Anti-interference fingerprint recognition method, device, system and storage medium

Abstract

The present invention provides an interference-resistant fingerprint recognition method, device, system, and storage medium, wherein the method comprises: obtaining user fingerprint information according to a pressing instruction; determining a clear area and a fuzzy area; filtering the pre-recorded data in the database to remove the area corresponding to the fuzzy area, obtaining first filtering information corresponding to each pre-recorded data; and identifying the user fingerprint information according to the first filtering information. The present invention distinguishes the user fingerprint information into clear areas that can be identified and fuzzy areas that cannot be identified or have low identification accuracy, and filters out the location information of the fuzzy areas from all pre-recorded data in the database, and then compares the clear areas with the remaining first filtering information to identify the fingerprint, thereby greatly improving the recognition efficiency and recognition time, avoiding the influence of interference factors such as stains and water stains on fingerprint recognition, and improving the user experience.

Description

Technical Field

[0001] The present invention relates to the field of fingerprint recognition, and more particularly to an anti-interference fingerprint recognition method, device, system and storage medium. Background Art

[0002] Fingerprint recognition is the process of classifying and comparing the fingerprints of an object to identify it. As one of the biometric identification technologies, fingerprint recognition technology has gradually matured in the new century and has entered the field of human production and life.

[0003] However, in actual applications, fingerprint recognition technology can be disrupted by stains or water on the fingerprint surface or the recognition device. The fingerprint recognition area and the finger must be wiped clean before recognition can resume. This reduces recognition accuracy, prolongs the time required to identify a single user, decreases recognition efficiency, and creates a poor user experience. Summary of the Invention

[0004] In view of this, the present invention provides an anti-interference fingerprint recognition method, comprising:

[0005] Acquiring fingerprint information of the current user according to a pressing instruction of the current user;

[0006] Determining a clear area and a fuzzy area different from the clear area in the acquired user fingerprint information, wherein the user fingerprint information is composed of the clear area and the fuzzy area;

[0007] Based on the fuzzy area, filtering the pre-recorded data in the database except for the area at the corresponding position of the fuzzy area, to obtain first filtering information corresponding to each pre-recorded data;

[0008] The user fingerprint information is identified according to the first filtering information.

[0009] Preferably, identifying the user fingerprint information according to the first filtering information includes:

[0010] comparing the clear area in the user fingerprint information with each of the first filtered information in the database;

[0011] If there is first filtering information in the database whose matching degree with the clear area reaches a first preset matching degree, the pre-recorded data corresponding to the first filtering information that reaches the first preset matching degree is used as the target data corresponding to the user fingerprint information, and the user fingerprint information is identified based on the target data;

[0012] Preferably, the first preset matching degree is not less than 80%.

[0013] Preferably, identifying the user fingerprint information according to the target data includes:

[0014] Clarifying the fuzzy area in the user fingerprint information to obtain identifiable data;

[0015] Filtering the target data to remove a portion having the same position and size as and corresponding to the clear area to obtain second filtered information;

[0016] comparing the identifiable data with the second filtered information;

[0017] If the matching degree reaches the second preset matching degree, the comparison is determined to be successful;

[0018] Preferably, the second preset matching degree is 95%.

[0019] Preferably, after comparing the identifiable data with the second filtering information, the method further includes:

[0020] If the matching degree is less than the second preset matching degree, the comparison is determined to have failed, a prompt message for re-acquiring the fingerprint is generated, and the process returns to the step of acquiring the user's fingerprint information according to the pressing instruction.

[0021] Preferably, respectively obtaining the number of times the clear area and the fuzzy area are recognized corresponding to the current user;

[0022] If the number of times the clear area and the fuzzy area are recognized reaches the preset number, and the last comparison between the identifiable data and the second filtered information does not result in a comparison failure, it is determined that the recognition has failed;

[0023] Preferably, the preset number of times is not less than 5 times.

[0024] Preferably, the step of clarifying the fuzzy area in the user fingerprint information to obtain identifiable data includes:

[0025] The fuzzy area is processed based on a pre-trained neural network processing model to obtain the recognizable data.

[0026] Preferably, the processing of the fuzzy region based on a pre-trained neural network processing model to obtain the identifiable data includes:

[0027] Performing homomorphic filtering on the fuzzy area using the neural network processing model to obtain the identifiable data;

[0028] Preferably, the performing homomorphic filtering processing on the fuzzy area using the neural network processing model to obtain the identifiable data includes:

[0029] Taking logarithms and Fourier transforming the image of the blurred area and its illumination component and reflection component into frequencies respectively;

[0030] After filtering by the filter, it is Fourier transformed into the spatial domain to obtain the recognizable data after homomorphic filtering.

[0031] In addition, to solve the above problems, the present invention also provides an anti-interference fingerprint recognition device, comprising:

[0032] An acquisition module, configured to acquire fingerprint information of a current user according to a pressing instruction of the current user;

[0033] a determination module, configured to determine a clear area and a fuzzy area different from the clear area in the acquired user fingerprint information; the user fingerprint information is composed of the clear area and the fuzzy area;

[0034] a filtering module configured to filter the pre-recorded data in the database, based on the fuzzy area, by excluding an area corresponding to the fuzzy area, to obtain first filtering information corresponding to each pre-recorded data;

[0035] An identification module is used to identify the user fingerprint information according to the first filtering information.

[0036] In addition, to solve the above problems, the present invention also provides an anti-interference fingerprint recognition system, including a memory and a processor, wherein the memory stores an anti-interference fingerprint recognition program, and the processor runs the anti-interference fingerprint recognition program to enable the anti-interference fingerprint recognition system to perform the anti-interference fingerprint recognition method as described above.

[0037] In addition, to solve the above problems, the present invention also provides a computer-readable storage medium, on which an anti-interference fingerprint recognition program is stored. When the anti-interference fingerprint recognition program is executed by a processor, the anti-interference fingerprint recognition method as described above is implemented.

[0038] The present invention provides an interference-resistant fingerprint recognition method, device, system, and storage medium, wherein the method comprises: obtaining user fingerprint information of the current user according to a pressing instruction of the current user; determining a clear area and a fuzzy area different from the clear area in the obtained user fingerprint information; the user fingerprint information is composed of the clear area and the fuzzy area; based on the fuzzy area, filtering the pre-recorded data in the database to remove the area corresponding to the fuzzy area to obtain first filtering information corresponding to each pre-recorded data; and identifying the user fingerprint information according to the first filtering information. The present invention distinguishes user fingerprint information into clear areas that can be identified and fuzzy areas that cannot be identified or have low identification accuracy, and filters all pre-recorded data in the database to remove the location information of the fuzzy areas, and then compares the clear areas with the remaining first filtering information to identify the fingerprint, thereby greatly improving the recognition efficiency and recognition time, avoiding the influence of interference factors such as stains and water stains on fingerprint recognition, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram of the hardware operating environment involved in the embodiment of the anti-interference fingerprint recognition method of the present invention;

[0040] Figure 2 Schematic diagram of the flow of the first embodiment of the anti-interference fingerprint recognition method of the present invention;

[0041] Figure 3 Schematic diagram of a detailed flow chart of step S400 in the second embodiment of the anti-interference fingerprint recognition method of the present invention;

[0042] Figure 4 4 is a flow chart of the detailed description of step S420 in the third embodiment of the anti-interference fingerprint recognition method of the present invention;

[0043] Figure 5 This is a schematic diagram of a detailed flowchart of step S4211a in the fourth embodiment of the anti-interference fingerprint recognition method of the present invention;

[0044] Figure 6 A fingerprint diagram of the overall process of the anti-interference fingerprint recognition method of the present invention and a schematic diagram of each recognition process;

[0045] Figure 7 This is a schematic diagram of module connections of the anti-interference fingerprint recognition device of the present invention.

[0046] Reference numerals:

[0047] 1. User fingerprint information; 11. Clear area; 12. Blurred area; 13. Recognizable data; 2. Pre-recorded information; 21. First filtered information; 22. Second filtered information.

[0048] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0049] The embodiments of the present invention are described in detail below, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions.

[0050] Furthermore, 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 identified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0051] In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "connect," "fixed," etc. should be understood broadly. For example, they may refer to fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0052] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] like Figure 1 , which is a schematic diagram of the structure of the hardware operating environment of the terminal involved in the embodiment of the present invention.

[0054] The anti-interference fingerprint recognition system of an embodiment of the present invention can be a PC, or a mobile terminal device such as a smartphone, tablet computer, or laptop computer. The anti-interference fingerprint recognition system may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen, an input unit such as a keyboard, or a remote control. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory or a stable memory such as a disk storage device. The memory 1005 may also be a storage device independent of the aforementioned processor 1001. Optionally, the anti-interference fingerprint recognition system may also include RF (Radio Frequency) circuits, audio circuits, a Wi-Fi module, and the like. In addition, the anti-interference fingerprint recognition system can also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, etc., which will not be described here.

[0055] Those skilled in the art will understand that Figure 1 The anti-interference fingerprint recognition system shown in the figure does not constitute a limitation thereof, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a data interface control program, a network connection program, and an anti-interference fingerprint recognition program.

[0056] Example 1:

[0057] Reference Figure 2 The first embodiment of the present invention provides an anti-interference fingerprint recognition method, comprising:

[0058] Step S100, acquiring user fingerprint information of the current user according to a pressing instruction of the current user;

[0059] As mentioned above, the fingerprint recognition device can be used to identify the unique identity of the user, compare the user's fingerprint information and fingerprint image with the pre-recorded data stored in the database, and after matching the corresponding user information, match the user information with the user, thereby determining the user information of the user.

[0060] As mentioned above, when the user performs fingerprint recognition, he or she first needs to make a fingerprint impression on the fingerprint recognition device, and place the fingerprint of the finger to be recognized toward the recognition area of ​​the recognition device for impression.

[0061] As mentioned above, during fingerprint recognition, after the user places the corresponding finger on the designated area of ​​the recognition device, the recognition device obtains or receives the corresponding fingerprint recognition press instruction and prompts to start the fingerprint recognition process.

[0062] In the above, according to the pressing instruction, the fingerprint of the current user is acquired, thereby obtaining the corresponding user fingerprint information.

[0063] The user fingerprint information mentioned above may include but is not limited to image data information collected from the user fingerprint and corresponding feature data.

[0064] Step S200, determining a clear area and a fuzzy area different from the clear area in the acquired user fingerprint information; the user fingerprint information is composed of the clear area and the fuzzy area;

[0065] During fingerprint recognition, if the user's fingerprint information is contaminated by dirt or water, it will cause some blurred areas. When there is interference, a fingerprint information consists of two parts:

[0066] 1. Clear area, which is the area that can be identified;

[0067] 2. Blurred areas are areas where the acquired user fingerprint information cannot be recognized or the recognition accuracy is reduced due to obstruction caused by stains and water stains.

[0068] The combination of clear area and fuzzy area constitutes the overall user fingerprint information.

[0069] Step S300: Based on the fuzzy area, filter the pre-recorded data in the database to remove the area corresponding to the fuzzy area, and obtain first filtering information corresponding to each pre-recorded data;

[0070] As mentioned above, the database stores all pre-stored fingerprints of users, which are pre-recorded data.

[0071] The blurred and clear areas both have boundaries, and the boundaries are connected. Specifically, edge detection or neural network recognition can be used to determine the boundaries of each area. Then, using the outer boundary of the blurred area as the boundary, based on the coordinates of the blurred area in the corresponding user fingerprint information, the area corresponding to the pre-recorded data in the database is removed, and the area corresponding to the clear area is retained.

[0072] Step S400: Identify the user fingerprint information according to the first filtering information.

[0073] After obtaining the position area corresponding to the blurred area, the first filtering information corresponding to all pre-recorded information in the database is obtained, and then the first filtering information is compared with the user fingerprint information to determine the user identity.

[0074] This embodiment distinguishes user fingerprint information into clear areas that can be identified and fuzzy areas that cannot be identified or have low identification accuracy, filters out the location information of the fuzzy areas from all pre-recorded data in the database, and then compares the clear areas with the remaining first filtered information to identify the fingerprint, thereby greatly improving the recognition efficiency and recognition time, avoiding the influence of interference factors such as stains and water stains on fingerprint recognition, and improving the user experience.

[0075] Example 2:

[0076] Reference Figure 3 The second embodiment of the present invention provides an anti-interference fingerprint recognition method. Based on the above-mentioned embodiment 1, the step S400 of identifying the user fingerprint information according to the first filtering information includes:

[0077] Step S410, comparing the clear area in the user fingerprint information with each of the first filtered information in the database;

[0078] In the above, the first filtered information is pre-recorded information that has been pre-processed.

[0079] The pre-processing mentioned above is to filter out the corresponding position information of the fuzzy area that cannot be identified or has a low recognition accuracy, and the pre-recorded information in the remaining area is the first filtered information.

[0080] As mentioned above, the clear area and the first filtered information can be equal in size, area, and identifiable area. Therefore, by comparing them with all the first filtered information in the pre-recorded information, the corresponding uniqueness of the fingerprint in the area can be further known.

[0081] Step S420: If there is first filtering information in the database whose matching degree with the clear area reaches a first preset matching degree (C1), the pre-recorded data corresponding to the first filtering information that reaches the first preset matching degree is used as target data corresponding to the user fingerprint information, and the user fingerprint information is identified based on the target data;

[0082] Furthermore, the first preset matching degree is not less than 80% (preferably, it can be 80%, that is, C1=80%).

[0083] The matching degree mentioned above can be similarity, and the comparison method can be a distance method. Euclidean distance is a simple method for measuring two feature matrices. For example, the similarity of the feature matrices is calculated by the difference between the elements at corresponding positions. Using this method, the similarity described by Euclidean distance is more accurate.

[0084] In the above, preferably, the first preset matching degree is a preset similarity threshold, which may be 80%.

[0085] In this embodiment, by filtering out the corresponding position corresponding to the fuzzy area from each pre-recorded information in the database, the remaining first filtered information is compared with the clear area, thereby greatly reducing the overall data calculation amount of the comparison and improving the recognition efficiency.

[0086] Example 3:

[0087] Reference Figure 4 The third embodiment of the present invention provides an anti-interference fingerprint recognition method. Based on the above embodiment 1, further, in step S420, identifying the user fingerprint information according to the target data includes:

[0088] Step S421, clarifying the fuzzy area in the user fingerprint information to obtain identifiable data;

[0089] In a further solution, if only the clear area is compared, and the clear area is small, there is a certain probability of inaccurate comparison.

[0090] In order to improve the accuracy, in this embodiment, the fuzzy area is clarified so as to perform further comparison.

[0091] The fuzzy area can be clarified by, for example, increasing contrast, increasing color or adjusting brightness, which is helpful to improve the blur or unclear situation of the image caused by stains or water stains.

[0092] As described above, when performing clarity, the blurred area can be processed by image processing means to obtain corresponding recognizable data.

[0093] Step S422: filtering out the target data from a portion having the same position and size as and corresponding to the clear area to obtain second filtered information;

[0094] Accordingly, in order to further identify the identifiable data, it is necessary to remove the other areas other than the identifiable data area from the data to be compared, that is, the information of the corresponding position of the clear area, whose size and position are the same as the size and position of the clear area.

[0095] Step S423, comparing the identifiable data with the second filtering information;

[0096] Step S424: If the matching degree reaches a second preset matching degree (C2), the comparison is determined to be successful;

[0097] Preferably, the second preset matching degree is 95%. (C1=95%)

[0098] As described above, the pre-recorded information in the database is obtained by removing the corresponding part of each data, thereby obtaining a corresponding part that does not contain the same position and size as the clear area, and only the part corresponding to the fuzzy area is left, so as to compare the identifiable data of the fuzzy area with the second filtered information in the pre-recorded information. If the matching degree reaches the second preset matching degree, that is, it is above 95%, then it is determined that the fingerprint recognition comparison is successful and matches the pre-recorded information.

[0099] In this embodiment, after comparing the clear area with the first filtered information corresponding to all pre-recorded information in the database, if the pre-recorded information with a matching degree of more than 80% is screened out, in order to further improve the accuracy, the fuzzy area is clarified and then compared with the second filtered information after filtering out the position information corresponding to the fuzzy area from the pre-recorded information. If the second preset matching degree is reached, the comparison is determined to be successful. On the one hand, the irrelevant position information corresponding to the fuzzy area is removed, and only the corresponding area is compared, which reduces the system's computational complexity. On the other hand, the two-step comparison, comparing the clear area and the fuzzy area respectively, greatly improves the overall recognition accuracy.

[0100] Furthermore, after comparing the identifiable data with the second filtering information in step S423, the following steps may be further performed:

[0101] Step S425: If the matching degree is less than the second preset matching degree, the comparison is determined to be failed, a prompt message for re-acquiring the fingerprint is generated, and the process returns to the step of acquiring the user's fingerprint information according to the pressing instruction.

[0102] As mentioned above, if the matching degree does not reach the second preset matching degree, it means that the recognition cannot guarantee uniqueness and the accuracy does not meet this standard. If the comparison is determined to be failed, a prompt message for re-acquiring the fingerprint can be generated to allow the user to re-acquire the fingerprint and return to the initial step to re-acquire the user's fingerprint information and re-identify.

[0103] Furthermore, it also includes:

[0104] Step S500, respectively obtaining the recognition times of the clear area and the fuzzy area corresponding to the current user;

[0105] Repeatedly perform fingerprint recognition multiple times, each time performing recognition for the clear area and the blurred area respectively. After a comparison is performed in both steps, the number of recognitions is recorded.

[0106] Step S600: If the number of times the clear area and the fuzzy area are recognized reaches a preset number, and the last comparison between the identifiable data and the second filtered information does not result in a comparison failure, then it is determined that the recognition has failed;

[0107] The preset number of times is not less than 5 times.

[0108] If the current user has been identified five times, and the final comparison of the identifiable data (the fuzzy area) with the second filtered information still fails, the entire identification process is considered a failure, and the user has failed fingerprint identification. Limiting the number of times a user can be identified improves fingerprint identification efficiency, rather than requiring the user to continuously identify the user. If the number of times reaches a certain threshold, indicating that the user's fingerprint is not pre-recorded in the database, or that the device is significantly affected by water stains and cannot guarantee identification accuracy, it will be necessary to clean the device and then re-identify, or terminate the identification process.

[0109] Example 4:

[0110] A third embodiment of the present invention provides an anti-interference fingerprint recognition method. Based on the first embodiment, step S421 of clarifying the blurred area in the user fingerprint information to obtain recognizable data includes:

[0111] Step S4211: Process the fuzzy area based on a pre-trained neural network processing model to obtain the recognizable data.

[0112] Furthermore, the step S4211 processes the fuzzy region based on a pre-trained neural network processing model to obtain the identifiable data, including:

[0113] Step S4211a, performing homomorphic filtering processing on the fuzzy area using the neural network processing model to obtain the identifiable data;

[0114] As mentioned above, during fingerprint recognition, water stains appear on the surface of the fingerprint device, resulting in severe image environment interference on the acquired fingerprint image, haziness and blurriness in the image, and water stains causing a large deviation in the light refractive index and uneven illumination. Here, the image enhancement method is used to remove or reduce these severe interferences and improve the clarity of the image.

[0115] As mentioned above, homomorphic filtering is a frequency domain method that relies on the illumination and reflective film properties of the image to improve the image quality.

[0116] Preferably, reference Figure 5 The step S4211a, performing homomorphic filtering on the fuzzy area using the neural network processing model to obtain the identifiable data, includes:

[0117] Step S4211a-1, taking logarithms and Fourier transforming the image of the blurred area and its illumination component and reflection component to frequencies;

[0118] Assume that the illumination component of the blurred area image f(x,y) is L(x,y) and its reflection component is R(x,y), then the following formula is obtained: f(x,y) = L(x,y)R(x,y); (Formula 1)

[0119] Among them, 0<L(x,y)<∞, 0<L(x,y)<1.

[0120] wherein the incident component is a representation of a slow spatial transformation and is associated with a low-frequency component;

[0121] The reflection component is a representation of fast spatial changes and is related to the high-frequency component.

[0122] In addition, in order to further improve the efficiency of the operation, in this embodiment, the logarithms of both sides of Formula 1 are taken, and then Fourier transform is performed to the frequency.

[0123] Step S4211a-2: After filtering through the filter, Fourier transform is performed to the spatial domain to obtain the recognizable data after homomorphic filtering.

[0124] Then, a suitable filter is selected for filtering, and then Fourier transform is performed to space to obtain the filtering effect of removing blur interference from the image.

[0125] The steps are:

[0126] Step 1. Take the logarithm of formula 1:

[0127] f1(x,y)=lnf(x,y)=lnL(x,y)+lnR(x,y)=L1(x,y)+R1(x,y);

[0128] Step 2: Perform Fourier transform:

[0129] F1(u,v)=FT(f1(x,y))=FT(L1(x,y))=FT(R1(x,y))=l1(x,y)+r1(x,y);

[0130] Step 3: Filtering:

[0131] G1(u,v)=H(u,v)F1(u,v)=H(u,v)l1(u,v)+H(u,v)r1(u,v);

[0132] Step 4: Inverse transform to the spatial domain:

[0133] g1(x, y) = FT -1 (G1(u,v));

[0134] Step 5. Get the index:

[0135] g(x, y)=exp(g1(x, y)).

[0136] In addition, in order to better illustrate the technical solutions of the embodiments provided in this application, refer to the attached Figure 6 , which is a brief flowchart of the anti-interference fingerprint recognition method provided in the embodiment.

[0137] In addition, reference Figure 7 The present invention also provides an anti-interference fingerprint recognition device, comprising:

[0138] An acquisition module 10 is configured to acquire fingerprint information of the current user according to a pressing instruction of the current user;

[0139] A determination module 20 is configured to determine a clear area and a fuzzy area different from the clear area in the acquired user fingerprint information; the user fingerprint information is composed of the clear area and the fuzzy area;

[0140] A filtering module 30 is configured to filter the pre-recorded data in the database, based on the fuzzy area, by removing the area corresponding to the fuzzy area, to obtain first filtering information corresponding to each pre-recorded data;

[0141] The identification module 40 is configured to identify the user fingerprint information according to the first filtering information.

[0142] In addition, the present invention also provides an anti-interference fingerprint recognition system, including a memory and a processor, wherein the memory stores an anti-interference fingerprint recognition program, and the processor runs the anti-interference fingerprint recognition program to enable the anti-interference fingerprint recognition system to perform the anti-interference fingerprint recognition method as described above.

[0143] In addition, the present invention also provides a computer-readable storage medium, on which an anti-interference fingerprint recognition program is stored. When the anti-interference fingerprint recognition program is executed by a processor, the anti-interference fingerprint recognition method as described above is implemented.

[0144] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0145] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, including a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention. The above is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, are similarly included in the patent protection scope of the present invention.

Claims

1. An anti-interference fingerprint recognition method, characterized in that: include: Acquiring fingerprint information of the current user according to a pressing instruction of the current user; Determining a clear area and a fuzzy area different from the clear area in the acquired user fingerprint information; The user fingerprint information consists of the clear area and the fuzzy area; Based on the fuzzy area, filtering the pre-recorded data in the database except for the area at the corresponding position of the fuzzy area, to obtain first filtering information corresponding to each pre-recorded data; Identifying the user fingerprint information according to the first filtering information includes: comparing the clear area in the user fingerprint information with each of the first filtered information in the database; If there is first filtering information in the database whose matching degree with the clear area reaches a first preset matching degree, the pre-recorded data corresponding to the first filtering information that reaches the first preset matching degree is used as the target data corresponding to the user fingerprint information, and the fuzzy area in the user fingerprint information is clarified to obtain recognizable data; Filtering the target data to remove a portion having the same position and size as and corresponding to the clear area to obtain second filtered information; comparing the identifiable data with the second filtered information; If the matching degree reaches the second preset matching degree, the comparison is determined to be successful.

2. The anti-interference fingerprint recognition method according to claim 1, wherein: The first preset matching degree is not less than 80%.

3. The anti-interference fingerprint recognition method according to claim 1, wherein: The second preset matching degree is 95%.

4. The anti-interference fingerprint recognition method according to claim 1, wherein: After comparing the identifiable data with the second filtering information, the method further includes: If the matching degree is less than the second preset matching degree, the comparison is determined to have failed, a prompt message for re-acquiring the fingerprint is generated, and the process returns to the step of acquiring the user's fingerprint information according to the pressing instruction.

5. The anti-interference fingerprint recognition method according to claim 4, characterized in that: Also includes: Obtaining the number of times the clear area and the fuzzy area corresponding to the current user are recognized respectively; If the number of times the clear area and the fuzzy area are recognized reaches a preset number, and the result of the last comparison between the identifiable data and the second filtered information does not fail, it is determined that the recognition has failed.

6. The anti-interference fingerprint recognition method according to claim 5, characterized in that: The range of the preset number of times is not less than 5 times.

7. The anti-interference fingerprint recognition method according to claim 1, wherein: The step of clarifying the fuzzy area in the user fingerprint information to obtain identifiable data includes: The fuzzy area is processed based on a pre-trained neural network processing model to obtain the recognizable data.

8. The anti-interference fingerprint recognition method according to claim 7, wherein: The processing of the fuzzy region based on the pre-trained neural network processing model to obtain the identifiable data includes: The fuzzy area is subjected to homomorphic filtering processing using the neural network processing model to obtain the recognizable data.

9. The anti-interference fingerprint recognition method according to claim 8, characterized in that: The performing homomorphic filtering processing on the fuzzy area using the neural network processing model to obtain the identifiable data includes: Taking logarithms and Fourier transforming the image of the blurred area and its illumination component and reflection component into frequencies respectively; After filtering by the filter, it is Fourier transformed into the spatial domain to obtain the recognizable data after homomorphic filtering.

10. An anti-interference fingerprint recognition device, characterized in that: include: An acquisition module, configured to acquire fingerprint information of a current user according to a pressing instruction of the current user; a determination module, configured to determine a clear area and a fuzzy area different from the clear area in the acquired user fingerprint information; The user fingerprint information consists of the clear area and the fuzzy area; a filtering module configured to filter the pre-recorded data in the database, based on the fuzzy area, by excluding an area corresponding to the fuzzy area, to obtain first filtering information corresponding to each pre-recorded data; an identification module for identifying the user fingerprint information based on the first filtering information, comprising: comparing the clear area in the user fingerprint information with each of the first filtering information in the database; if there is first filtering information in the database whose matching degree with the clear area reaches a first preset matching degree, using the pre-recorded data corresponding to the first filtering information that reaches the first preset matching degree as target data corresponding to the user fingerprint information, and clarifying the fuzzy area in the user fingerprint information to obtain identifiable data; filtering out the target data from a portion that is identical in position and size to and corresponding to the clear area to obtain second filtering information; comparing the identifiable data with the second filtering information; and determining that the comparison is successful if the matching degree reaches the second preset matching degree.

11. An anti-interference fingerprint recognition system, characterized in that: The system comprises a memory and a processor, wherein the memory stores an anti-interference fingerprint recognition program, and the processor runs the anti-interference fingerprint recognition program to enable the anti-interference fingerprint recognition system to perform the anti-interference fingerprint recognition method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an anti-interference fingerprint recognition program, which, when executed by a processor, implements the anti-interference fingerprint recognition method according to any one of claims 1 to 9.

Images