Fingerprint image matching method and device, medium and product

Abstract

The invention discloses a fingerprint image matching method and device, a medium and a product, and belongs to the technical field of image recognition, and the matching method comprises the steps: obtaining a to-be-recognized fingerprint image which comprises a plurality of fingerprint feature points; detecting each fingerprint feature point by using a rapid feature point extraction description algorithm, and determining a feature parameter corresponding to each fingerprint feature point; based on the multiple feature parameters and the multiple template feature parameters, the similarity between the fingerprint image and a template fingerprint image is determined, the similarity represents the matching degree of the fingerprint image and the template fingerprint image, and the template feature parameters are parameters corresponding to template fingerprint feature points in the template fingerprint image; the template fingerprint feature points are in one-to-one correspondence with the template feature parameters; and based on the similarity, determining a matching result of the fingerprint image and the template fingerprint image. According to the embodiment of the invention, the recognition accuracy of the fingerprint image can be improved.

Description

Technical Field

[0001] The present application belongs to the field of image recognition technology, and in particular, relates to a fingerprint image matching method, device, medium and product. Background Art

[0002] With the rapid development of information technology, the application scenarios of fingerprints are becoming more and more extensive. In the field of fingerprint recognition of user devices, the fingerprint recognition sensor is placed under the display screen of the user device to generate a fingerprint image through the fingerprint recognition sensor. However, the imaging quality of the above fingerprint image is generally poor, and the image clarity is low, so that the identified fingerprint image has fewer fingerprint feature points, resulting in inaccurate matching results when using the feature point matching algorithm, resulting in a low fingerprint image recognition rate and poor user experience. Summary of the invention

[0003] The embodiments of the present application provide a fingerprint image matching method, device, equipment, medium and product, which can improve the recognition accuracy of fingerprint images.

[0004] In a first aspect, an embodiment of the present application provides a fingerprint image matching method, comprising:

[0005] Acquire a fingerprint image to be identified, the fingerprint image including a plurality of fingerprint feature points;

[0006] Use fast feature point extraction and description algorithm to detect each fingerprint feature point and determine the feature parameters corresponding to each fingerprint feature point;

[0007] Based on multiple feature parameters and multiple template feature parameters, determine the similarity between the fingerprint image and the template fingerprint image, the similarity represents the matching degree between the fingerprint image and the template fingerprint image, the template feature parameters are parameters corresponding to the template fingerprint feature points in the template fingerprint image, and the template fingerprint feature points correspond to the template feature parameters one by one;

[0008] Based on the similarity, the matching result between the fingerprint image and the template fingerprint image is determined.

[0009] According to any of the aforementioned implementations of the first aspect of the present application, the feature parameter includes a feature vector, the template feature parameter includes a template feature vector, and both the feature vector and the template feature vector are multidimensional vectors;

[0010] Based on the multiple feature parameters and the multiple template feature parameters, determining the similarity between the fingerprint image and the template fingerprint image includes:

[0011] Based on the multiple feature vectors and the multiple template feature vectors, the similarity between the fingerprint image and the template fingerprint image is determined.

[0012] According to any of the aforementioned implementations of the first aspect of the present application, determining the similarity between a fingerprint image and a template fingerprint image based on a plurality of feature vectors and a plurality of template feature vectors includes:

[0013] Based on any two template feature vectors, a first covariance matrix is ​​determined, and based on any two feature vectors, a second covariance matrix is ​​determined, wherein the first covariance matrix represents the relative position relationship between the template fingerprint feature points corresponding to any two template feature vectors, and the second covariance matrix represents the relative position relationship between the fingerprint feature points corresponding to any two feature vectors;

[0014] Based on the first covariance matrix and the second covariance matrix, a similarity is determined.

[0015] According to any of the aforementioned implementations of the first aspect of the present application, the first covariance matrix includes a plurality of first row vectors, and the second covariance matrix includes a plurality of second row vectors;

[0016] Determining similarity based on the first covariance matrix and the second covariance matrix includes:

[0017] Based on the plurality of first row vectors and the plurality of second row vectors, a plurality of distance values ​​are determined, wherein one distance value is a distance value between any one of the first row vectors and any one of the second row vectors;

[0018] Determine a distance matrix based on multiple distance values, where the distance matrix represents the relative position relationship between the template fingerprint feature points and the fingerprint feature points;

[0019] Based on the distance matrix, the similarity is determined.

[0020] According to any of the aforementioned implementations of the first aspect of the present application, the distance matrix includes multiple distance row vectors, one distance row vector includes multiple distance values, and based on the distance matrix, determining the similarity includes:

[0021] Based on multiple distance values ​​in multiple distance row vectors in the distance matrix, determine a first distance vector and a second distance vector, the first distance vector being a vector determined based on the minimum distance value of each distance row vector in the multiple distance row vectors, and the second distance vector representing the position of each minimum distance value in the distance matrix;

[0022] Based on the first distance vector and the second distance vector, a similarity is determined.

[0023] According to any of the foregoing implementations of the first aspect of the present application, determining similarity based on the first distance vector and the second distance vector includes:

[0024] Calculate the Euclidean distance between the first distance vector and the second distance vector;

[0025] Based on the Euclidean distance, the similarity is determined.

[0026] According to any of the aforementioned implementations of the first aspect of the present application, the characteristic parameter includes local entropy, and the template characteristic parameter includes template local entropy;

[0027] Based on the multiple feature vectors and the multiple template feature vectors, determining the similarity between the fingerprint image and the template fingerprint image includes:

[0028] Based on the multiple local entropies and the multiple template local entropies, the similarity between the fingerprint image and the template fingerprint image is determined.

[0029] According to any of the aforementioned embodiments of the first aspect of the present application, based on multiple local entropies and multiple template local entropies, determining the similarity between the fingerprint image and the template fingerprint image includes:

[0030] Based on multiple local entropies and multiple template local entropies, multiple feature similarities are determined, where one feature similarity is a similarity determined based on any local entropy and any template local entropy, and the feature similarity represents the degree of similarity between a fingerprint feature point corresponding to any local entropy and a template fingerprint feature point corresponding to any template local entropy;

[0031] Based on multiple feature similarities, similarity is determined.

[0032] According to any of the aforementioned implementations of the first aspect of the present application, based on multiple local entropies and multiple template local entropies, multiple feature similarities are determined, including:

[0033] Based on multiple local entropies and multiple template local entropies, multiple mutual information is determined, and one mutual information is based on the mutual information determined by any local entropy and any template local entropy;

[0034] Normalizing the multiple mutual information to obtain normalized mutual information, where the normalized mutual information includes information obtained by normalizing each mutual information in the multiple mutual information;

[0035] Based on the mutual information and normalized mutual information, the feature similarity is determined.

[0036] According to any of the aforementioned implementations of the first aspect of the present application, before obtaining a fingerprint image to be identified, wherein the fingerprint image includes a plurality of fingerprint feature points, the matching method further includes:

[0037] Acquire an original fingerprint image, where the original fingerprint image includes multiple fingerprint feature points;

[0038] Counting the number of fingerprint feature points of the original fingerprint image to obtain a statistical result;

[0039] When the statistical result includes that the number of fingerprint feature points is less than the threshold, the original fingerprint image is determined to be the fingerprint image.

[0040] According to any of the aforementioned implementations of the first aspect of the present application, before determining the similarity between the fingerprint image and the template fingerprint image based on the multiple feature parameters and the multiple template feature parameters, the matching method further includes:

[0041] Acquire a template fingerprint image, where the template fingerprint image includes a plurality of template fingerprint feature points;

[0042] Using the fast feature point extraction and description algorithm, each template fingerprint feature point is detected and the template feature parameters corresponding to each template fingerprint feature point are determined.

[0043] In a second aspect, an embodiment of the present application provides a fingerprint image matching device, comprising:

[0044] An acquisition module is used to acquire a fingerprint image to be identified, where the fingerprint image includes a plurality of fingerprint feature points;

[0045] The detection module is used to detect each fingerprint feature point using a fast feature point extraction and description algorithm to determine the feature parameters corresponding to each fingerprint feature point;

[0046] A determination module, used to determine the similarity between the fingerprint image and the template fingerprint image based on multiple feature parameters and multiple template feature parameters, the similarity represents the matching degree between the fingerprint image and the template fingerprint image, the template feature parameters are parameters corresponding to the template fingerprint feature points in the template fingerprint image, and the template fingerprint feature points correspond to the template feature parameters one by one;

[0047] The matching module is used to determine the matching result between the fingerprint image and the template fingerprint image based on the similarity.

[0048] According to any of the aforementioned implementations of the second aspect of the present application, the feature parameter includes a feature vector, the template feature parameter includes a template feature vector, and both the feature vector and the template feature vector are multidimensional vectors;

[0049] Determine the module specifically for:

[0050] Based on the multiple feature vectors and the multiple template feature vectors, the similarity between the fingerprint image and the template fingerprint image is determined.

[0051] According to any of the foregoing implementations of the second aspect of the present application, the determination module may be specifically used for:

[0052] Based on any two template feature vectors, a first covariance matrix is ​​determined, and based on any two feature vectors, a second covariance matrix is ​​determined, wherein the first covariance matrix represents the relative position relationship between the template fingerprint feature points corresponding to any two template feature vectors, and the second covariance matrix represents the relative position relationship between the fingerprint feature points corresponding to any two feature vectors;

[0053] Based on the first covariance matrix and the second covariance matrix, a similarity is determined.

[0054] According to any of the aforementioned implementations of the second aspect of the present application, the first covariance matrix includes a plurality of first row vectors, and the second covariance matrix includes a plurality of second row vectors;

[0055] Determine the module specifically for:

[0056] Based on the plurality of first row vectors and the plurality of second row vectors, a plurality of distance values ​​are determined, wherein one distance value is a distance value between any one of the first row vectors and any one of the second row vectors;

[0057] Determine a distance matrix based on multiple distance values, where the distance matrix represents the relative position relationship between the template fingerprint feature points and the fingerprint feature points;

[0058] Based on the distance matrix, the similarity is determined.

[0059] According to any of the foregoing implementations of the second aspect of the present application, the distance matrix includes multiple distance row vectors, one distance row vector includes multiple distance values, and the determination module can be specifically used to:

[0060] Based on multiple distance values ​​in multiple distance row vectors in the distance matrix, determine a first distance vector and a second distance vector, the first distance vector being a vector determined based on the minimum distance value of each distance row vector in the multiple distance row vectors, and the second distance vector representing the position of each minimum distance value in the distance matrix;

[0061] Based on the first distance vector and the second distance vector, a similarity is determined.

[0062] According to any of the foregoing implementations of the second aspect of the present application, the determination module may be specifically used for:

[0063] Calculate the Euclidean distance between the first distance vector and the second distance vector;

[0064] Based on the Euclidean distance, the similarity is determined.

[0065] According to any of the aforementioned implementations of the second aspect of the present application, the characteristic parameter includes local entropy, and the template characteristic parameter includes template local entropy;

[0066] Determine the module specifically for:

[0067] Based on the multiple local entropies and the multiple template local entropies, the similarity between the fingerprint image and the template fingerprint image is determined.

[0068] According to any of the foregoing implementations of the second aspect of the present application, the determination module may be specifically used for:

[0069] Based on multiple local entropies and multiple template local entropies, multiple feature similarities are determined, where one feature similarity is a similarity determined based on any local entropy and any template local entropy, and the feature similarity represents the degree of similarity between a fingerprint feature point corresponding to any local entropy and a template fingerprint feature point corresponding to any template local entropy;

[0070] Based on multiple feature similarities, similarity is determined.

[0071] According to any of the foregoing implementations of the second aspect of the present application, the determination module may be specifically used for:

[0072] Based on multiple local entropies and multiple template local entropies, multiple mutual information is determined, and one mutual information is based on the mutual information determined by any local entropy and any template local entropy;

[0073] Normalizing the multiple mutual information to obtain normalized mutual information, where the normalized mutual information includes information obtained by normalizing each mutual information in the multiple mutual information;

[0074] Based on the mutual information and normalized mutual information, the feature similarity is determined.

[0075] According to any of the foregoing implementations of the second aspect of the present application, the acquisition module may also be used to:

[0076] Acquire an original fingerprint image, where the original fingerprint image includes multiple fingerprint feature points;

[0077] Counting the number of fingerprint feature points of the original fingerprint image to obtain a statistical result;

[0078] When the statistical result includes that the number of fingerprint feature points is less than the threshold, the original fingerprint image is determined to be the fingerprint image.

[0079] According to any of the foregoing implementations of the second aspect of the present application, the acquisition module may also be used to:

[0080] Acquire a template fingerprint image, where the template fingerprint image includes a plurality of template fingerprint feature points;

[0081] Using the fast feature point extraction and description algorithm, each template fingerprint feature point is detected and the template feature parameters corresponding to each template fingerprint feature point are determined.

[0082] In a third aspect, an embodiment of the present application provides a display device, the display device comprising:

[0083] a processor and a memory storing computer program instructions;

[0084] When the processor executes the computer program instructions, it is used to perform the fingerprint image matching method of the first aspect.

[0085] In a fourth aspect, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the fingerprint image matching method of the first aspect described above is implemented.

[0086] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when processed by a processor, implements the fingerprint image matching method of the first aspect.

[0087] The fingerprint image matching method, device, medium and product provided in the embodiments of the present application obtain a fingerprint image to be identified, use a fast feature point extraction and description algorithm to detect each fingerprint feature point, determine the feature parameters corresponding to each fingerprint feature point, and determine the similarity through the feature parameters corresponding to the feature points and the template feature parameters corresponding to the template fingerprint image. This can improve the recognition accuracy of the fingerprint image when the number of fingerprint feature points included in the fingerprint image is small, and improve the accuracy of the matching result of the fingerprint image and the template fingerprint image obtained based on the similarity. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0089] Figure 1 A schematic flow chart of a fingerprint image matching method provided in some embodiments of the present application.

[0090] Figure 2 A schematic diagram of an exemplary fingerprint image provided for some embodiments of the present application.

[0091] Figure 3 A schematic flow chart of a fingerprint image matching method provided in some other embodiments of the present application.

[0092] Figure 4 A schematic flow chart of a fingerprint image matching method provided in some embodiments of the present application.

[0093] Figure 5 A schematic flow chart of a fingerprint image matching method provided in some embodiments of the present application.

[0094] Figure 6 A schematic flow chart of a fingerprint image matching method provided in some embodiments of the present application.

[0095] Figure 7 A schematic diagram of the structure of a fingerprint image matching device provided in some embodiments of the present application.

[0096] Figure 8 A schematic diagram of the hardware structure of a display device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0097] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0098] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0099] At present, in the field of fingerprint recognition of user devices, a fingerprint image is usually generated by a fingerprint recognition sensor, and the fingerprint image is matched with a template fingerprint image to obtain a fingerprint recognition matching result. However, since the fingerprint recognition sensor is placed under the display screen of the user device, in some scenarios (for example, when the penetration ability of the display screen is limited), the imaging quality of the fingerprint image will be poor, resulting in inaccurate fingerprint matching and a poor user experience.

[0100] Based on this, the embodiments of the present application provide a fingerprint image matching method, device, medium and product, which can solve the above problems. Below, a fingerprint image matching method provided by the embodiments of the present application is described in detail.

[0101] like Figure 1 As shown, the embodiment of the present application provides a fingerprint image matching method, which may include the following steps S110 to S140.

[0102] S110: Acquire a fingerprint image to be identified, where the fingerprint image includes a plurality of fingerprint feature points.

[0103] The fingerprint to be identified can be obtained based on the target device. The fingerprint image can include multiple fingerprint feature points, such as Figure 2 As shown, Figure 2 is a schematic diagram of an exemplary fingerprint image, Figure 2 It includes multiple fingerprint feature points, and each "cross" is a fingerprint feature point. Here, the fingerprint image is an image in which the number of fingerprint feature points is less than a threshold.

[0104] S120: Using a fast feature point extraction and description algorithm, each fingerprint feature point is detected to determine the feature parameters corresponding to each fingerprint feature point.

[0105] The Oriented Fast and Rotated Brief (ORB) algorithm can be used to detect each fingerprint feature point and determine the feature parameters of each fingerprint feature point. For example, the ORB algorithm can be used to extract the feature points of the fingerprint. Figure 2 Each fingerprint feature point is detected to obtain feature parameters corresponding to each fingerprint feature point. Here, the feature parameters may include feature vectors and feature local entropy.

[0106] S130: Based on multiple feature parameters and multiple template feature parameters, determine the similarity between the fingerprint image and the template fingerprint image, the similarity represents the matching degree between the fingerprint image and the template fingerprint image, the template feature parameters are parameters corresponding to the template fingerprint feature points in the template fingerprint image, and the template fingerprint feature points correspond to the template feature parameters one by one.

[0107] The similarity between a fingerprint image and a template fingerprint image can be determined based on multiple feature parameters and multiple template feature parameters. For example, any feature parameter can be selected to match any template feature parameter to determine a sub-similarity. Each sub-similarity represents the degree of similarity between a fingerprint feature point corresponding to any feature parameter and a template feature point corresponding to any template feature parameter, thereby obtaining multiple similarities.

[0108] In some embodiments, before step S130: determining the similarity between the fingerprint image and the template fingerprint image based on the multiple feature parameters and the multiple template feature parameters, the fingerprint image matching method may further include the following steps:

[0109] A template fingerprint image is obtained, which includes a plurality of template fingerprint feature points; a fast feature point extraction and description algorithm is used to detect each template fingerprint feature point, and the template feature parameters corresponding to each template fingerprint feature point are determined.

[0110] A template fingerprint image including multiple template fingerprint feature points can be obtained in advance. It can be imagined that the template fingerprint image is an image whose number of feature points is greater than or equal to the above threshold. The ORB algorithm can be used to detect each template fingerprint feature point of the template fingerprint image to determine the template feature parameters corresponding to each template fingerprint feature point. Here, the template fingerprint feature points correspond to the template feature parameters one by one.

[0111] In some examples, the template feature parameter has a preset correspondence with the feature parameter, for example, when the feature parameter is a feature vector, the template feature parameter is a template feature vector, or, when the feature parameter is a local entropy, the template feature parameter is a template local entropy.

[0112] The embodiment of the present application detects each template fingerprint feature point in the template fingerprint image based on the ORB algorithm, determines the template feature parameters corresponding to each template fingerprint feature point, and determines the feature parameters and the template feature parameters through the same algorithm, which can improve the accuracy of the similarity determined based on the template feature parameters and the feature parameters.

[0113] S140: Determine the matching result between the fingerprint image and the template fingerprint image based on the similarity.

[0114] Based on the similarity, the matching result between the fingerprint image and the template fingerprint image can be determined. Taking the multiple sub-similarity determined based on selecting any one feature parameter and any one template feature parameter as an example, the number of sub-similarity greater than the similarity threshold is counted. When the number of sub-similarity is greater than or equal to the number threshold, the matching result that the fingerprint image matches the template fingerprint image can be output. Conversely, when the number of sub-similarity is less than the number threshold, the matching result that the fingerprint image does not match the template fingerprint image can be output.

[0115] The embodiment of the present application obtains a fingerprint image to be identified, uses a fast feature point extraction and description algorithm to detect each fingerprint feature point, determines the feature parameters corresponding to each fingerprint feature point, and determines the similarity through the feature parameters corresponding to the feature points and the template feature parameters corresponding to the template fingerprint image, thereby improving the recognition accuracy of the fingerprint image and the accuracy of the matching result between the fingerprint image and the template fingerprint image based on the similarity.

[0116] like Figure 3 As shown, in some embodiments, before step S110: obtaining a fingerprint image to be identified and the fingerprint image includes a plurality of fingerprint feature points, the fingerprint image matching method may further include steps S310 to S330.

[0117] S310: Acquire an original fingerprint image, where the original fingerprint image includes a plurality of fingerprint feature points.

[0118] The original fingerprint image can be obtained based on the fingerprint recognition sensor of the target device. Here, the original fingerprint image can include multiple fingerprint feature points, including feature points such as the end points, bifurcation points and breakpoints of the fingerprint pattern. The original fingerprint image is an image obtained by detecting the fingerprint feature points of the initial fingerprint image.

[0119] In some examples, before the above step S310, an initial fingerprint image may be acquired, and enhanced filtering may be performed on the initial fingerprint image to obtain a processed initial fingerprint image, and then fingerprint feature point detection may be performed on the processed initial fingerprint image to obtain an original fingerprint image.

[0120] S320: Count the number of fingerprint feature points of the original fingerprint image to obtain a statistical result.

[0121] The number of fingerprint feature points in the original fingerprint image can be counted to obtain a statistical result. Here, a preset threshold can be set in advance, and the number of feature points is compared with the threshold to obtain a statistical result.

[0122] S330: When the number of fingerprint feature points included in the statistical result is less than the threshold, determine that the original fingerprint image is a fingerprint image.

[0123] When the number of feature points is less than the threshold, it indicates that the original fingerprint image is a fingerprint image with low definition, and the original fingerprint image with the number of fingerprint feature points less than the threshold is determined as the fingerprint image.

[0124] The embodiment of the present application obtains the original fingerprint image, counts the number of fingerprint feature points included in the original fingerprint image, obtains a statistical result, and then determines that the original fingerprint image with the number of fingerprint feature points less than a threshold is a fingerprint image, which can quickly determine the fingerprint image with lower clarity, and then match the above fingerprint image, thereby improving the matching accuracy for the fingerprint image with lower clarity.

[0125] In some embodiments, the feature parameter may include a feature vector, and the template feature parameter may include a template feature vector. Both the feature vector and the template feature vector may be multi-dimensional vectors.

[0126] Step S130: Determining the similarity between the fingerprint image and the template fingerprint image based on the multiple feature parameters and the multiple template feature parameters may include the following steps:

[0127] Based on the multiple feature vectors and the multiple template feature vectors, the similarity between the fingerprint image and the template fingerprint image is determined.

[0128] Here, both the feature vector and the template feature vector are multi-dimensional vectors, for example, they can be 32-dimensional multi-dimensional vectors. Through the ORB algorithm, the feature vector corresponding to each fingerprint feature point can be determined, and the template feature vector corresponding to each template fingerprint feature point can be determined. Based on multiple feature vectors and multiple template feature vectors, the similarity between the fingerprint image and the template fingerprint image can be determined. For example, the distance value between any feature vector and the template feature vector can be calculated, and the sub-similarity between any of the above feature vectors and the template feature vector can be determined based on the distance value. It can be imagined that the smaller the distance value, the higher the sub-similarity between the above feature vector and the template feature vector.

[0129] The embodiment of the present application determines the similarity between a fingerprint image and a template fingerprint image based on a multidimensional feature vector and a multidimensional template feature vector, so that the similarity determined based on the multidimensional vector has higher accuracy, overcoming the problem of low recognition accuracy for fingerprint images with lower clarity in the prior art.

[0130] In some embodiments, determining the similarity between a fingerprint image and a template fingerprint image based on a plurality of feature vectors and a plurality of template feature vectors may include the following steps:

[0131] Based on any two template feature vectors, a first covariance matrix is ​​determined, and based on any two feature vectors, a second covariance matrix is ​​determined, the first covariance matrix represents the relative position relationship of the template fingerprint feature points corresponding to any two template feature vectors, and the second covariance matrix represents the relative position relationship of the fingerprint feature points corresponding to any two feature vectors; based on the first covariance matrix and the second covariance matrix, the similarity is determined.

[0132] The first covariance matrix can be determined based on any two template feature vectors. For example, the template feature vector and the feature vector are 32-dimensional multidimensional vectors. Each template feature vector includes multiple template feature values. Here, each template feature vector includes 32 template feature values. Each feature vector includes 32 eigenvalues. The first covariance matrix can be determined based on any two template feature vectors x. m1 (m 1 ,m 2 ,m 3 ,…m 32 ) and x m2 (m ′ 1 ,m ′ 2 ,m ′ 3 ,…m ′ 32 ) determines the first covariance matrix L, and based on any two eigenvectors x k1 (k 1 ,k2 ,k 3 ,…k 32 ) and x k2 (k ′ 1 ,k ′ 2 ,k ′ 3 ,…k ′ 32 ) determine the second covariance matrix Q, and determine the similarity based on the first covariance matrix and the second covariance matrix, where the first covariance matrix represents the relative position relationship between the template fingerprint feature points corresponding to any two template feature vectors, and the second covariance matrix represents the relative position relationship between the fingerprint feature points corresponding to any two feature vectors.

[0133] The embodiment of the present application can enhance the spatiality of the fingerprint image by determining a first covariance matrix based on any two template feature vectors, determining a second covariance matrix based on any two feature vectors, and determining the similarity based on the first covariance matrix and the second covariance matrix, so that the similarity determined based on the above method is more accurate.

[0134] In some embodiments, the first covariance matrix includes a plurality of first row vectors, and the second covariance matrix includes a plurality of second row vectors.

[0135] like Figure 4 As shown, optionally, determining the similarity based on the first covariance matrix and the second covariance matrix may include the following steps S410 to S430.

[0136] S410: Determine a plurality of distance values ​​based on a plurality of first row vectors and a plurality of second row vectors, wherein a distance value is a distance value between any one of the first row vectors and any one of the second row vectors.

[0137] A plurality of distance values ​​may be determined based on a plurality of first row vectors included in the first covariance matrix and a plurality of second row vectors included in the second covariance matrix, wherein a distance value is a distance value between any first row vector and any second row vector. 1 ,L 2 ,L 3 ,…L 32 ) and the second covariance matrix Q(Q 1 ,Q 2 ,Q 3 ,…Q 32 ) as an example,

[0138] L 1 ,L 2 ,L 3 ,…L 32For multiple first row vectors, Q 1 ,Q 2 ,Q 3 ,…Q 32 For multiple second row vectors, the distance value can be determined based on any first row vector and any second row vector, for example, based on L 1 With Q 1 Determine the distance value based on L 2 With Q 2 The distance value is determined, and so on, to obtain multiple distance values.

[0139] In some examples, the distance value may be determined based on the following formula:

[0140]

[0141] P is the distance value, L i For any first row vector, Q j is any second row vector.

[0142] S420: Determine a distance matrix based on the multiple distance values, where the distance matrix represents the relative position relationship between the template fingerprint feature points and the fingerprint feature points.

[0143] S430: Determine similarity based on the distance matrix.

[0144] A distance matrix may be determined based on the plurality of distance values, and the similarity may be determined based on the distance matrix. For example, the similarity may be determined based on parameters of the matrix.

[0145] The embodiment of the present application determines multiple distance values ​​through multiple first row vectors included in the first covariance matrix and multiple second row vectors included in the second covariance matrix, determines a distance matrix based on the multiple distance values, determines the relative position relationship between the template feature points and the fingerprint feature points, and determines the similarity based on the distance matrix, which can improve the robustness of fingerprint image matching and thereby improve the accuracy of the fingerprint image matching results.

[0146] In some embodiments, the distance matrix includes multiple distance row vectors, and a distance row vector includes multiple distance values. Accordingly, based on the distance matrix, determining the similarity may include the following steps:

[0147] Based on multiple distance values ​​in multiple distance row vectors in the distance matrix, a first distance vector and a second distance vector are determined, the first distance vector is a vector determined based on the minimum distance value of each distance row vector in the multiple distance row vectors, and the second distance vector represents the position of each minimum distance value in the distance matrix; based on the first distance vector and the second distance vector, similarity is determined.

[0148] In some embodiments, a first distance vector can be constructed based on the minimum distance value in each row vector in the distance matrix, and the first distance vector includes multiple distance values. A second distance vector is constructed based on the position of each minimum distance value in the first row vector in the distance matrix. Here, the second distance vector may include the position of the row of each minimum distance value in the first row vector in the distance matrix.

[0149] The similarity may be determined based on the first distance vector and the second distance vector. For example, the Hamming distance algorithm may be used to determine the distance between the first distance vector and the second distance vector to obtain the similarity. Here, a correspondence between the distance and the similarity may be established in advance to determine the similarity.

[0150] The embodiment of the present application constructs a first distance vector and a second distance vector based on multiple distance values ​​included in the distance matrix, and determines the similarity based on the first distance vector and the second distance vector. The first distance vector is constructed by screening the minimum value in each distance row vector, so that the minimum distance value between the fingerprint feature point and the template fingerprint feature point in any dimension can be determined, thereby improving the accuracy of the similarity between the determined fingerprint image and the target fingerprint image.

[0151] In some embodiments, determining the similarity based on the first distance vector and the second distance vector may include the following steps:

[0152] The Euclidean distance between the first distance vector and the second distance vector is calculated; and the similarity is determined based on the Euclidean distance.

[0153] Based on the first distance vector and the second distance vector, the Euclidean distance between the first distance vector and the second distance vector may be determined, and the similarity may be determined based on the following formula:

[0154] S=1-D (2)

[0155] S is the similarity and D is the Euclidean distance.

[0156] The embodiment of the present application calculates the Euclidean distance between the first distance vector and the second distance vector, and determines the similarity based on the Euclidean distance, thereby reducing the amount of calculation during fingerprint image matching and improving the efficiency of fingerprint image matching, while also reducing the rejection rate of fingerprint image matching.

[0157] In some embodiments, Figure 5 As shown, the feature parameters include local entropy, and the template feature parameters include template local entropy.

[0158] Step S130: Determine the similarity between the fingerprint image and the template fingerprint image based on the multiple feature vectors and the multiple template feature vectors, including:

[0159] S510: Determine the similarity between the fingerprint image and the template fingerprint image based on the multiple local entropies and the multiple template local entropies.

[0160] Here, the feature parameters may include local entropy. The fingerprint feature points may be detected based on the ORB algorithm to determine the local entropy corresponding to each fingerprint feature point. The local entropy may characterize the pixel grayscale distribution of each fingerprint feature point within a preset range. The similarity between the fingerprint image and the template fingerprint image may be determined based on multiple local entropies and multiple template local entropies.

[0161] In some examples, based on the local entropy of any template feature point, the local entropy of the target template that matches the local entropy can be determined in the template fingerprint image, and the target template fingerprint feature point corresponding to the local entropy of the target template can be determined. Here, the feature vector corresponding to the fingerprint feature point and the target feature vector corresponding to the target template fingerprint feature point can be determined based on the ORB algorithm, and the similarity is determined by the feature vector and the target feature vector.

[0162] The embodiment of the present application determines the similarity between a fingerprint image and a template fingerprint image based on multiple local entropies and multiple template local entropies, which can reduce the calculation steps during fingerprint image matching, save calculation time, improve the efficiency of fingerprint image matching and improve the accuracy of fingerprint image matching.

[0163] In some embodiments, the base step S510: determining the similarity between the fingerprint image and the template fingerprint image based on the multiple local entropies and the multiple template local entropies includes:

[0164] Based on multiple local entropies and multiple template local entropies, multiple feature similarities are determined, one feature similarity is a similarity determined based on any local entropy and any template local entropy, and the feature similarity represents the degree of similarity between a fingerprint feature point corresponding to any local entropy and a template fingerprint feature point corresponding to any template local entropy; based on multiple feature similarities, similarity is determined.

[0165] Here, the feature similarity can be determined based on any local entropy and any template local entropy to obtain multiple feature similarities, and then the number of feature similarities within the preset similarity range is counted to determine the matching result between the fingerprint image and the template fingerprint image. For example, when the number of feature similarities within the preset similarity range is greater than or equal to a preset threshold, it is determined that the fingerprint image matches the template fingerprint image.

[0166] The embodiment of the present application determines multiple feature similarities based on multiple local entropies and multiple template local entropies, and determines the similarity based on multiple feature similarities, thereby achieving determination of similarity based on local entropy and template local entropy, thereby improving the accuracy of the determined similarity.

[0167] In some embodiments, Figure 6 As shown, based on multiple local entropies and multiple template local entropies, multiple feature similarities are determined, including:

[0168] S610: Determine multiple mutual information based on multiple local entropies and multiple template local entropies, where one mutual information is the mutual information determined based on any local entropy and any template local entropy.

[0169] The mutual information can be determined based on the following formula:

[0170] MI(A,B)=H(A)+H(B)-H(A,B) (3)

[0171] MI(A,B) is the mutual information, H(A) is the template local entropy, H(B) is the local entropy, H(A,B)

[0172] It is the joint entropy of the local entropy and the template local entropy.

[0173] in:

[0174] H(A)=-∑ i P A logP A (i) (4)

[0175] H(B)=-∑ j P B logP B (j) (5)

[0176] H(A,B)=-∑ ij P AB logP AB (i,j) (6)

[0177] P AB =P A ×P B (7)

[0178] Here, P A is the grayscale distribution probability at the template fingerprint feature point i, P B is the grayscale distribution probability at fingerprint feature point j.

[0179] S620: Normalize the multiple mutual information to obtain normalized mutual information, where the normalized mutual information includes information obtained by normalizing each mutual information in the multiple mutual information.

[0180] Each mutual information can be normalized based on the following formula to obtain the normalized mutual information:

[0181]

[0182] NMI(A,B) is the normalized mutual information.

[0183] In some examples, the amount of information obtained by normalizing each mutual information within a preset value range may be counted, and when the amount of information is greater than or equal to a threshold, the normalized mutual information may be determined based on the above formula.

[0184] S630: Determine feature similarity based on the mutual information and the normalized mutual information.

[0185] Feature similarity can be determined based on the following formula:

[0186]

[0187] Here, when the amount of information is less than the threshold, the feature similarity is determined to be a first value, which indicates that the fingerprint feature point is not similar to the template fingerprint feature point, and a matching result that the fingerprint image does not match the template fingerprint image can be further output.

[0188] When the above information quantity is greater than or equal to the threshold, the feature similarity can be determined based on the above formula. The feature similarity represents the similarity between any fingerprint feature point and the template fingerprint feature point. Further, the similarity can be determined based on the feature similarity, which will not be repeated here.

[0189] The embodiment of the present application determines multiple mutual information based on multiple local entropies and multiple template local entropies, and normalizes the multiple mutual information to obtain normalized mutual information. The normalized mutual information can solve the problem of inaccurate similarity calculation caused by large changes in mutual information, thereby improving the accuracy of determining feature similarity based on mutual information and normalized mutual information.

[0190] Based on the same technical concept as the fingerprint image matching method provided in the above embodiment, the present application also provides a fingerprint image matching device. Please refer to the following embodiment.

[0191] like Figure 7 As shown, the fingerprint image matching device 700 provided in the embodiment of the present application includes:

[0192] The acquisition module 701 is used to acquire a fingerprint image to be identified, where the fingerprint image includes a plurality of fingerprint feature points;

[0193] The detection module 702 is used to detect each fingerprint feature point using a fast feature point extraction and description algorithm to determine the feature parameters corresponding to each fingerprint feature point;

[0194] The determination module 703 is used to determine the similarity between the fingerprint image and the template fingerprint image based on multiple feature parameters and multiple template feature parameters, where the similarity represents the matching degree between the fingerprint image and the template fingerprint image, and the template feature parameters are parameters corresponding to the template fingerprint feature points in the template fingerprint image, and the template fingerprint feature points correspond to the template feature parameters one by one;

[0195] The matching module 704 is used to determine the matching result between the fingerprint image and the template fingerprint image based on the similarity.

[0196] In some embodiments, the feature parameter includes a feature vector, the template feature parameter includes a template feature vector, and both the feature vector and the template feature vector are multi-dimensional vectors;

[0197] Determine the module specifically for:

[0198] Based on the multiple feature vectors and the multiple template feature vectors, the similarity between the fingerprint image and the template fingerprint image is determined.

[0199] In some embodiments, the determination module may be specifically configured to:

[0200] Based on any two template feature vectors, a first covariance matrix is ​​determined, and based on any two feature vectors, a second covariance matrix is ​​determined, wherein the first covariance matrix represents the relative position relationship between the template fingerprint feature points corresponding to any two template feature vectors, and the second covariance matrix represents the relative position relationship between the fingerprint feature points corresponding to any two feature vectors;

[0201] Based on the first covariance matrix and the second covariance matrix, a similarity is determined.

[0202] In some embodiments, the first covariance matrix includes a plurality of first row vectors, and the second covariance matrix includes a plurality of second row vectors;

[0203] Determine the module specifically for:

[0204] Based on the plurality of first row vectors and the plurality of second row vectors, a plurality of distance values ​​are determined, wherein one distance value is a distance value between any one of the first row vectors and any one of the second row vectors;

[0205] Determine a distance matrix based on multiple distance values, where the distance matrix represents the relative position relationship between the template fingerprint feature points and the fingerprint feature points;

[0206] Based on the distance matrix, the similarity is determined.

[0207] In some embodiments, the distance matrix includes multiple distance row vectors, and one distance row vector includes multiple distance values. The determination module can be specifically used to:

[0208] Based on multiple distance values ​​in multiple distance row vectors in the distance matrix, determine a first distance vector and a second distance vector, the first distance vector being a vector determined based on the minimum distance value of each distance row vector in the multiple distance row vectors, and the second distance vector representing the position of each minimum distance value in the distance matrix;

[0209] Based on the first distance vector and the second distance vector, a similarity is determined.

[0210] In some embodiments, the determination module may be specifically configured to:

[0211] Calculate the Euclidean distance between the first distance vector and the second distance vector;

[0212] Based on the Euclidean distance, the similarity is determined.

[0213] In some embodiments, the feature parameter comprises local entropy, and the template feature parameter comprises template local entropy;

[0214] Determine the module specifically for:

[0215] Based on the multiple local entropies and the multiple template local entropies, the similarity between the fingerprint image and the template fingerprint image is determined.

[0216] In some embodiments, the determination module may be specifically configured to:

[0217] Based on multiple local entropies and multiple template local entropies, multiple feature similarities are determined, where one feature similarity is a similarity determined based on any local entropy and any template local entropy, and the feature similarity represents the degree of similarity between a fingerprint feature point corresponding to any local entropy and a template fingerprint feature point corresponding to any template local entropy;

[0218] Based on multiple feature similarities, similarity is determined.

[0219] In some embodiments, the determination module may be specifically configured to:

[0220] Based on multiple local entropies and multiple template local entropies, multiple mutual information is determined, and one mutual information is based on the mutual information determined by any local entropy and any template local entropy;

[0221] Normalizing the multiple mutual information to obtain normalized mutual information, where the normalized mutual information includes information obtained by normalizing each mutual information in the multiple mutual information;

[0222] Based on the mutual information and normalized mutual information, the feature similarity is determined.

[0223] In some embodiments, the acquisition module may also be used to:

[0224] Acquire an original fingerprint image, where the original fingerprint image includes multiple fingerprint feature points;

[0225] Counting the number of fingerprint feature points of the original fingerprint image to obtain a statistical result;

[0226] When the statistical result includes that the number of fingerprint feature points is less than the threshold, the original fingerprint image is determined to be the fingerprint image.

[0227] In some embodiments, the acquisition module may also be used to:

[0228] Acquire a template fingerprint image, where the template fingerprint image includes a plurality of template fingerprint feature points;

[0229] Using the fast feature point extraction and description algorithm, each template fingerprint feature point is detected and the template feature parameters corresponding to each template fingerprint feature point are determined.

[0230] The device of the above embodiment is used to implement the corresponding fingerprint image matching method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0231] Figure 8 A schematic diagram of the hardware structure of a display device provided in an embodiment of the application.

[0232] The display device 800 may include a processor 801 and a memory 802 storing computer program instructions.

[0233] Specifically, the processor 801 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0234] The memory 802 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 802 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 802 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 802 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 802 is a non-volatile solid-state memory.

[0235] In certain embodiments, memory 802 includes a read-only memory (ROM). The ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of the above, where appropriate.

[0236] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect of the present application.

[0237] The processor 801 implements any one of the fingerprint image matching methods in the above embodiments by reading and executing the computer program instructions stored in the memory 802 .

[0238] In one example, the display device may further include a communication interface 803 and a bus 804. Figure 8 The processor 801, the memory 802, and the communication interface 803 are connected via a bus 804 and communicate with each other.

[0239] The communication interface 803 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0240] Bus 804 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 804 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0241] The display device of the above embodiment is used to implement the corresponding fingerprint image matching method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0242] In addition, in combination with the fingerprint image matching method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any fingerprint image matching method in the above embodiment is implemented.

[0243] In addition, in combination with the fingerprint image matching method in the above embodiment, the present application embodiment can provide a computer program product to implement. When the computer program product instructions are executed by the processor of the display device, any fingerprint image matching method in the above embodiment is implemented.

[0244] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0245] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0246] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or devices based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0247] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (device) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0248] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described devices, modules and units can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application.

Claims

1. A fingerprint image matching method, characterized in that: include: Acquire a fingerprint image to be identified, wherein the fingerprint image includes a plurality of fingerprint feature points; Using a fast feature point extraction and description algorithm, each of the fingerprint feature points is detected to determine the feature parameters corresponding to each of the fingerprint feature points; Based on the plurality of characteristic parameters and the plurality of template characteristic parameters, determining the similarity between the fingerprint image and the template fingerprint image, wherein the similarity represents the matching degree between the fingerprint image and the template fingerprint image, and the template characteristic parameters are parameters corresponding to the template fingerprint characteristic points in the template fingerprint image, and the template fingerprint characteristic points correspond to the template characteristic parameters one by one; Based on the similarity, a matching result between the fingerprint image and the template fingerprint image is determined.

2. The fingerprint image matching method according to claim 1, characterized in that: The feature parameter includes a feature vector, the template feature parameter includes a template feature vector, and both the feature vector and the template feature vector are multi-dimensional vectors; The determining the similarity between the fingerprint image and the template fingerprint image based on the plurality of feature parameters and the plurality of template feature parameters comprises: Determining the similarity between the fingerprint image and the template fingerprint image based on the plurality of feature vectors and the plurality of template feature vectors; Preferably, the determining the similarity between the fingerprint image and the template fingerprint image based on the plurality of feature vectors and the plurality of template feature vectors comprises: Based on any two template feature vectors, a first covariance matrix is ​​determined, and based on any two feature vectors, a second covariance matrix is ​​determined, wherein the first covariance matrix represents the relative position relationship between the template fingerprint feature points corresponding to the any two template feature vectors, and the second covariance matrix represents the relative position relationship between the fingerprint feature points corresponding to the any two feature vectors; The similarity is determined based on the first covariance matrix and the second covariance matrix.

3. The fingerprint image matching method according to claim 2, characterized in that: The first covariance matrix includes a plurality of first row vectors, and the second covariance matrix includes a plurality of second row vectors; The determining the similarity based on the first covariance matrix and the second covariance matrix includes: Based on the multiple first row vectors and the multiple second row vectors, determine multiple distance values, one distance value is a distance value between any one of the first row vectors and any one of the second row vectors; Determine a distance matrix based on the multiple distance values, wherein the distance matrix represents the relative position relationship between the template fingerprint feature points and the fingerprint feature points; Based on the distance matrix, determining the similarity; Preferably, the distance matrix includes a plurality of distance row vectors, one distance row vector includes a plurality of distance values, and the determining of the similarity based on the distance matrix includes: Based on multiple distance values ​​in multiple distance row vectors in the distance matrix, determine a first distance vector and a second distance vector, wherein the first distance vector is a vector determined based on the minimum distance value of each distance row vector in the multiple distance row vectors, and the second distance vector represents the position of each of the minimum distance values ​​in the distance matrix; Determining the similarity based on the first distance vector and the second distance vector; Preferably, determining the similarity based on the first distance vector and the second distance vector includes: Calculating the Euclidean distance between the first distance vector and the second distance vector; Based on the Euclidean distance, the similarity is determined.

4. The fingerprint image matching method according to claim 1, characterized in that: The characteristic parameters include local entropy, and the template characteristic parameters include template local entropy; Determining the similarity between the fingerprint image and the template fingerprint image based on the plurality of feature vectors and the plurality of template feature vectors includes: Based on the multiple local entropies and multiple template local entropies, the similarity between the fingerprint image and the template fingerprint image is determined.

5. The fingerprint image matching method according to claim 4, characterized in that: The determining the similarity between the fingerprint image and the template fingerprint image based on the plurality of local entropies and the plurality of template local entropies comprises: Based on the multiple local entropies and the multiple template local entropies, multiple feature similarities are determined, one feature similarity is a similarity determined based on any one of the local entropies and any one of the template local entropies, and the feature similarity represents the degree of similarity between the fingerprint feature point corresponding to any one of the local entropies and the template fingerprint feature point corresponding to any one of the template local entropies; Determining the similarity based on a plurality of the feature similarities; Preferably, the determining of multiple feature similarities based on the multiple local entropies and the multiple template local entropies includes: Based on the multiple local entropies and the multiple template local entropies, determine multiple mutual information, one mutual information is based on the mutual information determined by any one of the local entropies and any one of the template local entropies; Normalizing the multiple mutual information to obtain normalized mutual information, where the normalized mutual information includes information obtained by normalizing each of the multiple mutual information; The feature similarity is determined based on the mutual information and the normalized mutual information.

6. The fingerprint image matching method according to claim 1, characterized in that: Before obtaining the fingerprint image to be identified, wherein the fingerprint image includes a plurality of fingerprint feature points, the matching method further includes: Acquire an original fingerprint image, wherein the original fingerprint image includes a plurality of fingerprint feature points; Counting the number of fingerprint feature points of the original fingerprint image to obtain a statistical result; When the statistical result includes that the number of the fingerprint feature points is less than a threshold, the original fingerprint image is determined to be the fingerprint image.

7. The fingerprint image matching method according to claim 1, characterized in that: Before determining the similarity between the fingerprint image and the template fingerprint image based on the plurality of feature parameters and the plurality of template feature parameters, the matching method further comprises: Acquire a template fingerprint image, wherein the template fingerprint image includes a plurality of template fingerprint feature points; A fast feature point extraction and description algorithm is used to detect each template fingerprint feature point and determine the template feature parameters corresponding to each template fingerprint feature point.

8. A fingerprint image matching device, characterized in that: include: An acquisition module, used to acquire a fingerprint image to be identified, wherein the fingerprint image includes a plurality of fingerprint feature points; A detection module, used to detect each fingerprint feature point using a fast feature point extraction and description algorithm, and determine the feature parameters corresponding to each fingerprint feature point; A determination module, configured to determine the similarity between the fingerprint image and the template fingerprint image based on the plurality of characteristic parameters and the plurality of template characteristic parameters, wherein the similarity represents the degree of matching between the fingerprint image and the template fingerprint image, and the template characteristic parameters are parameters corresponding to the template fingerprint characteristic points in the template fingerprint image, and the template fingerprint characteristic points correspond to the template characteristic parameters one by one; A matching module is used to determine a matching result between the fingerprint image and the template fingerprint image based on the similarity.

9. A readable storage medium, characterized in that: The readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the fingerprint image matching method according to any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is processed by a processor, the fingerprint image matching method as claimed in any one of claims 1 to 7 is implemented.

Images