Fingerprint identification access control method and system

Abstract

The present invention provides a fingerprint identification access control method and system. The fingerprint identification access control method comprises: collecting a fingerprint image used for fingerprint identification for the same user in real time; on the basis of grayscale values of pixel blocks of a fingerprint portion of the currently collected fingerprint image, acquiring a first grayscale threshold value and a second grayscale threshold value corresponding to the current fingerprint image; using the first grayscale threshold value and the second grayscale threshold value to acquire a plurality of image blocks to be identified, and, on the basis of grayscale values of said image blocks, acquiring a comprehensive similarity numerical value of the current fingerprint image; and when the comprehensive similarity numerical value is not less than a preset similarity threshold value, determining that the fingerprint image of the current user passes fingerprint verification. The system comprises modules corresponding to the method steps.

Description

Fingerprint recognition access control method and system Technical Field

[0001] The present invention relates to the technical field of fingerprint recognition, and in particular to a fingerprint recognition access control method and system. Background Art

[0002] Fingerprint recognition is a biometric authentication technology characterized by uniqueness and stability, and is widely used in security. Currently, most fingerprint recognition products on the market use capacitive or optical sensors to capture fingerprint images, then use specific algorithms to extract features for comparison to determine user authenticity. These products often require users to perform specific pressing gestures and pressure, and are significantly affected by finger moisture, resulting in a less than ideal user experience.

[0003] Furthermore, in the mobile internet era, people have increasingly high expectations for identity authentication, hoping for quick and accurate authentication while also ensuring the authentication process is as simple and convenient as possible, without placing excessive burden on users. This requires fingerprint recognition systems to ensure accuracy while providing a good user experience.

[0004] Summary of the Invention

[0005] The present invention provides a fingerprint recognition access control method and system, which is used to solve the problem that traditional fingerprint recognition requires all feature recognition of the entire fingerprint image, and the processing efficiency and recognition response speed are low due to the large corresponding fingerprint area of ​​fingerprint recognition. Although extracting local fingerprint image blocks for recognition can reduce the recognition area, the recognition accuracy is low; the present invention extracts fingerprint image blocks from the fingerprint image, but according to the traditional image block extraction method, it is impossible to screen out the image blocks with the strongest fingerprint feature representation, which will lead to a high probability of fingerprint recognition failure and low fingerprint recognition accuracy due to the weak representation of the selected fingerprint image blocks.

[0006] The present invention proposes a fingerprint recognition access control method, which includes:

[0007] S1: Real-time collection of fingerprint images for fingerprint identification of the same user;

[0008] S2: Obtaining a first grayscale threshold and a second grayscale threshold corresponding to the current fingerprint image based on the grayscale value of the pixel block of the fingerprint portion of the currently collected fingerprint image; wherein the first grayscale threshold is greater than the second grayscale threshold;

[0009] S3: using the first grayscale threshold and the second grayscale threshold to obtain a plurality of image blocks to be identified, and combining the grayscale values ​​of the image blocks to be identified to obtain a comprehensive similarity value of the current fingerprint image;

[0010] S4: When the comprehensive similarity value is not lower than the preset similarity threshold, it is determined that the fingerprint image of the current user passes the fingerprint verification.

[0011] Furthermore, according to the grayscale value of the pixel block of the fingerprint portion of the currently collected fingerprint image, a first grayscale threshold and a second grayscale threshold corresponding to the current fingerprint image are obtained, including:

[0012] S21: extracting the grayscale value of the pixel block of the fingerprint part of the current fingerprint image;

[0013] S22: extracting the grayscale values ​​of the pixel blocks of the fingerprint portion that are lower than the optimal threshold corresponding to the fingerprint image as first grayscale value data;

[0014] S23: extracting the grayscale value of the pixel block of the fingerprint portion that is not lower than the optimal threshold corresponding to the fingerprint image as the second grayscale value data;

[0015] S24: using the first grayscale value data to set a first candidate grayscale threshold value for the fingerprint portion;

[0016] S25: using the second grayscale value data to set a second candidate grayscale threshold value for the fingerprint portion;

[0017] S26: Compare the first candidate grayscale threshold with the second candidate grayscale threshold, and use the larger one between the first candidate grayscale threshold and the second candidate grayscale threshold as the first grayscale threshold, and use the smaller one between the first candidate grayscale threshold and the second candidate grayscale threshold as the second grayscale threshold.

[0018] Furthermore, the first grayscale threshold and the second grayscale threshold are used to obtain a plurality of image blocks to be identified, and the comprehensive similarity value of the current fingerprint image is obtained in combination with the grayscale values ​​of the image blocks to be identified, including:

[0019] S31: Segmenting the fingerprint image using the first grayscale threshold and the second grayscale threshold to obtain a plurality of first image blocks to be identified and second image blocks to be identified;

[0020] S32: performing similarity comparisons on the plurality of first image blocks to be identified and the second image blocks to be identified with fingerprint positions corresponding to the fingerprint reference images of the user that have been entered into the database, to obtain similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified;

[0021] S33: Obtaining a comprehensive similarity value of the current fingerprint image by using the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified in combination with the grayscale value of the image to be identified.

[0022] Furthermore, segmenting the fingerprint image by the first grayscale threshold and the second grayscale threshold to obtain a plurality of image blocks to be identified includes:

[0023] S311: Extracting grayscale values ​​of all pixel blocks of the fingerprint portion in the fingerprint image;

[0024] S312: extracting pixel blocks whose grayscale values ​​exceed the first grayscale threshold as first-category pixel blocks;

[0025] S313: Retrieving, from the first type of pixel blocks, a target region whose number of blocks containing the first type of pixel blocks exceeds a preset first block number threshold within the first target region as a first target region;

[0026] S314: Segmenting the fingerprint image according to the position of the first target area to obtain a first image block to be identified;

[0027] S315: extracting pixel blocks whose grayscale values ​​exceed the second grayscale threshold but do not exceed the first grayscale threshold as second-category pixel blocks;

[0028] S316: Retrieving, from the second type of pixel blocks, a target region whose number of blocks containing the second type of pixel blocks exceeds a preset second block number threshold within the second target region as the second target region;

[0029] S317: Segment the fingerprint image according to the position of the second target area to obtain a second image block to be identified.

[0030] Furthermore, the area of ​​the first target area is smaller than the area of ​​the second target area, and the ratio between the area of ​​the first target area and the area of ​​the second target area is in the range of 1:1.7-1:2.3; at the same time, the first block number threshold is smaller than the second block number threshold, and the ratio between the first block number threshold and the second block number threshold is in the range of 1:2.1-1:2.8.

[0031] The present invention proposes a fingerprint recognition access control system, which includes:

[0032] Image acquisition module: real-time acquisition of fingerprint images for fingerprint identification of the same user;

[0033] Threshold acquisition module: acquires a first grayscale threshold and a second grayscale threshold corresponding to the current fingerprint image according to the grayscale value of the pixel block of the fingerprint portion of the currently collected fingerprint image; wherein the first grayscale threshold is greater than the second grayscale threshold;

[0034] An image block acquisition module is configured to acquire a plurality of image blocks to be identified by using the first grayscale threshold and the second grayscale threshold, and to acquire a comprehensive similarity value of the current fingerprint image in combination with the grayscale values ​​of the image blocks to be identified;

[0035] Similarity judgment module: When the comprehensive similarity value is not lower than the preset similarity threshold, it is determined that the fingerprint image of the current user passes the fingerprint verification.

[0036] Furthermore, the threshold acquisition module includes:

[0037] Gray value extraction module: extracts the gray value of the pixel block of the fingerprint part of the current fingerprint image;

[0038] A first grayscale value data module is configured to extract the grayscale values ​​of pixel blocks of the fingerprint portion that are lower than the optimal threshold corresponding to the fingerprint image as first grayscale value data;

[0039] A second grayscale value data module is used to extract the grayscale values ​​of the pixel blocks of the fingerprint portion that are not lower than the optimal threshold corresponding to the fingerprint image as the second grayscale value data;

[0040] A first candidate grayscale threshold module: using the first grayscale value data to set a first candidate grayscale threshold of the fingerprint part;

[0041] A second candidate grayscale threshold module: using the second grayscale value data to set a second candidate grayscale threshold of the fingerprint part;

[0042] Threshold comparison module: compares the first candidate grayscale threshold with the second candidate grayscale threshold, takes the larger candidate grayscale threshold between the first candidate grayscale threshold and the second candidate grayscale threshold as the first grayscale threshold, and takes the smaller candidate grayscale threshold between the first candidate grayscale threshold and the second candidate grayscale threshold as the second grayscale threshold.

[0043] Furthermore, the image block acquisition module includes:

[0044] An image block acquisition module to be identified is configured to segment the fingerprint image using the first grayscale threshold and the second grayscale threshold to obtain a plurality of first image blocks to be identified and second image blocks to be identified;

[0045] A similarity value comparison module is configured to compare the plurality of first image blocks to be identified and the second image blocks to be identified with the fingerprint positions corresponding to the fingerprint reference images entered into the database by the user in sequence, and obtain the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified;

[0046] Similarity value acquisition module: uses the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified respectively in combination with the grayscale value of the image to be identified to obtain the comprehensive similarity value of the current fingerprint image.

[0047] Furthermore, the module for obtaining the image block to be identified includes:

[0048] Gray value extraction module: extracts the gray value of all pixel blocks of the fingerprint part in the fingerprint image;

[0049] A first-category pixel block module: extracting pixel blocks whose grayscale values ​​exceed the first grayscale threshold as first-category pixel blocks;

[0050] A target region setting module: retrieving, from the first type of pixel blocks, a target region whose number of blocks containing the first type of pixel blocks exceeds a preset first block number threshold within the first target region as a first target region;

[0051] A first image block to be identified module: segments the fingerprint image according to the position of the first target area to obtain a first image block to be identified;

[0052] A second-category pixel block determination module is configured to extract pixel blocks whose grayscale values ​​exceed the second grayscale threshold but do not exceed the first grayscale threshold as second-category pixel blocks;

[0053] An area region retrieving module: retrieving a target region whose number of blocks containing the second type of pixel blocks exceeds a preset second block number threshold within the second target region from the second type of pixel blocks as a second target region;

[0054] Second target area module: segments the fingerprint image according to the position of the second target area to obtain a second image block to be identified.

[0055] Furthermore, the area of ​​the first target area is smaller than the area of ​​the second target area, and the ratio between the area of ​​the first target area and the area of ​​the second target area is in the range of 1:1.7-1:2.3; at the same time, the first block number threshold is smaller than the second block number threshold, and the ratio between the first block number threshold and the second block number threshold is in the range of 1:2.1-1:2.8.

[0056] Beneficial effects of the present invention: The technical solution proposed by the present invention reduces the possibility of misidentification and missed identification by real-time acquisition and comparison of multiple fingerprint images provided by the user, thereby improving the accuracy and security of fingerprint identification. By adopting a grayscale value comparison method, the complex manual feature extraction and matching process is avoided, which greatly saves time and computing resources. The present invention is fast and convenient, can provide a good user experience, and is suitable for application in various access control systems. By extracting local fingerprint image blocks for identification, the identification area can be reduced, thereby reducing processing time and response time, and improving identification efficiency. By extracting fingerprint image blocks from fingerprint images and screening out image blocks with the strongest fingerprint feature representation, the accuracy of fingerprint identification can be enhanced and the probability of identification failure can be reduced. By improving the image block extraction method and screening out image blocks with the strongest fingerprint feature representation, the robustness of fingerprint identification can be enhanced, so that the fingerprint identification system has better performance when facing different fingerprint images. By improving the efficiency and accuracy of fingerprint identification, the demand for hardware resources can be reduced, thereby reducing the cost of the fingerprint identification system. By improving the identification efficiency and accuracy, the user waiting time can be reduced, the system response speed can be improved, and the user experience can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] FIG1 is a step diagram of a fingerprint recognition access control method according to the present invention;

[0058] FIG2 is a module diagram of a fingerprint recognition access control system according to the present invention. DETAILED DESCRIPTION

[0059] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0060] Example 1

[0061] This embodiment provides a fingerprint recognition access control method, which includes:

[0062] S1: Real-time collection of fingerprint images for fingerprint identification of the same user;

[0063] S2: Obtaining a first grayscale threshold and a second grayscale threshold corresponding to the current fingerprint image based on the grayscale value of the pixel block of the fingerprint portion of the currently collected fingerprint image; wherein the first grayscale threshold is greater than the second grayscale threshold;

[0064] S3: using the first grayscale threshold and the second grayscale threshold to obtain a plurality of image blocks to be identified, and combining the grayscale values ​​of the image blocks to be identified to obtain a comprehensive similarity value of the current fingerprint image;

[0065] S4: When the comprehensive similarity value is not lower than the preset similarity threshold, it is determined that the fingerprint image of the current user passes the fingerprint verification.

[0066] The working principle of the above technical solution is as follows: the user presses the fingerprint sensor on the access control system, and the system collects the user's fingerprint image for fingerprint identification in real time. By analyzing the grayscale value of the pixel block of the fingerprint part of the currently collected fingerprint image, the system obtains the first grayscale threshold and the second grayscale threshold corresponding to the current fingerprint image. These thresholds may be used to identify specific features in the fingerprint image for subsequent comparison and verification. Using the first grayscale threshold and the second grayscale threshold, the system divides the fingerprint image into multiple image blocks to be identified, and combines the grayscale values ​​of these image blocks to calculate the comprehensive similarity value of the current fingerprint image. This step may include extracting the features of the fingerprint image, and then comparing them with the reference features stored in the database to calculate the similarity. When the comprehensive similarity value reaches or exceeds the preset similarity threshold, the system determines that the current user's fingerprint image has passed the fingerprint verification, thereby allowing the user to obtain access control authority.

[0067] The above technical solution has the following advantages: it can improve user experience. By providing a novel grayscale value comparison method, it avoids the complex manual feature extraction and matching process, significantly saving time and computing resources, and also significantly reducing manpower and material resources, thereby improving operation and maintenance efficiency and management level. By analyzing the grayscale values ​​of fingerprint images and calculating comprehensive similarity, high-precision fingerprint recognition can be achieved. This helps ensure that only authorized users can pass through the access control system, improving security. By utilizing grayscale thresholds, simple fingerprint forgery attacks, such as using fake fingerprints, can be effectively countered. This increases the security of the access control system and prevents fraud by illegally copied fingerprints. The fingerprint image acquisition and processing process is real-time, so users can quickly obtain the corresponding verification results after pressing their fingerprints on the access control system, improving the user experience. This method dynamically determines the grayscale threshold based on the characteristics of the currently acquired fingerprint image and combines it with the grayscale values ​​of the image block to be identified for similarity calculation. This method can adapt to changes in fingerprint features in different environments, improving the robustness and applicability of the system. Using a preset similarity threshold for determination can, to a certain extent, avoid false positives and missed positives, improving the reliability of fingerprint verification.

[0068] Example 2

[0069] In this embodiment, obtaining the first grayscale threshold and the second grayscale threshold corresponding to the current fingerprint image according to the grayscale value of the pixel block of the fingerprint portion of the currently collected fingerprint image includes:

[0070] S21: extracting the grayscale value of the pixel block of the fingerprint part of the current fingerprint image;

[0071] S22: extracting the grayscale values ​​of the pixel blocks of the fingerprint portion that are lower than the optimal threshold corresponding to the fingerprint image (the optimal threshold can be obtained by the Otsu algorithm) as first grayscale value data;

[0072] S23: extracting the grayscale value of the pixel block of the fingerprint portion that is not lower than the optimal threshold corresponding to the fingerprint image as the second grayscale value data;

[0073] S24: using the first grayscale value data to set a first candidate grayscale threshold value for the fingerprint portion;

[0074] S25: using the second grayscale value data to set a second candidate grayscale threshold value for the fingerprint portion;

[0075] S26: Compare the first candidate grayscale threshold with the second candidate grayscale threshold, and use the larger one between the first candidate grayscale threshold and the second candidate grayscale threshold as the first grayscale threshold, and use the smaller one between the first candidate grayscale threshold and the second candidate grayscale threshold as the second grayscale threshold.

[0076] The first candidate grayscale threshold and the second candidate grayscale threshold are obtained by the following formula:

[0077] Among them, H 01 Represents the first candidate grayscale threshold; H z represents the optimal threshold; X max represents the value of the inter-class variance corresponding to the optimal threshold; n1 represents the number of pixel blocks corresponding to the first gray value data; H i represents the grayscale value corresponding to the i-th pixel block; α1 represents the first threshold adjustment coefficient; L represents the total number of grayscale levels contained in the fingerprint image; P i represents the probability of occurrence of the grayscale level of the grayscale value corresponding to the i-th pixel block in the first grayscale value data;

[0078] Among them, H 02 represents the second candidate grayscale threshold; H z represents the optimal threshold; X max represents the value of the inter-class variance corresponding to the optimal threshold; n2 represents the number of pixel blocks corresponding to the second gray value data; H j represents the grayscale value corresponding to the jth pixel block; α2 represents the second threshold adjustment coefficient; L represents the total number of grayscale levels contained in the fingerprint image; P j Represents the probability of occurrence of the grayscale level of the grayscale value corresponding to the j-th pixel block in the second grayscale value data.

[0079] The working principle of the above technical solution is: extract the grayscale value of the pixel block of the fingerprint part of the current fingerprint image; extract the grayscale value of the pixel block in the pixel block of the fingerprint part that is lower than the optimal threshold corresponding to the fingerprint image (the optimal threshold can be obtained through the OTSU algorithm) as the first grayscale value data; extract the grayscale value of the pixel block in the pixel block of the fingerprint part that is not lower than the optimal threshold corresponding to the fingerprint image as the second grayscale value data; use the first grayscale value data to set the first candidate grayscale threshold of the fingerprint part; use the second grayscale value data to set the second candidate grayscale threshold of the fingerprint part; compare the first candidate grayscale threshold with the second candidate grayscale threshold, and use the larger candidate grayscale threshold between the first candidate grayscale threshold and the second candidate grayscale threshold as the first grayscale threshold, and use the smaller candidate grayscale threshold between the first candidate grayscale threshold and the second candidate grayscale threshold as the second grayscale threshold.

[0080] The effects of the above technical solution are as follows: by extracting the grayscale values ​​of pixel blocks in the fingerprint image and determining the first and second grayscale value data based on the optimal threshold, the solution can automatically adjust the grayscale threshold according to the characteristics of different fingerprint images, thereby adapting to different fingerprint images; by comparing the first and second candidate grayscale thresholds and selecting relatively appropriate thresholds as the first and second grayscale thresholds, the solution can ensure high-precision processing of the current fingerprint image and improve the accuracy of fingerprint recognition; by processing based on the grayscale values ​​of pixel blocks, the solution considers more information in the process of extracting grayscale values ​​and determining grayscale thresholds, thereby improving the reliability and robustness of the fingerprint image; because the calculation process of this solution is relatively simple and does not require a large amount of computing resources, the first and second grayscale thresholds can be quickly obtained and determined, which is suitable for real-time fingerprint image processing scenarios. The above-mentioned first and second candidate grayscale threshold calculation formulas improve the rationality of threshold settings, thereby improving the accuracy of subsequent target area calibration and the fingerprint feature representation of the fingerprint portion within the target area. By improving the accuracy of subsequent target area calibration and the fingerprint feature representation of the fingerprint portion within the target area, the recognition accuracy is effectively improved when only partial fingerprint recognition is performed. At the same time, the formula uses the optimal threshold and inter-class variance values ​​as references. By adjusting the threshold adjustment coefficients α1 and α2, the first and second candidate grayscale thresholds can be adaptively determined based on the grayscale distribution of the pixel blocks in the first and second grayscale value data. This can better adapt to the characteristics of different fingerprint images and improve the accuracy and robustness of fingerprint recognition. The formula takes into account the probability P of the grayscale level of the pixel block grayscale value in the first and second grayscale value data. i and P jThis better reflects the distribution of different grayscale levels in the fingerprint image, making the selected candidate grayscale threshold more reasonable and accurate. The formula introduces adjustment coefficients α1 and α2 to control the adjustment range of the candidate grayscale threshold. By properly setting the adjustment coefficients, the accuracy and sensitivity of the grayscale threshold can be further adjusted while maintaining adaptability, thereby improving the performance of the fingerprint recognition system.

[0081] Example 3

[0082] In this embodiment, the first grayscale threshold and the second grayscale threshold are used to obtain a plurality of image blocks to be identified, and the comprehensive similarity value of the current fingerprint image is obtained in combination with the grayscale values ​​of the image blocks to be identified, including:

[0083] S31: Segmenting the fingerprint image using the first grayscale threshold and the second grayscale threshold to obtain a plurality of first image blocks to be identified and second image blocks to be identified;

[0084] S32: performing similarity comparisons on the plurality of first image blocks to be identified and the second image blocks to be identified with fingerprint positions corresponding to the fingerprint reference images of the user that have been entered into the database, to obtain similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified;

[0085] S33: Obtaining a comprehensive similarity value of the current fingerprint image by using the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified in combination with the grayscale value of the image to be identified.

[0086] The comprehensive similarity value of the current fingerprint image is obtained by the following formula: SIM = 0.5·(λ1·S p1 +λ2·S p2 )

[0087] Among them, SIM represents the comprehensive similarity value; S p1 represents the average similarity value of all first image blocks to be identified; S p2 represents the average similarity value of all the image blocks to be identified; λ1 and λ2 represent the weight coefficient corresponding to the first image block to be identified and the weight coefficient corresponding to the second image block to be identified respectively; C1 and C2 represent the number of the first image block to be identified and the second image block to be identified respectively; B s N represents the ratio between the area of ​​the first target area and the area of ​​the second target area; i M represents the number of first-type pixel blocks contained in the i-th first image block to be identified; iN represents the number of pixel blocks of the first type contained in the i-th first image block to be identified whose grayscale values ​​are greater than the second grayscale threshold; 01 Indicates the first block number threshold; N 02 Indicates the second block number threshold; N j M represents the number of second-type pixel blocks contained in the j-th second image block to be identified; j It represents the number of pixel blocks of the second type contained in the j-th second image block to be identified whose grayscale values ​​are not lower than the first grayscale threshold.

[0088] The working principle of the above technical solution is as follows: the fingerprint image is segmented by a first grayscale threshold and a second grayscale threshold to obtain a plurality of first image blocks to be identified and a second image block to be identified. These image blocks contain different characteristic areas in the fingerprint image; next, each first image block to be identified and the second image block to be identified are compared for similarity with the fingerprint reference image that the user has entered into the database. The similarity comparison can use various fingerprint matching algorithms, such as comparison algorithms based on feature points, lines, etc. Through comparison, the similarity value of each image block with the fingerprint reference image in the database can be calculated; the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified and the grayscale values ​​of their corresponding image blocks to be identified are combined to calculate the comprehensive similarity value of the current fingerprint image.

[0089] The above technical solution improves the accuracy of the fingerprint recognition system by segmenting the fingerprint image into multiple image blocks and performing similarity comparisons with fingerprint reference images in a database. This is because each image block can more precisely match the fingerprint image in the database, reducing overall matching errors. After segmenting the fingerprint image, each image block can be independently compared for similarity. This prevents damage, contamination, or deformation in the entire fingerprint image from affecting the overall matching result. This enhances the system's robustness to various fingerprint variations. Compared to directly matching the entire fingerprint image, segmenting the fingerprint image into multiple image blocks allows for parallel processing of similarity comparisons for each image block, thereby increasing matching speed. Because each image block is smaller, the computational effort required is reduced, enabling more efficient use of computing resources, optimizing algorithm performance, and improving recognition rates. By combining the grayscale values ​​of the image blocks to be identified, a more comprehensive assessment of fingerprint image similarity can be achieved. Grayscale values ​​reflect the brightness information within the image blocks. By combining similarity values ​​with grayscale values, the degree of fingerprint matching can be more accurately determined. The above formula can improve the accuracy of similarity evaluation by integrating similarity. The setting of weights can effectively improve the accuracy of determining the importance of representing pixel blocks within the corresponding grayscale value range, and further improve the accuracy of obtaining the comprehensive similarity threshold. At the same time, by introducing weight coefficients λ1 and λ2, different weights can be assigned to different image blocks to be identified. In this way, the influence of different image blocks on the overall similarity can be adjusted according to actual conditions, which improves the flexibility of similarity calculation. s Represents the ratio between the area of ​​the first target area and the area of ​​the second target area. This ratio can be used to measure the size difference of the fingerprint area occupied by the two image blocks to be identified. By considering the target area ratio, a reasonable similarity evaluation can be performed on image blocks of different sizes; N in the formula i and M j Respectively represent the number of pixel blocks in the i-th first image block to be identified and the j-th second image block to be identified and the number of pixel blocks that reach a certain grayscale threshold. In this way, statistical information on the grayscale value of pixel blocks can be introduced into the similarity calculation, and the brightness characteristics within the image block can be considered more comprehensively. 01 、N 02 Related to the first grayscale threshold and the second grayscale threshold. These thresholds can be adjusted according to actual conditions to meet the characteristics and requirements of different fingerprint images. By setting adaptive thresholds, the adaptability and accuracy of similarity calculations can be improved.

[0090] Example 4

[0091] In this embodiment, segmenting the fingerprint image using the first grayscale threshold and the second grayscale threshold to obtain multiple image blocks to be identified includes:

[0092] S311: Extracting grayscale values ​​of all pixel blocks of the fingerprint portion in the fingerprint image;

[0093] S312: extracting pixel blocks whose grayscale values ​​exceed the first grayscale threshold as first-category pixel blocks;

[0094] S313: Retrieving, from the first type of pixel blocks, a target region whose number of blocks containing the first type of pixel blocks exceeds a preset first block number threshold within the first target region as a first target region;

[0095] S314: Segmenting the fingerprint image according to the position of the first target area to obtain a first image block to be identified;

[0096] S315: extracting pixel blocks whose grayscale values ​​exceed the second grayscale threshold but do not exceed the first grayscale threshold as second-category pixel blocks;

[0097] S316: Retrieving, from the second type of pixel blocks, a target region whose number of blocks containing the second type of pixel blocks exceeds a preset second block number threshold within the second target region as the second target region;

[0098] S317: Segment the fingerprint image according to the position of the second target area to obtain a second image block to be identified.

[0099] The working principle of the above technical solution is as follows: extract all pixel blocks from the entire fingerprint image and record their grayscale values; identify pixel blocks with grayscale values ​​exceeding a first grayscale threshold; these pixel blocks may represent the main features of the fingerprint image; find a target area within the first type of pixel blocks that meets a preset first block number threshold, i.e., an area that contains a sufficient number of pixel blocks of the first type within a certain range. This area is considered the first target area; segment the fingerprint image based on the location information of the first target area, and extract a first image block to be identified, which may contain the important fingerprint feature; then identify pixel blocks with grayscale values ​​between the first grayscale threshold and the second grayscale threshold but below the second grayscale threshold; these pixel blocks may contain secondary fingerprint features; find a target area within the second type of pixel blocks that meets a preset second block number threshold, i.e., an area that contains a sufficient number of pixel blocks of the second type, as the second target area; segment the fingerprint image based on the location information of the second target area, and extract a second image block to be identified, which may contain the secondary fingerprint feature.

[0100] The effects of the above technical solution are: by segmenting and extracting regions of the fingerprint image, the image blocks to be identified containing the main fingerprint features and secondary fingerprint features can be accurately extracted, which helps to improve the accuracy and comprehensiveness of the fingerprint recognition system for fingerprint features; by setting the first grayscale threshold and the second grayscale threshold, the noise and non-fingerprint areas in the image can be effectively filtered out, thereby increasing the focus on the fingerprint part and reducing the impact of noise on the recognition results; dividing the fingerprint image into multiple image blocks to be identified and processing the feature information of different regions separately helps to increase the system's recognition robustness for different fingerprint features and improves the system's fingerprint recognition effect in complex environments; through multiple segmentations and extractions, the technical solution can more comprehensively capture the feature information in the fingerprint image, thereby improving the accuracy and reliability of the fingerprint recognition system, making it more suitable for various practical application scenarios. By extracting pixel blocks that exceed a first grayscale threshold and pixel blocks that do not exceed the first grayscale threshold but exceed a second grayscale threshold from the fingerprint image, the fingerprint features can be extracted more accurately, thereby improving the accuracy of recognition; by retrieving the target area from the first type of pixel blocks and the second type of pixel blocks, the fingerprint image can be segmented according to the position of the target area to obtain the image blocks to be identified, thereby avoiding the overall processing of the image blocks to be identified, reducing the computational complexity, and improving the computational efficiency; when processing a large number of fingerprint images, this target area-based segmentation and recognition method can significantly reduce the amount of data that needs to be stored and processed, thereby optimizing the use of storage space; due to the use of a grayscale threshold-based pixel block classification method and a target area-based target selection method, illegal intrusions and security vulnerabilities can be effectively avoided, thereby improving the security of the access control system.

[0101] Example 5

[0102] In this embodiment, the area of ​​the first target area is smaller than the area of ​​the second target area, and the ratio between the area of ​​the first target area and the area of ​​the second target area is in the range of 1:1.7-1:2.3; at the same time, the first block number threshold is smaller than the second block number threshold, and the ratio between the first block number threshold and the second block number threshold is in the range of 1:2.1-1:2.8.

[0103] The working principle of the above technical solution is as follows: First, for a specific area in the fingerprint image, the areas of the first target area and the second target area are calculated, with the ratio between the first target area and the second target area ranging from 1:1.7 to 1:2.3. This means that after the target area is calculated, the system will compare and filter, and only target areas that meet the specified ratio range will be retained; the ratio between the first block number threshold and the second block number threshold ranges from 1:2.1 to 1:2.8.

[0104] The effects of the above technical solution are: by limiting and screening the target area and numerical threshold, the accuracy and precision of fingerprint image processing can be improved. Only target areas and values ​​that meet a specific ratio range will be retained, thereby reducing the possibility of misjudgment and misidentification; setting a specific ratio range and numerical threshold can enhance the system's resistance to noise and interference. This means that even in the presence of a certain degree of interference, the system can still better identify and extract fingerprint features; by flexibly setting the ratio range and numerical threshold, the technical solution may have a certain degree of adaptability and can be applied to fingerprint images of different types and qualities, and to a certain extent overcome the challenges brought about by image quality and environmental changes; once the appropriate ratio range and numerical threshold are determined, the technical solution may be able to quickly and effectively process a large amount of fingerprint image data, thereby improving processing efficiency and response speed.

[0105] Example 6

[0106] This embodiment provides a fingerprint recognition access control system, which includes:

[0107] Image acquisition module: real-time acquisition of fingerprint images for fingerprint identification of the same user;

[0108] Threshold acquisition module: acquires a first grayscale threshold and a second grayscale threshold corresponding to the current fingerprint image according to the grayscale value of the pixel block of the fingerprint portion of the currently collected fingerprint image; wherein the first grayscale threshold is greater than the second grayscale threshold;

[0109] An image block acquisition module is configured to acquire a plurality of image blocks to be identified by using the first grayscale threshold and the second grayscale threshold, and to acquire a comprehensive similarity value of the current fingerprint image in combination with the grayscale values ​​of the image blocks to be identified;

[0110] Similarity judgment module: When the comprehensive similarity value is not lower than the preset similarity threshold, it is determined that the fingerprint image of the current user passes the fingerprint verification.

[0111] The working principle of the above technical solution is as follows: the user presses the fingerprint sensor on the access control system, and the system collects the user's fingerprint image for fingerprint identification in real time. By analyzing the grayscale value of the pixel block of the fingerprint part of the currently collected fingerprint image, the system obtains the first grayscale threshold and the second grayscale threshold corresponding to the current fingerprint image. These thresholds may be used to identify specific features in the fingerprint image for subsequent comparison and verification. Using the first grayscale threshold and the second grayscale threshold, the system divides the fingerprint image into multiple image blocks to be identified, and combines the grayscale values ​​of these image blocks to calculate the comprehensive similarity value of the current fingerprint image. This step may include extracting the features of the fingerprint image, and then comparing them with the reference features stored in the database to calculate the similarity. When the comprehensive similarity value reaches or exceeds the preset similarity threshold, the system determines that the current user's fingerprint image has passed the fingerprint verification, thereby allowing the user to obtain access control authority.

[0112] The above technical solution has the following advantages: it can improve user experience. By providing a novel grayscale value comparison method, it avoids the complex manual feature extraction and matching process, significantly saving time and computing resources, and also significantly reducing manpower and material resources, thereby improving operation and maintenance efficiency and management level. By analyzing the grayscale values ​​of fingerprint images and calculating comprehensive similarity, high-precision fingerprint recognition can be achieved. This helps ensure that only authorized users can pass through the access control system, improving security. By utilizing grayscale thresholds, simple fingerprint forgery attacks, such as the use of fake fingerprints, can be effectively countered. This increases the security of the access control system and prevents fraud by illegally copied fingerprints. The fingerprint image acquisition and processing process is real-time, so users can quickly obtain the corresponding verification results after pressing their fingerprints on the access control system, improving the user experience. This method dynamically determines the grayscale threshold based on the characteristics of the currently acquired fingerprint image and combines it with the grayscale values ​​of the image block to be identified for similarity calculation. This method can adapt to changes in fingerprint features in different environments, improving the robustness and applicability of the system. Using a preset similarity threshold for judgment can, to a certain extent, avoid false positives and missed positives, improving the reliability of fingerprint verification.

[0113] Example 7

[0114] In this embodiment, the threshold acquisition module includes:

[0115] Gray value extraction module: extracts the gray value of the pixel block of the fingerprint part of the current fingerprint image;

[0116] A first grayscale value data module is configured to extract the grayscale values ​​of the pixel blocks of the fingerprint portion that are lower than the optimal threshold corresponding to the fingerprint image (the optimal threshold can be obtained by the OTSU algorithm) as first grayscale value data;

[0117] A second grayscale value data module is used to extract the grayscale values ​​of the pixel blocks of the fingerprint portion that are not lower than the optimal threshold corresponding to the fingerprint image as the second grayscale value data;

[0118] A first candidate grayscale threshold module: using the first grayscale value data to set a first candidate grayscale threshold of the fingerprint part;

[0119] A second candidate grayscale threshold module: using the second grayscale value data to set a second candidate grayscale threshold of the fingerprint part;

[0120] Threshold comparison module: compares the first candidate grayscale threshold with the second candidate grayscale threshold, takes the larger candidate grayscale threshold between the first candidate grayscale threshold and the second candidate grayscale threshold as the first grayscale threshold, and takes the smaller candidate grayscale threshold between the first candidate grayscale threshold and the second candidate grayscale threshold as the second grayscale threshold.

[0121] The first candidate grayscale threshold and the second candidate grayscale threshold are obtained by the following formula:

[0122] Among them, H 01 Represents the first candidate grayscale threshold; H z represents the optimal threshold; X max represents the value of the inter-class variance corresponding to the optimal threshold; n1 represents the number of pixel blocks corresponding to the first gray value data; H i represents the grayscale value corresponding to the i-th pixel block; α1 represents the first threshold adjustment coefficient; L represents the total number of grayscale levels contained in the fingerprint image; P i represents the probability of occurrence of the grayscale level of the grayscale value corresponding to the i-th pixel block in the first grayscale value data;

[0123] Among them, H 02 represents the second candidate grayscale threshold; H z represents the optimal threshold; X max represents the value of the inter-class variance corresponding to the optimal threshold; n2 represents the number of pixel blocks corresponding to the second gray value data; H j represents the grayscale value corresponding to the jth pixel block; α2 represents the second threshold adjustment coefficient; L represents the total number of grayscale levels contained in the fingerprint image; P j Represents the probability of occurrence of the grayscale level of the grayscale value corresponding to the j-th pixel block in the second grayscale value data.

[0124] The working principle of the above technical solution is: extract the grayscale value of the pixel block of the fingerprint part of the current fingerprint image; extract the grayscale value of the pixel block in the pixel block of the fingerprint part that is lower than the optimal threshold corresponding to the fingerprint image (the optimal threshold can be obtained through the OTSU algorithm) as the first grayscale value data; extract the grayscale value of the pixel block in the pixel block of the fingerprint part that is not lower than the optimal threshold corresponding to the fingerprint image as the second grayscale value data; use the first grayscale value data to set the first candidate grayscale threshold of the fingerprint part; use the second grayscale value data to set the second candidate grayscale threshold of the fingerprint part; compare the first candidate grayscale threshold with the second candidate grayscale threshold, and use the larger candidate grayscale threshold between the first candidate grayscale threshold and the second candidate grayscale threshold as the first grayscale threshold, and use the smaller candidate grayscale threshold between the first candidate grayscale threshold and the second candidate grayscale threshold as the second grayscale threshold.

[0125] The effects of the above technical solution are as follows: by extracting the grayscale values ​​of pixel blocks in the fingerprint image and determining the first and second grayscale value data based on the optimal threshold, the solution can automatically adjust the grayscale threshold according to the characteristics of different fingerprint images, thereby adapting to different fingerprint images; by comparing the first and second candidate grayscale thresholds and selecting relatively appropriate thresholds as the first and second grayscale thresholds, the solution can ensure high-precision processing of the current fingerprint image and improve the accuracy of fingerprint recognition; by processing based on the grayscale values ​​of pixel blocks, the solution considers more information in the process of extracting grayscale values ​​and determining grayscale thresholds, thereby improving the reliability and robustness of the fingerprint image; because the calculation process of this solution is relatively simple and does not require a large amount of computing resources, the first and second grayscale thresholds can be quickly obtained and determined, which is suitable for real-time fingerprint image processing scenarios. The above-mentioned first and second candidate grayscale threshold calculation formulas improve the rationality of threshold settings, thereby improving the accuracy of subsequent target area calibration and the fingerprint feature representation of the fingerprint portion within the target area. By improving the accuracy of subsequent target area calibration and the fingerprint feature representation of the fingerprint portion within the target area, the recognition accuracy is effectively improved when only partial fingerprint recognition is performed. At the same time, the formula uses the optimal threshold and inter-class variance values ​​as references. By adjusting the threshold adjustment coefficients α1 and α2, the first and second candidate grayscale thresholds can be adaptively determined based on the grayscale distribution of the pixel blocks in the first and second grayscale value data. This can better adapt to the characteristics of different fingerprint images and improve the accuracy and robustness of fingerprint recognition. The formula takes into account the probability P of the grayscale level of the pixel block grayscale value in the first and second grayscale value data. i and P jThis better reflects the distribution of different grayscale levels in the fingerprint image, making the selected candidate grayscale threshold more reasonable and accurate. The formula introduces adjustment coefficients α1 and α2 to control the adjustment range of the candidate grayscale threshold. By properly setting the adjustment coefficients, the accuracy and sensitivity of the grayscale threshold can be further adjusted while maintaining adaptability, thereby improving the performance of the fingerprint recognition system.

[0126] Example 8

[0127] In this embodiment, the image block acquisition module includes:

[0128] An image block acquisition module to be identified is configured to segment the fingerprint image using the first grayscale threshold and the second grayscale threshold to obtain a plurality of first image blocks to be identified and second image blocks to be identified;

[0129] A similarity value comparison module is configured to compare the plurality of first image blocks to be identified and the second image blocks to be identified with the fingerprint positions corresponding to the fingerprint reference images entered into the database by the user in sequence, and obtain the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified;

[0130] Similarity value acquisition module: uses the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified respectively in combination with the grayscale value of the image to be identified to obtain the comprehensive similarity value of the current fingerprint image.

[0131] The comprehensive similarity value of the current fingerprint image is obtained by the following formula: SIM = 0.5·(λ1·S p1 +λ2·S p2 )

[0132] Among them, SIM represents the comprehensive similarity value; S p1 represents the average similarity value of all first image blocks to be identified; S p2 represents the average similarity value of all the image blocks to be identified; λ1 and λ2 represent the weight coefficient corresponding to the first image block to be identified and the weight coefficient corresponding to the second image block to be identified respectively; C1 and C2 represent the number of the first image block to be identified and the second image block to be identified respectively; B s N represents the ratio between the area of ​​the first target area and the area of ​​the second target area; i M represents the number of first-type pixel blocks contained in the i-th first image block to be identified; i N represents the number of pixel blocks of the first type contained in the i-th first image block to be identified whose grayscale values ​​are greater than the second grayscale threshold; 01 Indicates the first block number threshold; N02 Indicates the second block number threshold; N j M represents the number of second-type pixel blocks contained in the j-th second image block to be identified; j It represents the number of pixel blocks of the second type contained in the j-th second image block to be identified whose grayscale values ​​are not lower than the first grayscale threshold.

[0133] The working principle of the above technical solution is as follows: the fingerprint image is segmented by a first grayscale threshold and a second grayscale threshold to obtain a plurality of first image blocks to be identified and a second image block to be identified. These image blocks contain different characteristic areas in the fingerprint image; next, each first image block to be identified and the second image block to be identified are compared for similarity with the fingerprint reference image that the user has entered into the database. The similarity comparison can use various fingerprint matching algorithms, such as comparison algorithms based on feature points, lines, etc. Through comparison, the similarity value of each image block with the fingerprint reference image in the database can be calculated; the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified and the grayscale values ​​of their corresponding image blocks to be identified are combined to calculate the comprehensive similarity value of the current fingerprint image.

[0134] The above technical solution improves the accuracy of the fingerprint recognition system by segmenting the fingerprint image into multiple image blocks and performing similarity comparisons with fingerprint reference images in a database. This is because each image block can more precisely match the fingerprint image in the database, reducing overall matching errors. After segmenting the fingerprint image, each image block can be independently compared for similarity. This prevents damage, contamination, or deformation in the entire fingerprint image from affecting the overall matching result. This enhances the system's robustness to various fingerprint variations. Compared to directly matching the entire fingerprint image, segmenting the fingerprint image into multiple image blocks allows for parallel processing of similarity comparisons for each image block, thereby increasing matching speed. Because each image block is smaller, the computational effort required is reduced, enabling more efficient use of computing resources, optimizing algorithm performance, and improving recognition rates. By combining the grayscale values ​​of the image blocks to be identified, a more comprehensive assessment of fingerprint image similarity can be achieved. Grayscale values ​​reflect the brightness information within the image blocks. By combining similarity values ​​with grayscale values, the degree of fingerprint matching can be more accurately determined. The above formula can improve the accuracy of similarity evaluation by integrating similarity. The setting of weights can effectively improve the accuracy of determining the importance of representing pixel blocks within the corresponding grayscale value range, and further improve the accuracy of obtaining the comprehensive similarity threshold. At the same time, by introducing weight coefficients λ1 and λ2, different weights can be assigned to different image blocks to be identified. In this way, the influence of different image blocks on the overall similarity can be adjusted according to actual conditions, which improves the flexibility of similarity calculation. sRepresents the ratio between the area of ​​the first target area and the area of ​​the second target area. This ratio can be used to measure the size difference of the fingerprint area occupied by the two image blocks to be identified. By considering the target area ratio, a reasonable similarity evaluation can be performed on image blocks of different sizes; N in the formula i and M j Respectively represent the number of pixel blocks in the i-th first image block to be identified and the j-th second image block to be identified and the number of pixel blocks that reach a certain grayscale threshold. In this way, statistical information on the grayscale value of pixel blocks can be introduced into the similarity calculation, and the brightness characteristics within the image block can be considered more comprehensively. 01 、N 02 Related to the first grayscale threshold and the second grayscale threshold. These thresholds can be adjusted according to actual conditions to meet the characteristics and requirements of different fingerprint images. By setting adaptive thresholds, the adaptability and accuracy of similarity calculations can be improved.

[0135] Example 9

[0136] In this embodiment, the module for obtaining the image block to be identified includes:

[0137] Gray value extraction module: extracts the gray value of all pixel blocks of the fingerprint part in the fingerprint image;

[0138] A first-category pixel block module: extracting pixel blocks whose grayscale values ​​exceed the first grayscale threshold as first-category pixel blocks;

[0139] A target region setting module: retrieving, from the first type of pixel blocks, a target region whose number of blocks containing the first type of pixel blocks exceeds a preset first block number threshold within the first target region as a first target region;

[0140] A first image block to be identified module: segments the fingerprint image according to the position of the first target area to obtain a first image block to be identified;

[0141] A second-category pixel block determination module is configured to extract pixel blocks whose grayscale values ​​exceed the second grayscale threshold but do not exceed the first grayscale threshold as second-category pixel blocks;

[0142] An area region retrieving module: retrieving a target region whose number of blocks containing the second type of pixel blocks exceeds a preset second block number threshold within the second target region from the second type of pixel blocks as a second target region;

[0143] Second target area module: segments the fingerprint image according to the position of the second target area to obtain a second image block to be identified.

[0144] The working principle of the above technical solution is as follows: extract all pixel blocks from the entire fingerprint image and record their grayscale values; identify pixel blocks with grayscale values ​​exceeding a first grayscale threshold; these pixel blocks may represent the main features of the fingerprint image; find a target area within the first type of pixel blocks that meets a preset first block number threshold, i.e., an area that contains a sufficient number of pixel blocks of the first type within a certain range. This area is considered the first target area; segment the fingerprint image based on the location information of the first target area, and extract a first image block to be identified, which may contain the important fingerprint feature; then identify pixel blocks with grayscale values ​​between the first grayscale threshold and the second grayscale threshold but below the second grayscale threshold; these pixel blocks may contain secondary fingerprint features; find a target area within the second type of pixel blocks that meets a preset second block number threshold, i.e., an area that contains a sufficient number of pixel blocks of the second type, as the second target area; segment the fingerprint image based on the location information of the second target area, and extract a second image block to be identified, which may contain the secondary fingerprint feature.

[0145] The effects of the above technical solution are: by segmenting and extracting regions of the fingerprint image, the image blocks to be identified containing the main fingerprint features and secondary fingerprint features can be accurately extracted, which helps to improve the accuracy and comprehensiveness of the fingerprint recognition system for fingerprint features; by setting the first grayscale threshold and the second grayscale threshold, the noise and non-fingerprint areas in the image can be effectively filtered out, thereby increasing the focus on the fingerprint part and reducing the impact of noise on the recognition results; dividing the fingerprint image into multiple image blocks to be identified and processing the feature information of different regions separately helps to increase the system's recognition robustness for different fingerprint features and improves the system's fingerprint recognition effect in complex environments; through multiple segmentations and extractions, the technical solution can more comprehensively capture the feature information in the fingerprint image, thereby improving the accuracy and reliability of the fingerprint recognition system, making it more suitable for various practical application scenarios. By extracting pixel blocks that exceed a first grayscale threshold and pixel blocks that do not exceed the first grayscale threshold but exceed a second grayscale threshold from the fingerprint image, the fingerprint features can be extracted more accurately, thereby improving the accuracy of recognition; by retrieving the target area from the first type of pixel blocks and the second type of pixel blocks, the fingerprint image can be segmented according to the position of the target area to obtain the image blocks to be identified, thereby avoiding the overall processing of the image blocks to be identified, reducing the computational complexity, and improving the computational efficiency; when processing a large number of fingerprint images, this target area-based segmentation and recognition method can significantly reduce the amount of data that needs to be stored and processed, thereby optimizing the use of storage space; due to the use of a grayscale threshold-based pixel block classification method and a target area-based target selection method, illegal intrusions and security vulnerabilities can be effectively avoided, thereby improving the security of the access control system.

[0146] Example 10

[0147] In this embodiment, the area of ​​the first target area is smaller than the area of ​​the second target area, and the ratio between the area of ​​the first target area and the area of ​​the second target area is in the range of 1:1.7-1:2.3; at the same time, the first block number threshold is smaller than the second block number threshold, and the ratio between the first block number threshold and the second block number threshold is in the range of 1:2.1-1:2.8.

[0148] The working principle of the above technical solution is as follows: First, for a specific area in the fingerprint image, the areas of the first target area and the second target area are calculated, with the ratio between the first target area and the second target area ranging from 1:1.7 to 1:2.3. This means that after the target area is calculated, the system will compare and filter, and only target areas that meet the specified ratio range will be retained; the ratio between the first block number threshold and the second block number threshold ranges from 1:2.1 to 1:2.8.

[0149] The effects of the above technical solution are: by limiting and screening the target area and numerical threshold, the accuracy and precision of fingerprint image processing can be improved. Only target areas and values ​​that meet a specific ratio range will be retained, thereby reducing the possibility of misjudgment and misidentification; setting a specific ratio range and numerical threshold can enhance the system's resistance to noise and interference. This means that even in the presence of a certain degree of interference, the system can still better identify and extract fingerprint features; by flexibly setting the ratio range and numerical threshold, the technical solution may have a certain degree of adaptability and can be applied to fingerprint images of different types and qualities, and to a certain extent overcome the challenges brought about by image quality and environmental changes; once the appropriate ratio range and numerical threshold are determined, the technical solution may be able to quickly and effectively process a large amount of fingerprint image data, thereby improving processing efficiency and response speed.

[0150] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A fingerprint recognition access control method, It is characterized in that The fingerprint recognition access control method comprises: Real-time collection of fingerprint images for fingerprint identification of the same user; According to the grayscale value of the pixel block of the fingerprint part of the currently collected fingerprint image, a first grayscale threshold and a second grayscale threshold corresponding to the current fingerprint image are obtained; wherein the first grayscale threshold is greater than the second grayscale threshold; Acquire a plurality of image blocks to be identified by using the first grayscale threshold and the second grayscale threshold, and acquire a comprehensive similarity value of the current fingerprint image in combination with the grayscale values ​​of the image blocks to be identified; When the comprehensive similarity value is not lower than the preset similarity threshold, it is determined that the fingerprint image of the current user passes the fingerprint verification.

2. According to the fingerprint recognition access control method of claim 1, It is characterized in that According to the grayscale value of the pixel block of the fingerprint part of the currently collected fingerprint image, the first grayscale threshold and the second grayscale threshold corresponding to the current fingerprint image are obtained, including: Extracting the grayscale value of the pixel block of the fingerprint part of the current fingerprint image; Extracting the grayscale values ​​of the pixel blocks of the fingerprint portion that are lower than the optimal threshold corresponding to the fingerprint image as the first grayscale value data; Extracting the grayscale value of the pixel block that is not lower than the optimal threshold corresponding to the fingerprint image from the pixel block of the fingerprint part as the second grayscale value data; Using the first gray value data to set a first candidate gray threshold value of the fingerprint portion; Using the second gray value data to set a second candidate gray threshold value of the fingerprint portion; The first candidate grayscale threshold is compared with the second candidate grayscale threshold, the larger one of the first candidate grayscale threshold and the second candidate grayscale threshold is used as the first grayscale threshold, and the smaller one of the first candidate grayscale threshold and the second candidate grayscale threshold is used as the second grayscale threshold.

3. According to the fingerprint recognition access control method of claim 1, It is characterized in that Using the first grayscale threshold and the second grayscale threshold to obtain a plurality of image blocks to be identified, and combining the grayscale values ​​of the image blocks to be identified to obtain a comprehensive similarity value of the current fingerprint image, including: Segmenting the fingerprint image by using the first grayscale threshold and the second grayscale threshold to obtain a plurality of first image blocks to be identified and second image blocks to be identified; Comparing the plurality of first image blocks to be identified and the second image blocks to be identified with the fingerprint positions corresponding to the fingerprint reference images entered into the database by the user in sequence, and obtaining the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified; The comprehensive similarity value of the current fingerprint image is obtained by using the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified respectively and combining with the gray value of the image to be identified.

4. According to the fingerprint recognition access control method of claim 3, It is characterized in that The fingerprint image is segmented by the first grayscale threshold and the second grayscale threshold to obtain a plurality of image blocks to be identified, including: Extracting the grayscale values ​​of all pixel blocks of the fingerprint part in the fingerprint image; Extracting pixel blocks whose grayscale values ​​exceed the first grayscale threshold as first-category pixel blocks; Retrieving a target region in which the number of blocks containing the first type of pixel blocks exceeds a preset first block number threshold within the area of ​​the first target region from the first type of pixel blocks as the first target region; Segmenting the fingerprint image according to the position of the first target area to obtain a first image block to be identified; Extracting pixel blocks whose grayscale values ​​exceed the second grayscale threshold but do not exceed the first grayscale threshold as second-category pixel blocks; Retrieving, from the second type of pixel blocks, a target region whose number of blocks including the second type of pixel blocks exceeds a preset second block number threshold within the area of ​​the second target region as the second target region; The fingerprint image is segmented according to the position of the second target area to obtain a second image block to be identified.

5. According to the fingerprint recognition access control method of claim 4, It is characterized in that The area of ​​the first target area is smaller than that of the second target area, and the ratio between the area of ​​the first target area and the area of ​​the second target area is in the range of 1:1.7-1:2.3; at the same time, the first block number threshold is smaller than the second block number threshold, and the ratio between the first block number threshold and the second block number threshold is in the range of 1:2.1-1:2.

8.

6. A fingerprint recognition access control system, It is characterized in that The fingerprint recognition access control system comprises: Image acquisition module: real-time acquisition of fingerprint images for fingerprint identification of the same user; Threshold acquisition module: according to the gray value of the pixel block of the fingerprint part of the currently collected fingerprint image, obtain the first gray threshold and the second gray threshold corresponding to the current fingerprint image; wherein the first gray threshold is greater than the second gray threshold; An image block acquisition module: using the first grayscale threshold and the second grayscale threshold to acquire a plurality of image blocks to be identified, and combining the grayscale values ​​of the image blocks to be identified to acquire a comprehensive similarity value of the current fingerprint image; Similarity judgment module: when the comprehensive similarity value is not lower than the preset similarity threshold, it is determined that the fingerprint image of the current user passes the fingerprint verification.

7. According to claim 6, the fingerprint recognition access control system, It is characterized in that The threshold acquisition module comprises: Gray value extraction module: extracts the gray value of the pixel block of the fingerprint part of the current fingerprint image; A first gray value data module: extracting the gray value of the pixel block of the fingerprint part which is lower than the optimal threshold value corresponding to the fingerprint image as the first gray value data; A second gray value data module: extracting the gray value of the pixel block of the fingerprint part which is not lower than the optimal threshold value corresponding to the fingerprint image as the second gray value data; A first candidate grayscale threshold module: using the first grayscale value data to set a first candidate grayscale threshold of the fingerprint part; A second candidate grayscale threshold module: using the second grayscale value data to set a second candidate grayscale threshold of the fingerprint part; Threshold comparison module: compares the first candidate grayscale threshold with the second candidate grayscale threshold, takes the larger one of the first candidate grayscale threshold and the second candidate grayscale threshold as the first grayscale threshold, and takes the smaller one of the first candidate grayscale threshold and the second candidate grayscale threshold as the second grayscale threshold.

8. According to claim 6, the fingerprint recognition access control system, It is characterized in that The image block acquisition module comprises: An image block acquisition module to be identified: segmenting the fingerprint image by the first grayscale threshold and the second grayscale threshold to obtain a plurality of first image blocks to be identified and second image blocks to be identified; A similarity value comparison module is used to compare the plurality of first image blocks to be identified and the second image blocks to be identified with the fingerprint positions corresponding to the fingerprint reference images that the user has entered into the database, and obtain the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified; Similarity value acquisition module: using the similarity values ​​corresponding to the plurality of first image blocks to be identified and the second image blocks to be identified respectively and combining with the gray value of the image to be identified to acquire the comprehensive similarity value of the current fingerprint image.

9. According to claim 8, the fingerprint recognition access control system, It is characterized in that The module for acquiring the image block to be identified comprises: Gray value extraction module: extracts the gray values ​​of all pixel blocks of the fingerprint part in the fingerprint image; A first-category pixel block module: extracting pixel blocks whose grayscale values ​​exceed the first grayscale threshold as first-category pixel blocks; A target region setting module: retrieves a target region whose number of blocks including the first type of pixel blocks exceeds a preset first block number threshold in the first type of pixel blocks as a first target region; A first image block to be identified module: segmenting the fingerprint image according to the position of the first target area to obtain a first image block to be identified; A second-category pixel block determination module: extracting pixel blocks whose grayscale values ​​exceed the second grayscale threshold but do not exceed the first grayscale threshold as second-category pixel blocks; An area region calling module: calling, from the second type of pixel blocks, a target region whose number of blocks containing the second type of pixel blocks in the second target region exceeds a preset second block number threshold value as the second target region; Second target area module: segment the fingerprint image according to the position of the second target area to obtain a second image block to be identified.

10. The fingerprint recognition access control system according to claim 9, It is characterized in that The area of ​​the first target area is smaller than that of the second target area, and the ratio between the area of ​​the first target area and the area of ​​the second target area is in the range of 1:1.7-1:2.3; at the same time, the first block number threshold is smaller than the second block number threshold, and the ratio between the first block number threshold and the second block number threshold is in the range of 1:2.1-1:2.8.

Images