank feature includes the fingerprint blank feature corresponding to the number and area of ​​the fingerprint blank area of ​​the fingerprint optical image, and then the forged fingerprint can be identified according to the number and area of ​​the fingerprint blank area of ​​the fingerprint optical image.

[0056] The beneficial effect of the above implementation method is that it can identify the forged fingerprint by combining the concave-convex, incomplete and sharp boundaries of the fingerprint optical image, thereby improving the recognition accuracy of the forged fingerprint.

[0057] The beneficial effect of the above implementation is that a forged fingerprint can be identified based on the number and area of ​​the fingerprint blank areas in the fingerprint optical image.

[0058] In some implementations, in the above S120, a fingerprint blank feature of the fingerprint optical image is determined according to the fingerprint optical image through a blank feature recognition model, and a second forgery probability corresponding to the fingerprint optical image is determined according to the fingerprint blank feature, including S121 to S122, and S121 to S122 are specifically described below.

[0059] S121. Determine multiple fingerprint blank areas of the fingerprint optical image according to the fingerprint optical image through the blank feature recognition model, adjust the brightness and contrast of each fingerprint blank area and perform post-filtering processing, perform binarization processing on each fingerprint blank area, and recognize fine line patterns in each fingerprint blank area through wavelet transform.

[0060] Figure 4 This is a schematic diagram of processing a blank area of ​​a fingerprint using the method in an embodiment of the present application. Figure 4 As shown, when the method in the embodiment of the present application is working, a plurality of fingerprint blank areas of the fingerprint optical image can be determined according to the fingerprint optical image through the blank feature recognition model, the brightness and contrast of each fingerprint blank area are adjusted and filtered, and each fingerprint blank area is binarized, and the fine line pattern in each fingerprint blank area is identified through wavelet transform to identify the fingerprint lines in the fingerprint blank area.

[0061] For example, Figure 4 As shown in Figure a, for Figure 4 The fingerprint blank area in the rectangular frame in Figure a can be enhanced by the above method to achieve the recognition accuracy of the fingerprint line in the fingerprint blank area.

[0062] For example, Figure 4As shown in Figure b, by performing image enhancement using the above method, the fingerprint line in the blank area of ​​the fingerprint can be identified, and then whether the blank area is a real fingerprint can be judged based on the fingerprint line in the blank area of ​​the fingerprint.

[0063] S122, determining a fingerprint blank feature according to the number and area of ​​the plurality of fingerprint blank areas and a fine line pattern in each fingerprint blank area, and determining a second forgery probability corresponding to the fingerprint optical image according to the fingerprint blank feature.

[0064] Since the blank area of ​​a real fingerprint is often caused by insufficient fingerprint pressing force, there are often tiny fingerprint lines in the blank area of ​​a real fingerprint; while forged fingerprints are often caused by defects in the forged fingerprint production process, so there are often no fingerprint lines in the blank area of ​​a forged fingerprint.

[0065] Based on the above reasons, when performing forged fingerprint recognition, the fingerprint blank feature can be determined based on the number and area of ​​multiple fingerprint blank areas and the fine line pattern in each fingerprint blank area, and the second forgery probability corresponding to the fingerprint optical image can be determined based on the fingerprint blank feature, thereby realizing the judgment of the forged fingerprint in combination with the fine line pattern in each fingerprint blank area, thereby improving the recognition probability of the forged fingerprint.

[0066] The beneficial effect of the above implementation is that the forged fingerprint is judged in combination with the fine line pattern in the blank area of ​​each fingerprint, thereby improving the recognition probability of the forged fingerprint.

[0067] The beneficial effect of the above-mentioned implementation method is that the fingerprint blank characteristics are determined according to the number and area of ​​multiple fingerprint blank areas and the fine lines pattern in each fingerprint blank area, and the fingerprint as a whole can be combined with the fine lines in each fingerprint blank area to identify the forged fingerprint, thereby improving the accuracy of forged fingerprint identification.

[0068] In some implementations, the above method further includes S210 to S220, and S210 to S220 are described in detail below.

[0069] S210, identifying fingerprint connection areas of adjacent fingerprint lines of the fingerprint optical image around each fingerprint blank area of ​​the fingerprint optical image, and determining fingerprint connection features of the fingerprint optical image according to the fingerprint blank area and the fingerprint connection areas around the fingerprint blank area through a fingerprint connection recognition model, and determining a fifth forgery probability corresponding to the fingerprint optical image according to the fingerprint connection features.

[0070] Figure 5 This is a schematic diagram of identifying the fingerprint connection area using the method in the embodiment of the present application, such as Figure 5As shown, since a connection area is often generated around a blank defect when a forged fingerprint is produced, when identifying a forged fingerprint, a fingerprint connection area of ​​adjacent fingerprint lines of the fingerprint optical image can be identified around each fingerprint blank area in the fingerprint optical image. The adjacent fingerprint lines around each fingerprint blank area often cause the fingerprint to produce a connected area due to the pressing in the production of the forged fingerprint. Therefore, the forged fingerprint can be identified through the adjacent fingerprint lines around each fingerprint blank area.

[0071] After determining the adjacent fingerprint lines around each fingerprint blank area, the fingerprint connection feature of the fingerprint optical image can be determined according to the fingerprint blank area and the fingerprint connection area around the fingerprint blank area through the fingerprint connection recognition model, and the fifth forgery probability corresponding to the fingerprint optical image can be determined according to the fingerprint connection feature. The fifth forgery probability represents the probability of judging that the fingerprint is a forged fingerprint through the connection area around the fingerprint blank area.

[0072] Exemplarily, when the fingerprint connection feature of the fingerprint optical image is determined based on the fingerprint blank area and the fingerprint connection area around the fingerprint blank area, the fingerprint connection feature of the fingerprint optical image can be determined based on all the fingerprint blank areas and the fingerprint connection area around each fingerprint blank area.

[0073] S220: When the first forgery probability is less than the preset first forgery probability and the fifth forgery probability is greater than or equal to the preset fifth forgery probability, or when the first forgery probability is greater than or equal to the preset third forgery probability and the fifth forgery probability is greater than or equal to the preset sixth forgery probability, it is determined that the fingerprint corresponding to the fingerprint optical image is a forged fingerprint, wherein the preset sixth forgery probability is less than the preset fifth forgery probability.

[0074] When performing forged fingerprint identification, when the first forgery probability is less than the preset first forgery probability, and when the fifth forgery probability is greater than or equal to the preset fifth forgery probability, it means that the probability of judging the fingerprint as a forged fingerprint through the fingerprint boundary features of the fingerprint optical image is low, while the probability of judging the fingerprint as a forged fingerprint through the connection area around the blank area of ​​the fingerprint is high, and thus the fingerprint corresponding to the fingerprint optical image can be judged as a forged fingerprint, thereby achieving accurate identification of the forged fingerprint.

[0075] When performing forged fingerprint identification, when the first forgery probability is greater than or equal to the preset third forgery probability, and when the fifth forgery probability is greater than or equal to the preset sixth forgery probability, the preset sixth forgery probability is less than the preset fifth forgery probability, indicating that the first forgery probability obtained based on the fingerprint boundary feature and the fifth forgery probability obtained based on the fingerprint blank feature are both within a larger numerical range, and neither can be judged as a forged fingerprint based on the first forgery probability and the fifth forgery probability alone. The fingerprint corresponding to the fingerprint optical image can be judged as a forged fingerprint based on the first forgery probability and the fifth forgery probability, which can ensure the recognition accuracy of forged fingerprints and avoid missed detection.

[0076] The beneficial effect of the above implementation method is that when the probability of judging a fingerprint as a forged fingerprint by the fingerprint boundary features of the fingerprint optical image is low, and when the probability of judging a fingerprint as a forged fingerprint by the connection area around the blank area of ​​the fingerprint is high, the fingerprint corresponding to the fingerprint optical image can be judged as a forged fingerprint, thereby ensuring the recognition accuracy of forged fingerprints.

[0077] The beneficial effect of the above implementation method is that when the fingerprint cannot be judged as a forged fingerprint based on the first forgery probability and the fifth forgery probability alone, the fingerprint corresponding to the fingerprint optical image can be judged as a forged fingerprint based on the first forgery probability and the fifth forgery probability, thereby ensuring the recognition accuracy of the forged fingerprint.

[0078] In some implementations, the method further includes: determining a first number of fingerprint lines connected to each fingerprint connection area, and determining a second number of fingerprint lines intersecting each fingerprint blank area, and determining a ratio of the first number to the second number as a fingerprint connection area adjustment factor, and adjusting the fifth forgery probability by multiplying the fingerprint connection area adjustment factor on the fifth forgery probability.

[0079] When forged fingerprints are made, the fingerprint lines around the forged fingerprints are often connected due to the production process. However, clean and real fingerprints often do not have fingerprint lines connected around the blank area. Therefore, when performing forged fingerprint recognition, Figure 5 As shown, the first number of fingerprint lines connected to each fingerprint connection area can be determined. The first number represents the number of fingerprint lines connected by each fingerprint connection area. The larger the first number, the higher the possibility that the fingerprint is a forged fingerprint.

[0080] When performing forged fingerprint recognition, Figure 5 As shown, the second number of fingerprint lines intersecting each fingerprint blank area can be determined, and the second number represents the number of fingerprint lines spanned by the fingerprint blank area. The larger the second number is, the more fingerprint lines are affected by the fingerprint blank area.

[0081] After obtaining the first number and the second number, the ratio of the first number to the second number can be determined as a fingerprint connection area adjustment factor. The fingerprint connection area adjustment factor represents the ratio of the connection between fingerprint lines. Then, the probability of whether the fingerprint is a forged fingerprint can be evaluated by the fingerprint connection area adjustment factor.

[0082] After obtaining the fingerprint connection area adjustment factor, the fifth forgery probability can be adjusted by multiplying the fingerprint connection area adjustment factor on the fifth forgery probability to achieve adjustment of the fifth forgery probability, and then forged fingerprint detection can be performed based on the adjusted fifth fingerprint forgery probability.

[0083] For example, when determining the first number of fingerprint lines connected to each fingerprint connection area, an edge detection algorithm (such as Canny edge detection) can be used on the binary image to extract the contours of the fingerprint lines, and the places where the fingerprint lines in each fingerprint connection area intersect or bifurcate can be identified, thereby realizing the identification of the first number of fingerprint lines connected to each fingerprint connection area.

[0084] The beneficial effect of the above implementation method is that due to the manufacturing process, the fingerprint lines around the forged fingerprint may be connected, and the fingerprint forgery probability can be evaluated according to the connection status of the fingerprint lines connected to each fingerprint connection area, thereby improving the recognition accuracy of the forged fingerprint.

[0085] The beneficial effect of the above implementation method is also to determine the first number of fingerprint lines connected to each fingerprint connection area, and determine the second number of fingerprint lines intersecting with each fingerprint blank area, and determine the ratio of the first number to the second number as the fingerprint connection area adjustment factor, and the fifth forgery probability can be adjusted according to the fingerprint connection area adjustment factor, thereby further improving the accuracy of forged fingerprint recognition.

[0086] In some implementations, the above method also includes: determining the completed fingerprint line of the fingerprint in each fingerprint blank area of ​​the fingerprint optical image through a region growing algorithm, and when the misalignment distance between the completed fingerprint line in at least one fingerprint blank area and the blank fingerprint lines around the fingerprint blank area is greater than a preset misalignment distance, determining that the first forgery probability is greater than or equal to the preset first forgery probability.

[0087] When forged fingerprints are produced, the fingerprint lines of the forged fingerprints are often misaligned on both sides of the blank area of ​​the fingerprint due to reasons of the production process. The forged fingerprint can then be identified by identifying the features of the fingerprint lines being misaligned on both sides of the blank area of ​​the fingerprint.

[0088] When identifying the features of a forged fingerprint in which the fingerprint line is misplaced on both sides of a blank area of ​​the fingerprint, the complementary fingerprint line of the fingerprint can be determined in each blank area of ​​the fingerprint optical image through a region growing algorithm, and the complementary fingerprint line is based on the estimated fingerprint line position.

[0089] Exemplarily, when determining the completed fingerprint line of the fingerprint in each fingerprint blank area of ​​the fingerprint optical image, the fingerprint line can be completed from one side of each fingerprint blank area to the fingerprint blank area through a region growing algorithm to obtain the completed fingerprint line in the fingerprint blank area.

[0090] After the completed fingerprint lines in the fingerprint blank area are obtained, the corresponding relationships of the fingerprint lines can be determined one by one from one end to the other end of the fingerprint blank area according to the corresponding relationships of the fingerprint lines.

[0091] After obtaining the completed fingerprint line in the blank area of ​​the fingerprint, when the misalignment distance between at least one completed fingerprint line in the blank area of ​​the fingerprint and the blank fingerprint lines around the blank area of ​​the fingerprint is greater than the preset misalignment distance, it means that the misalignment amplitude between the completed fingerprint line and the fingerprint lines around the blank area of ​​the fingerprint is too large, and then it can be determined that the first forgery probability is greater than or equal to the preset first forgery probability, and then the fingerprint corresponding to the fingerprint optical image can be judged as a forged fingerprint according to the first forged fingerprint probability.

[0092] Exemplarily, the preset misalignment distance may be 1.5 to 2 times the distance between adjacent fingerprint lines closest to the fingerprint line causing the misalignment.

[0093] The beneficial effect of the above implementation is that the recognition accuracy of the forged fingerprint can be further improved by recognizing the features of the fingerprint line of the forged fingerprint that is misaligned on both sides of the blank area of ​​the fingerprint.

[0094] The beneficial effect of the above implementation method is that, through the region growing algorithm, the completed fingerprint line of the fingerprint is determined in each fingerprint blank area of ​​the fingerprint optical image, and the forged fingerprint is judged based on the completed fingerprint line, thereby ensuring the recognition efficiency and accuracy of the forged fingerprint.

[0095] In some implementations, the method further includes: determining, according to the fingerprint optical image, the number of fingerprint intersections and the total number of fingerprint lines of the fingerprint optical image through a fingerprint line intersection recognition algorithm, and determining a ratio of the number of fingerprint line intersections to the total number of fingerprint lines as a fingerprint intersection area adjustment factor, and adjusting the fifth forgery probability by multiplying the fifth forgery probability by the fingerprint connection area adjustment factor and the fingerprint intersection area adjustment factor.

[0096] Forged fingerprints often overlap due to the manufacturing process, so forged fingerprints can be identified based on the features of the overlap between fingerprints.

[0097] Figure 6 This is a schematic diagram of identifying the intersection state of fingerprints using the method in the embodiment of the present application. Figure 6 As shown in the rectangular box area in , when identifying a forged fingerprint based on the fingerprint intersection feature, the fingerprint line intersection recognition algorithm can be used to determine the fingerprint intersection number and the total number of fingerprint lines in the fingerprint optical image based on the fingerprint optical image. The fingerprint intersection number and the total number of fingerprint lines represent the state of the fingerprint lines intersecting.

[0098] After obtaining the number of fingerprint intersections and the total number of fingerprint lines, the ratio of the number of fingerprint line intersections to the total number of fingerprint lines can be determined as a fingerprint intersection area adjustment factor. The fingerprint intersection area adjustment factor represents the proportion of fingerprint lines that produce fingerprint intersections in all fingerprints.

[0099] After obtaining the fingerprint connection area adjustment factor, the fifth forgery probability can be adjusted by multiplying the fingerprint connection area adjustment factor and the fingerprint intersection area adjustment factor, thereby adjusting the fifth forgery probability of forged fingerprint identification according to the characteristics of the fingerprint connection area and the characteristics of the fingerprint intersection area, and further improving the accuracy of forged fingerprint identification.

[0100] For example, the fingerprint line intersection recognition algorithm can use the edge detection algorithm to extract the contour of the fingerprint line and refine the extracted edge to make the fingerprint line thinner and continuous to facilitate subsequent intersection detection. After obtaining the fingerprint line, the connected component analysis can be used to identify the area where the fingerprint lines intersect, and the identified intersection areas can be counted to obtain the number of fingerprint line intersections.

[0101] For example, the total number of fingerprint lines can be counted by analyzing the number of pixels or the length of the fingerprint lines. Specifically, the fingerprint lines can be detected using Hough Transform.

[0102] The beneficial effect of the above implementation is that when forged fingerprints are crossed due to the manufacturing process, the forged fingerprints can be identified with high precision by identifying the crossing features between the fingerprints.

[0103] The beneficial effect of the above implementation method is that the ratio of the number of fingerprint line intersections to the total number of fingerprint lines can be determined as a fingerprint intersection area adjustment factor, and the fingerprint intersection area adjustment factor is used to judge the forged fingerprint, thereby ensuring the recognition accuracy of the forged fingerprint.

[0104] The beneficial effect of the above-mentioned implementation method is that after obtaining the fingerprint intersection area adjustment factor, the fifth forgery probability is adjusted by multiplying the fingerprint connection area adjustment factor and the fingerprint intersection area adjustment factor on the fifth forgery probability, and the forged fingerprint is comprehensively judged by combining the above-mentioned fingerprint connection area adjustment factor and fingerprint intersection area adjustment factor, thereby ensuring the recognition accuracy of forged fingerprints and avoiding false detection.

[0105] An embodiment of the present application also provides a fingerprint unlocking device based on forged fingerprint feature recognition, comprising a unit for executing any of the methods described above.

[0106] Figure 7 A schematic diagram of the logical structure of a fingerprint unlocking device based on forged fingerprint feature recognition provided by an embodiment of the present application is shown in FIG. Figure 7 As shown, the device 1 of this embodiment includes a processing unit 11, a storage unit 12 and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12 and the transceiver unit 13 cooperate with each other to implement the above method. The beneficial effects of the embodiment of the present application have been described in the above method and will not be repeated here.

[0107] An embodiment of the present application also provides a fingerprint unlocking device based on forged fingerprint feature recognition, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.

[0108] Figure 8 A schematic diagram of the physical structure of a fingerprint unlocking device based on forged fingerprint feature recognition provided by an embodiment of the present application, such as Figure 8 As shown, the device 2 of this embodiment includes: at least one processor 20 ( Figure 8 Only one processor 20 is shown in the figure), a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20. When the processor 20 executes the computer program 22, the steps in any of the above-mentioned method embodiments are implemented. The beneficial effects of the embodiments of the present application have been described in the above-mentioned methods and will not be repeated here.

[0109] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0110] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0111] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0112] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0113] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0114] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0115] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0116] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0118] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A fingerprint unlocking method based on forged fingerprint feature recognition, characterized in that: The method comprises: Acquire a fingerprint optical image acquired by an optical fingerprint unlocking component; Determine the fingerprint boundary feature of the fingerprint optical image according to the fingerprint optical image through the fingerprint boundary feature recognition model, and determine the first forgery probability corresponding to the fingerprint optical image according to the fingerprint boundary feature; determine the fingerprint blank feature of the fingerprint optical image according to the fingerprint optical image through the blank feature recognition model, and determine the second forgery probability corresponding to the fingerprint optical image according to the fingerprint blank feature; When the first forgery probability is greater than or equal to the preset first forgery probability, or when the first forgery probability is less than the preset first forgery probability and when the second forgery probability is greater than or equal to the preset second forgery probability, or when the first forgery probability is greater than or equal to the preset third forgery probability and when the second forgery probability is greater than or equal to the preset fourth forgery probability, the fingerprint corresponding to the fingerprint optical image is determined to be a forged fingerprint; wherein the preset third forgery probability is less than the preset first forgery probability, and the preset fourth forgery probability is less than the preset second forgery probability.

2. The method according to claim 1, characterized in that The fingerprint boundary features include the boundary features corresponding to the concave-convex, incomplete and sharp boundaries of the fingerprint optical image, and the fingerprint blank features include the fingerprint blank features corresponding to the number and area of ​​the fingerprint blank areas of the fingerprint optical image.

3. The method according to claim 2, characterized in that Determining a fingerprint blank feature of the fingerprint optical image according to the fingerprint optical image through a blank feature recognition model, and determining a second forgery probability corresponding to the fingerprint optical image according to the fingerprint blank feature, including: Through the blank feature recognition model, multiple fingerprint blank areas of the fingerprint optical image are determined according to the fingerprint optical image, the brightness and contrast of each fingerprint blank area are adjusted and filtered, and each fingerprint blank area is binarized, and the fine line pattern in each fingerprint blank area is identified through wavelet transform; The fingerprint blank feature is determined according to the number and area of ​​the plurality of fingerprint blank areas and the fine line pattern in each fingerprint blank area, and the second forgery probability corresponding to the fingerprint optical image is determined according to the fingerprint blank feature.

4. The method according to claim 3, characterized in that The method further comprises: Identify fingerprint connection areas of adjacent fingerprint lines of the fingerprint optical image around each fingerprint blank area of ​​the fingerprint optical image, and determine fingerprint connection features of the fingerprint optical image according to the fingerprint blank area and the fingerprint connection areas around the fingerprint blank area through a fingerprint connection recognition model, and determine a fifth forgery probability corresponding to the fingerprint optical image according to the fingerprint connection features; When the first forgery probability is less than the preset first forgery probability and when the fifth forgery probability is greater than or equal to the preset fifth forgery probability, or when the first forgery probability is greater than or equal to the preset third forgery probability and when the fifth forgery probability is greater than or equal to the preset sixth forgery probability, the fingerprint corresponding to the fingerprint optical image is determined to be a forged fingerprint; wherein the preset sixth forgery probability is less than the preset fifth forgery probability.

5. The method according to claim 4, characterized in that The method further comprises: Determine a first number of fingerprint lines connected to each fingerprint connection area, determine a second number of fingerprint lines intersecting each fingerprint blank area, and determine a ratio of the first number to the second number as a fingerprint connection area adjustment factor, and multiply the fifth forgery probability by the fingerprint connection area adjustment factor to adjust the fifth forgery probability.

6. The method according to claim 5, characterized in that The method further comprises: The completed fingerprint line of the fingerprint is determined in each fingerprint blank area of ​​the fingerprint optical image by using a region growing algorithm. When the misalignment distance between the completed fingerprint line in at least one fingerprint blank area and the blank fingerprint lines around the fingerprint blank area is greater than a preset misalignment distance, it is determined that the first forgery probability is greater than or equal to the preset first forgery probability.

7. A fingerprint unlocking device based on forged fingerprint feature recognition, characterized in that: Comprising means for performing the method according to any one of claims 1 to 6.

8. A fingerprint unlocking device based on forged fingerprint feature recognition, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images