Biological feature recognition method and system

Abstract

The invention belongs to the field of biological feature recognition, and discloses a biological feature recognition method and system, and the method comprises the steps: S1, carrying out the calculation of a first image which is stored in a database and is input in advance and comprises biological feature information, dividing each first image into a plurality of first comparison regions, calculating a first comparison coefficient of each first comparison region, storing all the first comparison areas and the first comparison coefficients; s2, acquiring a second image containing biological feature information of a person needing biological feature recognition; and S3, comparing the second image with each first image in sequence, judging whether a first image conforming to an identity verification standard exists in a database, and if yes, indicating that biological feature recognition is passed. According to the method, the non-similarity of the first comparison area containing more feature information is preferentially obtained, the distribution information of the first comparison area with the similarity meeting the requirement is dynamically introduced, and the judgment result can be obtained through fewer comparison times.

Description

Technical Field

[0001] The present invention relates to the field of biometric identification, and in particular to a biometric identification method and system. Background Art

[0002] Biometric recognition refers to obtaining images containing human biological features such as facial images, fingerprint images, pupil images, etc., then extracting features from these images, and comparing the extracted features with the features of pre-recorded images of the same type (for example, calculating similarity), and determining whether biometric recognition has been passed based on the comparison results.

[0003] In the prior art, it is usually necessary to first obtain the features of the entire image, and then compare based on the obtained features. If the number of pre-recorded images is too large, the speed of biometric recognition will be too slow. In order to improve the efficiency of recognition, the prior art also has a method of first dividing into multiple areas of the same size, and then comparing based on the area. The advantage of this method is that it does not need to calculate all pixels to obtain features. Only the features of a part of the area need to be calculated each time. When more areas fail to pass the feature comparison, it means that the remaining areas no longer need to be compared, which can further improve the efficiency of feature comparison. However, this partition comparison method also has certain defects. That is, since there is no restriction on the comparison order of the areas, if the areas that are compared first are areas with less feature information, it will also take a long time to obtain the comparison results. Summary of the invention

[0004] The purpose of the present invention is to disclose a biometric identification method and system to solve the technical problems raised in the background technology.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] The present invention provides a biometric feature recognition method, comprising:

[0007] S1, calculating the first images containing biometric information that are pre-entered and stored in the database, dividing each first image into a plurality of first comparison areas, calculating a first comparison coefficient for each first comparison area, and storing all the first comparison areas and first comparison coefficients;

[0008] S2, acquiring a second image containing biometric information of a person who needs to undergo biometric identification;

[0009] S3, comparing the second image with each first image in turn to determine whether there is a first image in the database that meets the identity authentication standard. If so, it means that the biometric identification is passed and the comparison ends;

[0010] For the first image P1, whether P1 meets the identity verification standard is determined in the following manner:

[0011] S30, using UP1 to represent the set of first comparison areas corresponding to P1, obtaining the first comparison area ARE1 with the largest first comparison coefficient in UP1, and storing ARE1 in the set UP2;

[0012] S31, obtain the non-similarity score of ARE1, and delete ARE1 from UP1;

[0013] S32, determining whether the sum of the non-similarity scores of the first comparison area in UP2 is greater than a set score threshold, if so, it means that P1 does not meet the identity authentication standard, if not, proceeding to S33;

[0014] S33, respectively calculating a second comparison coefficient for each first comparison area in UP1 based on the first comparison coefficient and UP2;

[0015] S34, obtaining the non-similarity score of the first comparison region with the largest second comparison coefficient in UP1, deleting the first comparison region with the largest second comparison coefficient from UP1, and storing the first comparison region with the largest second comparison coefficient in UP2;

[0016] S35, determining whether the number of the remaining first comparison areas in UP1 is less than 1, if so, proceeding to S32, if not, it indicates that P1 meets the identity authentication standard.

[0017] Preferably, dividing the first image into a plurality of first comparison areas comprises:

[0018] Processing the first image using a preprocessing algorithm to obtain an image PF;

[0019] NL and NW are used to represent the length and width of PF, respectively;

[0020] Divide PF into The length is , the width is The image area is N, where N represents a preset integer;

[0021] The obtained image area is enlarged to obtain a plurality of first comparison areas.

[0022] Preferably, the obtained image area is enlarged to obtain a plurality of first comparison areas, including:

[0023] S41, taking all image regions as elements in a set ARU;

[0024] S42, randomly extract an image region ru from ARU, perform enlargement processing on ru to obtain a first comparison region, and store the obtained first comparison region into the set CMPU;

[0025] S43, determining whether the ARU still has an image area, if so, proceeding to the second step, if not, taking the first comparison area in the CMPU as the determined first comparison area.

[0026] Preferably, enlarging ru to obtain a first comparison area includes:

[0027] S51, taking ru as the comparison target, and storing ru into the set FA;

[0028] S52, obtaining a set ruA of all image regions adjacent to the comparison target in ARU;

[0029] S53, respectively calculating the competition value of each image region in ruA;

[0030] S54, determining whether the maximum value among all the competitive values ​​is greater than the set competitive value threshold, if so, storing the image region with the largest competitive value in ruA into the set FA, and proceeding to S55; if not, stopping the processing, and splicing all the image regions in FA to obtain the first comparison region;

[0031] S55, deleting the image area in FA from ARU;

[0032] S56, taking the image area with the largest competition value in ruA as the updated comparison target, and entering S52.

[0033] Preferably, the first image is processed using a preprocessing algorithm to obtain the image PF, including:

[0034] Performing noise reduction processing on the first image to obtain an indirect image;

[0035] The indirect image is enhanced to obtain the image PF.

[0036] Preferably, the calculation formula of the first comparison coefficient is:

[0037]

[0038] is the first comparison coefficient of the first comparison area q, is the number of pixels belonging to the set EG existing in the first comparison area q, The number of pixels in the first comparison area q, represents the distance between the coordinates of the center of the first comparison area q and the coordinates of the center of the first image, represents the length of the first image, qu is the set of pixels in the first comparison area q, is the image gradient of pixel z, It represents the maximum value of the image gradient of all the pixels in the first comparison area, and d1, d2 and d3 are the first weighting factor, the second weighting factor and the third weighting factor respectively.

[0039] Preferably, the process of obtaining EG is as follows:

[0040] Calculate the detection value in the horizontal direction and the detection value in the vertical direction of each pixel in the first comparison area q respectively;

[0041] The comparison value of each pixel in the first comparison area q is calculated using the following formula:

[0042]

[0043] Represents the comparison value of pixel c, and Respectively represent the detection value of the horizontal direction and the detection value of the vertical direction of the pixel c;

[0044] The pixel points whose comparison values ​​are greater than the set comparison value threshold are taken as elements of EG.

[0045] Preferably, for the first comparison area im, the process of obtaining the non-similarity score of im includes:

[0046] Store the coordinates of all pixels in im into the set LKim;

[0047] Acquire a second comparison area composed of all pixel points corresponding to the coordinates in LKim in the second image PS;

[0048] Calculate the similarity between im and the second comparison area;

[0049] Determine whether the similarity is greater than the pre-set similarity threshold. If not, use the following formula to calculate the non-similarity score of im :

[0050]

[0051] is the first comparison coefficient of im, CMPU1 is the set of the first comparison areas in P1, A first comparison coefficient representing a first comparison region i;

[0052] If so, the non-similarity score of im is 0.

[0053] Preferably, calculating the second comparison coefficient of each first comparison area in UP1 based on the first comparison coefficient and UP2 respectively includes:

[0054] The second comparison coefficient is calculated using the following formula:

[0055]

[0056] is the second comparison coefficient of the first comparison area j, is the first comparison coefficient of the first comparison area j, represents the number of first comparison areas belonging to UP2 among all first comparison areas adjacent to the first comparison area j, NUP2 represents the total number of first comparison areas in UP2, represents the fourth weighting factor.

[0057] The present invention also provides a biometric feature recognition system, including a preprocessing module, an acquisition module and a comparison module;

[0058] The preprocessing module is used to calculate the first images containing biometric information that are pre-entered and stored in the database, divide each first image into a plurality of first comparison areas, calculate the first comparison coefficient of each first comparison area, and store all the first comparison areas and the first comparison coefficients;

[0059] The acquisition module is used to acquire a second image containing biometric information of a person who needs to undergo biometric identification;

[0060] The comparison module is used to compare the second image with each first image in turn to determine whether there is a first image in the database that meets the identity authentication standard. If so, it means that the biometric identification has passed and the comparison ends;

[0061] For the first image P1, whether P1 meets the identity verification standard is determined in the following manner:

[0062] S30, using UP1 to represent the set of first comparison areas corresponding to P1, obtaining the first comparison area ARE1 with the largest first comparison coefficient in UP1, and storing ARE1 in the set UP2;

[0063] S31, obtain the non-similarity score of ARE1, and delete ARE1 from UP1;

[0064] S32, determining whether the sum of the non-similarity scores of the first comparison area in UP2 is greater than a set score threshold, if so, it means that P1 does not meet the identity authentication standard, if not, proceeding to S33;

[0065] S33, respectively calculating a second comparison coefficient for each first comparison area in UP1 based on the first comparison coefficient and UP2;

[0066] S34, obtaining the non-similarity score of the first comparison region with the largest second comparison coefficient in UP1, deleting the first comparison region with the largest second comparison coefficient from UP1, and storing the first comparison region with the largest second comparison coefficient in UP2;

[0067] S35, determining whether the number of the remaining first comparison areas in UP1 is less than 1, if so, proceeding to S32, if not, it indicates that P1 meets the identity authentication standard.

[0068] Beneficial effects:

[0069] The present invention calculates the first comparison area and the first comparison coefficient in advance, and then in the process of judging whether there is a first image that meets the identity authentication standard in a second database, first calculates the non-similarity of the first comparison area with the largest first comparison coefficient, and then cyclically obtains the second comparison coefficient for the remaining first comparison areas with undetermined non-similarity based on the first comparison coefficient, and determines the comparison order by the second comparison coefficient, so that the non-similarity can be obtained preferentially for the first comparison area containing more feature information, and the second comparison coefficient dynamically introduces the distribution information of the first comparison area whose similarity meets the requirements during the calculation process, so that the first comparison area with a high correlation with the already determined high similarity area and more judgment significance can be judged more preferentially, which is conducive to judging whether the first image meets the identity authentication standard with fewer comparison times, and can effectively improve the judgment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0071] Figure 1 A schematic diagram of a biometric identification method of the present invention. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] The present invention provides a biometric feature recognition method, comprising:

[0074] S1, calculating the first images containing biometric information that are pre-entered and stored in the database, dividing each first image into a plurality of first comparison areas, calculating a first comparison coefficient for each first comparison area, and storing all the first comparison areas and first comparison coefficients;

[0075] The database of the present invention can be a local database or a cloud database. In some small or local biometric recognition systems, image data may be stored in a local database (such as a relational database or a non-relational database). These databases may be data stored on a server, workstation, or embedded device. In larger-scale systems or systems that require remote access, pre-entered images are usually stored in a cloud database. Cloud databases can provide the advantages of higher scalability, fault tolerance, and distributed storage. Common cloud service providers such as AWS, Google Cloud, Microsoft Azure, etc. all provide data storage solutions related to biometric recognition.

[0076] The authorized person pre-enters a first image containing biometric information, and the first image provides a basis for the subsequent biometric identification process.

[0077] S2, acquiring a second image containing biometric information of a person who needs to undergo biometric identification;

[0078] The first image and the second image of the present invention have the same image type, which may be a face image, a fingerprint image, a pupil image, or the like.

[0079] Furthermore, the first image and the second image of the present invention have the same resolution.

[0080] S3, comparing the second image with each first image in turn to determine whether there is a first image in the database that meets the identity authentication standard. If so, it means that the biometric identification has passed and the comparison ends; if not, it means that the biometric identification has not passed;

[0081] For the first image P1, whether P1 meets the identity verification standard is determined in the following manner:

[0082] S30, using UP1 to represent the set of first comparison areas corresponding to P1, obtaining the first comparison area ARE1 with the largest first comparison coefficient in UP1, and storing ARE1 in the set UP2;

[0083] S31, obtain the non-similarity score of ARE1, and delete ARE1 from UP1;

[0084] S32, determining whether the sum of the non-similarity scores of the first comparison area in UP2 is greater than a set score threshold, if so, it means that P1 does not meet the identity authentication standard, if not, proceeding to S33;

[0085] S33, respectively calculating a second comparison coefficient for each first comparison area in UP1 based on the first comparison coefficient and UP2;

[0086] S34, obtaining the non-similarity score of the first comparison region with the largest second comparison coefficient in UP1, deleting the first comparison region with the largest second comparison coefficient from UP1, and storing the first comparison region with the largest second comparison coefficient in UP2;

[0087] S35, determining whether the number of the remaining first comparison areas in UP1 is less than 1, if so, proceeding to S32, if not, it indicates that P1 meets the identity authentication standard.

[0088] In the process of comparing the second image with the first image, the present invention calculates the non-similarity score. When it is found that the non-similarity score is greater than the set score threshold, the comparison of the current first image is stopped and the comparison of the next first image is continued. In this way, the comparison result can be obtained without comparing all the pixels, which can effectively improve the efficiency of the comparison.

[0089] The score threshold of the present invention may be a value between 0.2 and 0.3, such as 0.25. The value of the score threshold may be adjusted according to the safety requirement. The higher the safety requirement, the lower the score threshold is set.

[0090] In the process of performing regional comparison, the present invention does not determine the order of comparison based on the static first comparison coefficient, because this cannot utilize the distribution information of the image details in the second image and the position information of the area with higher similarity, resulting in that when the comparison order is determined based on the first comparison coefficient, after comparing the first comparison area with a higher comparison order, it may be that the position difference between the first comparison areas is too large, and the local areas with a larger range cannot be continuously compared well, resulting in the comparison result being not representative enough, that is, more first comparison areas need to be compared to determine whether the identity authentication standard is met. After the present invention introduces dynamic position data, it can give priority to comparing the local areas with a larger range with higher first comparison coefficients, and after comparing multiple first comparison areas with smaller areas, it can simultaneously compare the local areas with a larger area formed by multiple first comparison areas with similar positions. This makes the comparison results with a higher comparison order more representative, and the comparison results can be obtained with fewer comparison times. Preferably, the first image is divided into multiple first comparison areas, including:

[0091] Processing the first image using a preprocessing algorithm to obtain an image PF;

[0092] NL and NW are used to represent the length and width of PF, respectively;

[0093] Divide PF into The length is , the width is The image area is N, where N represents a preset integer;

[0094] The obtained image area is enlarged to obtain a plurality of first comparison areas.

[0095] The preset integer of the present invention may be 50 or 100, or may be a positive integer of other values, and may be adjusted as required. The higher the resolution of the image, the larger the value of the preset integer is generally set.

[0096] Using preprocessing algorithms for processing can improve the recognition accuracy in subsequent processing stages.

[0097] Preferably, the obtained image area is enlarged to obtain a plurality of first comparison areas, including:

[0098] S41, taking all image regions as elements in a set ARU;

[0099] S42, randomly extract an image region ru from ARU, perform enlargement processing on ru to obtain a first comparison region, and store the obtained first comparison region into the set CMPU;

[0100] S43, determining whether the ARU still has an image area, if so, proceeding to the second step, if not, taking the first comparison area in the CMPU as the determined first comparison area.

[0101] The above process is to continuously extract an image region ru from ARU for enlargement processing, and the image region actually pointed to by ru is continuously changed until there is no image region in ARU, and then the processing process is terminated, thereby obtaining multiple first comparison regions.

[0102] Preferably, enlarging ru to obtain a first comparison area includes:

[0103] S51, taking ru as the comparison target, and storing ru into the set FA;

[0104] S52, obtaining a set ruA of all image regions adjacent to the comparison target in ARU;

[0105] S53, respectively calculating the competition value of each image region in ruA;

[0106] S54, determining whether the maximum value among all the competitive values ​​is greater than the set competitive value threshold, if so, storing the image region with the largest competitive value in ruA into the set FA, and proceeding to S55; if not, stopping the processing, and splicing all the image regions in FA to obtain the first comparison region;

[0107] S55, deleting the image area in FA from ARU;

[0108] S56, taking the image area with the largest competition value in ruA as the updated comparison target, and entering S52.

[0109] The enlargement processing of the present invention includes the image area in ruA that is adjacent to the comparison target position and has the largest competition value into the range of the first comparison area where the comparison target is located, realizing the adaptive expansion of the area of ​​the first comparison area, and being able to put as many image areas that originally belonged to the same area into the same first comparison area as possible. In this way, the obtained first comparison area has an irregular shape, but can include a local area (such as the mouth area) as completely as possible, which is conducive to improving the integrity of the image features obtained in the comparison process when performing a regional comparison with the second image, and obtaining a more accurate comparison result.

[0110] Preferably, the calculation formula of the competitive value is:

[0111]

[0112] represents the competitive value of image region r in ruA, represents the edge judgment value, and Respectively represent the number of pixels with grayscale values ​​equal to v in r and the comparison target, represents the edge judgment weight;

[0113] The calculation formula of the edge judgment value is:

[0114]

[0115] and are the average values ​​of the horizontal and vertical coordinates of the pixel points belonging to the edge of the image in the image region r, respectively; and They are respectively the average values ​​of the horizontal and vertical coordinates of the pixel points belonging to the edge of the image in the comparison target.

[0116] The competitive value of the present invention is calculated from the edge judgment value and the difference in the number of pixels of various gray values. If the edge judgment value is smaller, the difference in the number of pixels of various gray values ​​is smaller, then the probability that r and the comparison target belong to the same area is higher, thus realizing the adaptive acquisition of the first comparison area. The edge judgment value is obtained by calculating the difference between the average coordinates of the pixels belonging to the edge of the image. The larger the difference, the smaller the correlation between the two image areas. Since not only the difference in the number of pixels of different gray values ​​is taken into account, but also the difference in the position of the edges in the image area is taken into account, the comprehensive difference between the two image areas can be more accurately represented.

[0117] Preferably, the edge judgment weight is .

[0118] Preferably, the competition value threshold is 0.7.

[0119] Preferably, the first image is processed using a preprocessing algorithm to obtain the image PF, including:

[0120] Performing noise reduction processing on the first image to obtain an indirect image;

[0121] The indirect image is enhanced to obtain the image PF.

[0122] The noise reduction process of the present invention can be implemented by algorithms such as median filtering, and the enhancement process can be implemented by histogram equalization, which adjusts the contrast of the image to make the grayscale distribution of the image uniform, thereby achieving the effect of enhancing the image details.

[0123] Preferably, the calculation formula of the first comparison coefficient is:

[0124]

[0125] is the first comparison coefficient of the first comparison area q, is the number of pixels belonging to the set EG existing in the first comparison area q, The number of pixels in the first comparison area q, represents the distance between the coordinates of the center of the first comparison area q and the coordinates of the center of the first image, represents the length of the first image, qu is the set of pixels in the first comparison area q, is the image gradient of pixel z, It represents the maximum value of the image gradient of all the pixels in the first comparison area, and d1, d2 and d3 are the first weighting factor, the second weighting factor and the third weighting factor respectively.

[0126] The first comparison coefficient of the present invention is obtained based on static data, so it can be calculated and stored first, so that it can be directly called when used without the need for further calculation. The first comparison area for comparison can be determined more quickly, which is beneficial to improving the efficiency of biometric recognition.

[0127] The first comparison coefficient takes into account the number of pixels in EG, the distance from the center of the first image, and the dispersion of the image gradient. The more pixels in EG, the smaller the distance from the center of the first image, and the greater the dispersion of the image gradient, the larger the first comparison coefficient is, indicating that the first comparison area contains more important image details, and the greater the impact of the result obtained after comparison. When comparing with the second image, the first comparison area should be given priority for comparison.

[0128] Preferably, the first weighting factor, the second weighting factor and the third weighting factor are all 0.33.

[0129] Preferably, the process of obtaining EG is as follows:

[0130] Calculate the detection value in the horizontal direction and the detection value in the vertical direction of each pixel in the first comparison area q respectively;

[0131] The comparison value of each pixel in the first comparison area q is calculated using the following formula:

[0132]

[0133] Represents the comparison value of pixel c, and Respectively represent the detection value of the horizontal direction and the detection value of the vertical direction of the pixel c;

[0134] The pixel points whose comparison values ​​are greater than the set comparison value threshold are taken as elements of EG.

[0135] By calculating the detection value, the pixel points with rich contour information can be quickly screened out as elements in the EG, so that the calculation process of the first comparison coefficient can refer to the pixel points with rich contour information to improve the effectiveness of the first comparison coefficient in representing the importance of the first comparison area.

[0136] The calculation formula for the detection value in the horizontal direction is:

[0137]

[0138] x and y are the horizontal and vertical coordinates of pixel c respectively; is the gray value of the pixel with the horizontal coordinate x+1 and the vertical coordinate y+1;

[0139] The calculation formula for the detection value in the vertical direction is:

[0140] .

[0141] The comparison value threshold may be set to 100.

[0142] Preferably, for the first comparison area im, the process of obtaining the non-similarity score of im includes:

[0143] Store the coordinates of all pixels in im into the set LKim;

[0144] Acquire a second comparison area composed of all pixel points corresponding to the coordinates in LKim in the second image PS;

[0145] Calculate the similarity between im and the second comparison area;

[0146] Determine whether the similarity is greater than the pre-set similarity threshold. If not, use the following formula to calculate the non-similarity score of im :

[0147]

[0148] is the first comparison coefficient of im, CMPU1 is the set of the first comparison areas in P1, A first comparison coefficient representing a first comparison region i;

[0149] If so, the non-similarity score of im is 0.

[0150] The non-similarity score of the present invention is represented by the ratio of the first comparison coefficient of im to the sum of the first comparison coefficients of all first comparison areas. Therefore, if the first comparison coefficient of im is larger, when the similarity is less than a similarity threshold set in advance, the corresponding non-similarity score of im will be higher, so that when the difference between the first image and the second image is large, the comparison result can be obtained by comparing only part of the first comparison area.

[0151] The similarity between im and the second comparison region may be calculated by a cosine similarity calculation algorithm, and accordingly, the similarity threshold may be 0.8.

[0152] Preferably, calculating the second comparison coefficient of each first comparison area in UP1 based on the first comparison coefficient and UP2 respectively includes:

[0153] The second comparison coefficient is calculated using the following formula:

[0154]

[0155] is the second comparison coefficient of the first comparison area j, is the first comparison coefficient of the first comparison area j, represents the number of first comparison areas belonging to UP2 among all first comparison areas adjacent to the first comparison area j, NUP2 represents the total number of first comparison areas in UP2, represents the fourth weighting factor.

[0156] The second comparison coefficient of the present invention is obtained based on the first comparison coefficient. Since the first comparison coefficient can be directly called during calculation, the calculation speed is very fast. The second comparison coefficient introduces a dynamic gray value distribution related to the second image. When there are more other first comparison areas around j that meet the requirements of similarity with the local area in the second image, the larger the second comparison coefficient corresponding to j, the higher the possibility that the first comparison area around j belongs to the local area of ​​the whole. In this way, the comparison of a larger continuous range can be given priority. While performing a comparison of a small range, the comparison of a large range can be achieved as quickly as possible, which is conducive to obtaining a more comprehensive comparison result and improving the accuracy of the comparison based on a small part of the first comparison area to determine whether the first image meets the requirements.

[0157] The fourth weighting factor may be 0.8.

[0158] The present invention also provides a biometric feature recognition system, including a preprocessing module, an acquisition module and a comparison module;

[0159] The preprocessing module is used to calculate the first images containing biometric information that are pre-entered and stored in the database, divide each first image into a plurality of first comparison areas, calculate the first comparison coefficient of each first comparison area, and store all the first comparison areas and the first comparison coefficients;

[0160] The acquisition module is used to acquire a second image containing biometric information of a person who needs to undergo biometric identification;

[0161] The comparison module is used to compare the second image with each first image in turn to determine whether there is a first image in the database that meets the identity authentication standard. If so, it means that the biometric identification has passed and the comparison ends;

[0162] For the first image P1, whether P1 meets the identity verification standard is determined in the following manner:

[0163] S30, using UP1 to represent the set of first comparison areas corresponding to P1, obtaining the first comparison area ARE1 with the largest first comparison coefficient in UP1, and storing ARE1 in the set UP2;

[0164] S31, obtain the non-similarity score of ARE1, and delete ARE1 from UP1;

[0165] S32, determining whether the sum of the non-similarity scores of the first comparison area in UP2 is greater than a set score threshold, if so, it means that P1 does not meet the identity authentication standard, if not, proceeding to S33;

[0166] S33, respectively calculating a second comparison coefficient for each first comparison area in UP1 based on the first comparison coefficient and UP2;

[0167] S34, obtaining the non-similarity score of the first comparison region with the largest second comparison coefficient in UP1, deleting the first comparison region with the largest second comparison coefficient from UP1, and storing the first comparison region with the largest second comparison coefficient in UP2;

[0168] S35, determining whether the number of the remaining first comparison areas in UP1 is less than 1, if so, proceeding to S32, if not, it indicates that P1 meets the identity authentication standard.

[0169] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A biometric identification method, characterized in that: include: S1, calculating the first images containing biometric information that are pre-entered and stored in the database, dividing each first image into a plurality of first comparison areas, calculating a first comparison coefficient for each first comparison area, and storing all the first comparison areas and first comparison coefficients; S2, acquiring a second image containing biometric information of a person who needs to undergo biometric identification; S3, comparing the second image with each first image in turn to determine whether there is a first image in the database that meets the identity authentication standard. If so, it means that the biometric identification is passed and the comparison ends; For the first image P1, whether P1 meets the identity verification standard is determined in the following manner: S30, using UP1 to represent the set of first comparison areas corresponding to P1, obtaining the first comparison area ARE1 with the largest first comparison coefficient in UP1, and storing ARE1 in the set UP2; S31, obtain the non-similarity score of ARE1, and delete ARE1 from UP1; S32, determining whether the sum of the non-similarity scores of the first comparison area in UP2 is greater than a set score threshold, if so, it means that P1 does not meet the identity authentication standard, if not, proceeding to S33; S33, respectively calculating a second comparison coefficient for each first comparison area in UP1 based on the first comparison coefficient and UP2; S34, obtaining the non-similarity score of the first comparison region with the largest second comparison coefficient in UP1, deleting the first comparison region with the largest second comparison coefficient from UP1, and storing the first comparison region with the largest second comparison coefficient in UP2; S35, determining whether the number of the remaining first comparison areas in UP1 is less than 1, if so, proceeding to S32, if not, it indicates that P1 meets the identity authentication standard.

2. A biometric feature recognition method according to claim 1, characterized in that: Dividing the first image into a plurality of first comparison regions comprises: Processing the first image using a preprocessing algorithm to obtain an image PF; NL and NW are used to represent the length and width of PF, respectively; Divide PF into The length is , the width is The image area is N, where N represents a preset integer; The obtained image area is enlarged to obtain a plurality of first comparison areas.

3. A biometric feature recognition method according to claim 2, characterized in that: The obtained image region is enlarged to obtain a plurality of first comparison regions, including: S41, taking all image regions as elements in a set ARU; S42, randomly extract an image region ru from ARU, perform enlargement processing on ru to obtain a first comparison region, and store the obtained first comparison region into the set CMPU; S43, determining whether the ARU still has an image area, if so, proceeding to the second step, if not, taking the first comparison area in the CMPU as the determined first comparison area.

4. A biometric feature recognition method according to claim 3, characterized in that: Performing an enlargement process on ru to obtain a first comparison area, including: S51, taking ru as the comparison target, and storing ru into the set FA; S52, obtaining a set ruA of all image regions adjacent to the comparison target in ARU; S53, respectively calculating the competition value of each image region in ruA; S54, determining whether the maximum value among all the competitive values ​​is greater than the set competitive value threshold, if so, storing the image region with the largest competitive value in ruA into the set FA, and proceeding to S55; if not, stopping the processing, and splicing all the image regions in FA to obtain the first comparison region; S55, deleting the image area in FA from ARU; S56, taking the image area with the largest competition value in ruA as the updated comparison target, and entering S52.

5. A biometric feature recognition method according to claim 2, characterized in that: The first image is processed using a preprocessing algorithm to obtain an image PF, including: Performing noise reduction processing on the first image to obtain an indirect image; The indirect image is enhanced to obtain the image PF.

6. A biometric feature recognition method according to claim 1, characterized in that: The calculation formula of the first comparison coefficient is: ; is the first comparison coefficient of the first comparison area q, is the number of pixels belonging to the set EG existing in the first comparison area q, The number of pixels in the first comparison area q, represents the distance between the coordinates of the center of the first comparison area q and the coordinates of the center of the first image, represents the length of the first image, qu is the set of pixels in the first comparison area q, is the image gradient of pixel z, It represents the maximum value of the image gradient of all the pixels in the first comparison area, and d1, d2 and d3 are the first weighting factor, the second weighting factor and the third weighting factor respectively.

7. A biometric feature recognition method according to claim 6, characterized in that: The process of obtaining EG is as follows: Calculate the detection value in the horizontal direction and the detection value in the vertical direction of each pixel in the first comparison area q respectively; The comparison value of each pixel in the first comparison area q is calculated using the following formula: ; Represents the comparison value of pixel c, and Respectively represent the detection value of the horizontal direction and the detection value of the vertical direction of the pixel c; The pixel points whose comparison values ​​are greater than the set comparison value threshold are taken as elements of EG.

8. A biometric feature recognition method according to claim 6, characterized in that: For the first comparison region im, the process of obtaining the non-similarity score of im includes: Store the coordinates of all pixels in im into the set LKim; Acquire a second comparison area composed of all pixel points corresponding to the coordinates in LKim in the second image PS; Calculate the similarity between im and the second comparison area; Determine whether the similarity is greater than the pre-set similarity threshold. If not, use the following formula to calculate the non-similarity score of im : ; is the first comparison coefficient of im, CMPU1 is the set of the first comparison areas in P1, A first comparison coefficient representing a first comparison region i; If so, the non-similarity score of im is 0.

9. A biometric feature recognition method according to claim 6, characterized in that: Calculating the second comparison coefficient of each first comparison area in UP1 based on the first comparison coefficient and UP2, including: The second comparison coefficient is calculated using the following formula: ; is the second comparison coefficient of the first comparison area j, is the first comparison coefficient of the first comparison area j, represents the number of first comparison areas belonging to UP2 among all first comparison areas adjacent to the first comparison area j, NUP2 represents the total number of first comparison areas in UP2, represents the fourth weighting factor.

10. A biometric recognition system, characterized in that: It includes a preprocessing module, an acquisition module and a comparison module; The preprocessing module is used to calculate the first images containing biometric information that are pre-entered and stored in the database, divide each first image into a plurality of first comparison areas, calculate the first comparison coefficient of each first comparison area, and store all the first comparison areas and the first comparison coefficients; The acquisition module is used to acquire a second image containing biometric information of a person who needs to undergo biometric identification; The comparison module is used to compare the second image with each first image in turn to determine whether there is a first image in the database that meets the identity authentication standard. If so, it means that the biometric identification has passed and the comparison ends; For the first image P1, whether P1 meets the identity verification standard is determined in the following manner: S30, using UP1 to represent the set of first comparison areas corresponding to P1, obtaining the first comparison area ARE1 with the largest first comparison coefficient in UP1, and storing ARE1 in the set UP2; S31, obtain the non-similarity score of ARE1, and delete ARE1 from UP1; S32, determining whether the sum of the non-similarity scores of the first comparison area in UP2 is greater than a set score threshold, if so, it means that P1 does not meet the identity authentication standard, if not, proceeding to S33; S33, respectively calculating a second comparison coefficient for each first comparison area in UP1 based on the first comparison coefficient and UP2; S34, obtaining the non-similarity score of the first comparison region with the largest second comparison coefficient in UP1, deleting the first comparison region with the largest second comparison coefficient from UP1, and storing the first comparison region with the largest second comparison coefficient in UP2; S35, determining whether the number of the remaining first comparison areas in UP1 is less than 1, if so, proceeding to S32, if not, it indicates that P1 meets the identity authentication standard.

Images