Fingerprint identification method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a fingerprint identification method and device, electronic equipment and a storage medium. The fingerprint identification method comprises the following steps: acquiring a to-be-identified fingerprint image; the to-be-identified fingerprint image is identified through a plurality of seed templates, the plurality of seed templates are spliced into at least one first virtual puzzle, and the adjacent seed templates in the first virtual puzzle have overlapping areas; if the identification of the fingerprint image to be identified by the plurality of seed templates fails, determining at least one reference area from the first virtual puzzle according to the similarity between the fingerprint image to be identified and the plurality of seed templates; determining the auxiliary template, of which the overlapping rate with any reference region is greater than an overlapping rate threshold value, in the plurality of auxiliary templates as a supplementary template; and identifying the fingerprint image to be identified through the supplementary template.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of data processing, and in particular, to a fingerprint recognition method, device, electronic device, and storage medium. Background Art

[0002] In recent years, fingerprint recognition technology has been widely used in fields such as fingerprint unlocking and payment of mobile terminals such as smart phones. With the development of mobile terminal components towards integration and miniaturization, the size of the sensor for fingerprint recognition is designed to be smaller and smaller. However, the smaller the sensor size, the fewer fingerprint features it collects each time, which will directly affect the success rate of fingerprint recognition. The prior art usually increases the number of fingerprint templates used for fingerprint recognition to improve the success rate of fingerprint recognition. However, the increase in the number of fingerprint templates used for fingerprint recognition in the prior art will correspondingly increase the time consumed for fingerprint recognition and reduce the efficiency of fingerprint recognition. Summary of the Invention

[0003] In view of this, the embodiments of the present application provide a fingerprint recognition method, device, electronic device, and storage medium, which at least partially solve the above problems.

[0004] According to a first aspect of the embodiments of the present application, there is provided a fingerprint recognition method, including: obtaining a fingerprint image to be recognized; recognizing the fingerprint image to be recognized through a plurality of seed templates, wherein the plurality of seed templates are spliced into at least one first virtual jigsaw puzzle, and there are overlapping regions between adjacent seed templates in the first virtual jigsaw puzzle; if the recognition of the fingerprint image to be recognized through the plurality of seed templates fails, determining at least one reference region from the first virtual jigsaw puzzle according to the similarity between the fingerprint image to be recognized and the plurality of seed templates; determining, as supplementary templates, the auxiliary templates among the plurality of auxiliary templates whose overlap rate with any one of the reference regions is greater than an overlap rate threshold; and recognizing the fingerprint image to be recognized through the supplementary templates.

[0005] In a possible implementation manner, the determining at least one reference region from the first virtual jigsaw puzzle according to the similarity between the fingerprint image to be recognized and the plurality of seed templates includes: determining a plurality of alternative regions in the first virtual jigsaw puzzle, wherein the size of the alternative regions is determined based on the size of the fingerprint image to be recognized; determining the similarity between the fingerprint image to be recognized and the plurality of alternative regions; sorting the plurality of alternative regions in descending order of similarity with the fingerprint image to be recognized; and determining at least one of the alternative regions ranked ahead as the reference region.

[0006] In a possible implementation, the method provided by the embodiments of the present application further includes: obtaining a fingerprint template library including a plurality of fingerprint templates; determining the splicing relationship between the fingerprint templates in the fingerprint template library, where the splicing relationship is used to indicate the relative positions and overlapping rates between the fingerprint templates in the fingerprint template library; determining the seed template, the auxiliary template, and the isolated template from the fingerprint template library according to the splicing relationship; or determining the seed template and the auxiliary template from the fingerprint template library according to the splicing relationship.

[0007] In a possible implementation, the determining the seed template, the auxiliary template, and the isolated template from the fingerprint template library according to the splicing relationship includes: determining a plurality of the seed templates from the fingerprint template library according to the splicing relationship, where the plurality of seed templates can be spliced into the connected first virtual jigsaw puzzle; determining, according to the splicing relationship, the fingerprint templates in the fingerprint template library that are other than the seed templates and are located within the first virtual jigsaw puzzle as the auxiliary templates, where the overlapping rate between the seed template corresponding to the position of the auxiliary template and the adjacent seed template is less than the overlapping rate between this auxiliary template and the adjacent seed template; determining, according to the splicing relationship, the fingerprint templates in the fingerprint template library that are located outside the first virtual jigsaw puzzle as the isolated templates, where, in at least one second virtual jigsaw puzzle formed by splicing the isolated templates, the area of any one of the second virtual jigsaw puzzles is less than the area of the first virtual jigsaw puzzle, and the second virtual jigsaw puzzle is a connected jigsaw puzzle.

[0008] In a possible implementation, the determining the seed template and the auxiliary template from the fingerprint template library includes: determining a plurality of the seed templates from the fingerprint template library according to the splicing relationship, where the plurality of seed templates can be spliced into at least one of the first virtual jigsaw puzzles, and the first virtual jigsaw puzzle is a connected jigsaw puzzle; determining, according to the splicing relationship, the fingerprint templates in the fingerprint template library that are other than the seed templates and are located within the first virtual jigsaw puzzle as the auxiliary templates, where the overlapping rate between the seed template corresponding to the position of the auxiliary template and the adjacent seed template is less than the overlapping rate between this auxiliary template and the adjacent seed template.

[0009] In a possible implementation, after the recognition of the fingerprint image to be recognized fails by using the plurality of seed templates and before determining at least one reference area from the first virtual jigsaw puzzle according to the similarity between the fingerprint image to be recognized and the plurality of seed templates, the method further includes: recognizing the fingerprint image to be recognized by using at least one isolated template, where there is no overlapping area between the isolated template and any one of the seed templates.

[0010] In a possible implementation, the method provided by the embodiments of the present application further includes: after successfully recognizing the fingerprint image to be recognized, updating the fingerprint template library according to the fingerprint image to be recognized; based on the updated fingerprint template library, determining the seed template, the auxiliary template, and the isolated template, or determining the seed template and the auxiliary template.

[0011] In a possible implementation, the step of updating the fingerprint template library according to the fingerprint image to be recognized after successfully recognizing the fingerprint image to be recognized includes: if the number of fingerprint templates in the fingerprint template library is less than the template number threshold, adding at least a part of the fingerprint image to be recognized as a fingerprint template to the fingerprint template library; if the number of fingerprint templates in the fingerprint template library is equal to the template number threshold, adding at least a part of the fingerprint image to be recognized as a fingerprint template to the fingerprint template library, and deleting the fingerprint template with the largest corresponding overlap rate from the fingerprint template library.

[0012] According to a second aspect of the embodiments of the present application, there is provided a fingerprint recognition device, including: an acquisition module, configured to acquire a fingerprint image to be recognized; a first recognition module, configured to recognize the fingerprint image to be recognized through a plurality of seed templates, wherein the plurality of seed templates are spliced into at least one first virtual jigsaw puzzle, and there is an overlapping area between adjacent seed templates in the first virtual jigsaw puzzle; a reference module, configured to, when the recognition of the fingerprint image to be recognized fails through the plurality of seed templates, determine at least one reference area from the first virtual jigsaw puzzle according to the similarity between the fingerprint image to be recognized and the plurality of seed templates; a supplement module, configured to determine, as a supplementary template, an auxiliary template in the plurality of auxiliary templates whose overlap rate with any one of the reference areas is greater than the overlap rate threshold; and a second recognition module, configured to recognize the fingerprint image to be recognized through the supplementary template.

[0013] According to a third aspect of the embodiments of the present application, there is provided an electronic device, including: a processor, a memory, a communication interface, and a communication bus, where the processor, the memory, and the communication interface complete communication with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the method according to any one of the embodiments in the first aspect above.

[0014] According to a fourth aspect of the embodiments of the present application, there is provided a computer storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the method according to any one of the embodiments in the first aspect above.

[0015] In the embodiments of the present application, the fingerprint template can be divided into a seed template and an auxiliary template. Among them, multiple seed templates can be spliced into at least one first virtual jigsaw puzzle, and there are overlapping areas between adjacent seed templates in the first virtual jigsaw puzzle. After obtaining the fingerprint image to be recognized, the fingerprint image to be recognized can be recognized first through the seed template, rather than using all fingerprint templates to recognize the fingerprint image to be recognized. If the fingerprint image to be recognized is successfully recognized through multiple seed templates, the number of fingerprint templates used for fingerprint recognition can be greatly reduced, thereby reducing the time consumed for fingerprint recognition and improving the efficiency of fingerprint recognition. Moreover, if the fingerprint image to be recognized fails to be recognized through multiple seed templates, at least one reference area can be determined from the first virtual jigsaw puzzle according to the similarity between the fingerprint image to be recognized and the multiple seed templates, and the auxiliary template with an overlap rate greater than the overlap rate threshold with any reference area among the multiple auxiliary templates is determined as a supplementary template, and the fingerprint image to be recognized is recognized through the supplementary template. That is, on the basis of recognizing the fingerprint image to be recognized through the seed template, some auxiliary templates are used as supplementary templates to recognize the fingerprint image to be recognized, and the remaining auxiliary templates can no longer be used to recognize the fingerprint image to be recognized, which can reduce the number of fingerprint templates used for fingerprint recognition, thereby reducing the time consumed for fingerprint recognition and improving the efficiency of fingerprint recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the embodiments of the present application, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0017] Figure 1 is a flowchart of the steps of a fingerprint recognition method provided by an optional embodiment of the present application;

[0018] Figure 2 is a schematic diagram of a first virtual jigsaw puzzle formed by splicing seed templates provided by an optional embodiment of the present application;

[0019] Figure 3 is a schematic diagram of the relative position relationship between a seed template and an auxiliary template provided by an optional embodiment of the present application;

[0020] Figure 4 is a flowchart of the steps of another fingerprint recognition method provided by an optional embodiment of the present application;

[0021] Figure 5 is a flowchart of the steps of obtaining the splicing relationship between a fingerprint template library and fingerprint templates provided by an optional embodiment of the present application;

[0022] Figure 6 It is a flowchart of steps for determining a seed template, an auxiliary template, and an isolated template provided by an alternative embodiment of the present application;

[0023] Figure 7 It is a structural block diagram of a fingerprint recognition device provided by an alternative embodiment of the present application;

[0024] Figure 8 It is a schematic structural diagram of an electronic device provided by an alternative embodiment of the present application. Detailed implementation manners

[0025] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art shall fall within the protection scope of the embodiments of the present application.

[0026] The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms of "a", "an", "the", and "said" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0027] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0028] The present application provides a fingerprint recognition method, device, electronic device, and storage medium to at least partially solve the above problems existing in the prior art.

[0029] The fingerprint recognition method provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0030] As Figure 1 shown, a first aspect of the embodiments of the present application provides a fingerprint recognition method, including:

[0031] S110: Obtain a fingerprint image to be recognized.

[0032] As a feasible implementation method, a fingerprint sensor such as an ultrasonic fingerprint sensor, a capacitive fingerprint sensor, or an optical fingerprint sensor can be used to collect a user's fingerprint, thereby obtaining a fingerprint image to be recognized.

[0033] S120: Use multiple seed templates to recognize the fingerprint image to be recognized. Among them, the multiple seed templates are spliced into at least one first virtual jigsaw puzzle, and there are overlapping regions between adjacent seed templates in the first virtual jigsaw puzzle.

[0034] Before recognizing the fingerprint image to be recognized, multiple seed templates can be stored in advance. Specifically, the multiple seed templates can be spliced into at least one first virtual jigsaw puzzle. There are overlapping regions between adjacent seed templates in the first virtual jigsaw puzzle. Based on this overlapping region, the first virtual jigsaw puzzle formed by the seed templates can be a connected jigsaw puzzle for each part, so as to ensure the integrity of the first virtual jigsaw puzzle. It should be noted that when there are multiple first virtual jigsaw puzzles, the multiple first virtual jigsaw puzzles can be multiple first virtual jigsaw puzzles that are not connected to each other.

[0035] The first virtual jigsaw puzzle 10 that can be formed by splicing multiple seed templates can be as Figure 2 and Figure 3 shown. It should be noted that to clearly show the first virtual jigsaw puzzle, Figure 2 and Figure 3 hide the overlapping parts between adjacent seed templates 11.

[0036] As a feasible implementation method, there is a partial area of each seed template that does not overlap with any other seed template. By restricting that there is a partial area of each seed template that does not overlap with any other seed template, the overlap rate between seed templates can be reduced, so that fewer seed templates can be used to splice the above first virtual jigsaw puzzle, thereby reducing the number of seed templates.

[0037] S130: If the recognition of the fingerprint image to be recognized fails using multiple seed templates, then determine at least one reference area from the first virtual jigsaw puzzle according to the similarity between the fingerprint image to be recognized and the multiple seed templates.

[0038] Similarity is used to indicate the size of the difference. The higher the similarity, the smaller the difference. The calculation method of similarity can refer to the related technology and will not be elaborated here. As a feasible implementation method, the similarity between a fingerprint image and a seed template can be obtained by calculating the gray-scale difference between the fingerprint image and the seed template pixel by pixel. Optionally, the similarity can be expressed by mathematical indicators such as the mean squared error (MSE). For example, the mean squared error of the gray-scale values of the fingerprint image and the seed template can be calculated pixel by pixel, and this mean squared error is used to represent the similarity between the fingerprint image and the seed template.

[0039] In the embodiments of the present application, the fingerprint image to be recognized can be compared with the area formed by the seed templates on the first virtual jigsaw puzzle to determine the similarity between the fingerprint image to be recognized and each area on the first virtual jigsaw puzzle, and one or more areas with the maximum similarity to the fingerprint image on the first virtual jigsaw puzzle are determined as the reference areas.

[0040] S140: Determine the auxiliary templates with an overlap rate greater than the overlap rate threshold with any of the reference areas among the multiple auxiliary templates as the supplementary templates.

[0041] The relative positional relationship between the auxiliary template 12 and the seed template 11 can be as Figure 3 shown. Specifically, the auxiliary template 12 can be a fingerprint template located within the range of the first virtual jigsaw puzzle, that is, the auxiliary template 12 can have an overlapping area with at least one seed template 11. The overlap rate threshold between the auxiliary template and the reference area can be greater than zero, so as to avoid determining the auxiliary template 12 without an overlapping area with the reference area as the supplementary template. It should be understood that the seed template, the auxiliary template, and the following isolated template all belong to fingerprint templates and can all be used to compare with the fingerprint image to be recognized to recognize the fingerprint image to be recognized.

[0042] As a feasible implementation, the number of reference areas can be multiple, such as 3 to 5, and can be specifically set according to needs to ensure as much as possible that the supplementary templates can be determined. Optionally, if no supplementary templates are determined based on the above reference areas, that is, there are no auxiliary templates with an overlap rate greater than the overlap rate threshold with the above reference areas, new reference areas can be continuously determined with reference to the above embodiments until the supplementary templates are determined.

[0043] S150: Recognize the fingerprint image to be recognized through the supplementary templates.

[0044] By comparing the fingerprint image to be recognized with each supplementary template, the fingerprint image to be recognized can be recognized. The specific recognition process can refer to the related technology and will not be elaborated here.

[0045] In the embodiments of the present application, a fingerprint template can be divided into a seed template and an auxiliary template. Multiple seed templates can be spliced into at least one first virtual jigsaw puzzle, and there are overlapping areas between adjacent seed templates in the first virtual jigsaw puzzle. After obtaining the fingerprint image to be recognized, the fingerprint image to be recognized can be recognized first through the seed template, rather than using all fingerprint templates to recognize the fingerprint image to be recognized. If the fingerprint image to be recognized is successfully recognized through multiple seed templates, the number of fingerprint templates used for fingerprint recognition can be greatly reduced, thereby reducing the time consumed for fingerprint recognition and improving the efficiency of fingerprint recognition. Moreover, if the fingerprint image to be recognized fails to be recognized through multiple seed templates, at least one reference area can be determined from the first virtual jigsaw puzzle according to the similarity between the fingerprint image to be recognized and the multiple seed templates. The auxiliary template with an overlap rate greater than the overlap rate threshold with any reference area among the multiple auxiliary templates is determined as a supplementary template, and the fingerprint image to be recognized is recognized through the supplementary template. That is, on the basis of recognizing the fingerprint image to be recognized through the seed template, some auxiliary templates are used as supplementary templates to recognize the fingerprint image to be recognized, and the remaining auxiliary templates can no longer be used to recognize the fingerprint image to be recognized, which can reduce the number of fingerprint templates used for fingerprint recognition, thereby reducing the time consumed for fingerprint recognition and improving the efficiency of fingerprint recognition.

[0046] The inventor of the present application conducted an experiment on recognizing the fingerprint image to be recognized by using the fingerprint recognition method provided in the embodiments of the present application and the prior art that does not distinguish between seed templates and auxiliary templates under the condition that the total number of fingerprint templates is the same. The experimental results show that for the case where the recognition result is successful, the number of fingerprint templates used in the fingerprint recognition method provided in the embodiments of the present application is approximately 28% less than that of the prior art; for the case where the recognition result is failure, the number of fingerprint templates used in the fingerprint recognition method provided in the embodiments of the present application is approximately 60% less than that of the prior art. It can be seen that using the fingerprint recognition method provided in the embodiments of the present application to recognize the fingerprint image to be recognized can significantly reduce the number of fingerprint templates used.

[0047] In some optional embodiments, determining at least one reference area from the first virtual jigsaw puzzle according to the similarity between the fingerprint image to be recognized and the multiple seed templates includes:

[0048] Determine multiple alternative areas in the first virtual jigsaw puzzle, where the size of the alternative area is determined based on the size of the fingerprint image to be recognized. Determine the similarity between the fingerprint image to be recognized and the multiple alternative areas. Sort the multiple alternative areas in descending order of similarity to the fingerprint image to be recognized, and determine at least one alternative area ranked ahead as the reference area.

[0049] After obtaining the fingerprint image to be recognized, the direction of the fingerprint image to be recognized can be identified, and by rotating the fingerprint image to be recognized or rotating the seed template, the directions of the fingerprints in the fingerprint image to be recognized and the seed template are aligned, so as to facilitate the recognition of the fingerprint image to be recognized by multiple seed templates. Moreover, after aligning the directions of the fingerprints in the fingerprint image to be recognized and the seed template, multiple alternative regions can be divided in the first virtual jigsaw puzzle formed by splicing the seed templates based on the size of the fingerprint image to be recognized. The positions of two adjacent alternative regions can intersect, so that the total region formed by splicing all the alternative regions can cover the complete first virtual jigsaw puzzle.

[0050] After determining the similarity between the fingerprint image to be recognized and each alternative region, in the alternative regions, the alternative regions can be sorted in descending order of the similarity with the fingerprint image to be recognized, and at least one of the alternative regions ranked at the top, such as the top 3 alternative regions or the top 5 alternative regions, is determined as the reference region according to the sorting result.

[0051] In the embodiment of the present application, multiple alternative regions can be determined based on the alternative regions in the first virtual jigsaw puzzle, the similarity between the fingerprint image to be recognized and the multiple alternative regions is determined, the multiple alternative regions are sorted in descending order of the similarity with the fingerprint image to be recognized, and at least one of the alternative regions ranked at the top is determined as the reference region. It is possible to use the alternative regions with a higher similarity to the fingerprint image to be recognized as the reference region, so that the supplementary template determined based on the overlap rate with the reference region also has a higher similarity to the fingerprint image to be recognized, thereby improving the success rate of recognizing the fingerprint image to be recognized through the supplementary template.

[0052] As Figure 4 shown, in some alternative embodiments, the fingerprint recognition method provided by the present application further includes:

[0053] S210: Obtain a fingerprint template library including multiple fingerprint templates.

[0054] It should be understood that the fingerprint template library can be a template set formed by fingerprint templates input by users. As a feasible implementation manner, fingerprint templates can be input through fingerprint sensors such as ultrasonic fingerprint sensors, capacitive fingerprint sensors, or optical fingerprint sensors. The embodiment of the present application does not limit the manner of inputting fingerprint templates.

[0055] S220: Determine the splicing relationship between the fingerprint templates in the fingerprint template library, and the splicing relationship is used to indicate the relative positions and overlap rates between the fingerprint templates in the fingerprint template library.

[0056] S230: Determine a seed template, an auxiliary template, and an isolated template from the fingerprint template library according to the splicing relationship; or, determine a seed template and an auxiliary template from the fingerprint template library according to the splicing relationship.

[0057] The isolated template can be understood as a fingerprint template that does not have an overlapping area with any seed template, and its position can be outside the at least one first virtual puzzle pieced together by multiple seed templates.

[0058] The puzzles pieced together by the fingerprint templates in the fingerprint template library can include multiple non-connected virtual puzzles. In the embodiments of the present application, according to the splicing relationship, a seed template, an auxiliary template, and an isolated template can be determined from the fingerprint template library. The positions of the seed template and the isolated template are located in different virtual puzzles, that is, at least some of the fingerprint templates in only some virtual puzzles can be determined as seed templates. Or, according to the splicing relationship, a seed template and an auxiliary template are determined from the fingerprint template library. In this case, at least some of the fingerprint templates in each virtual puzzle can be determined as seed templates.

[0059] In the embodiments of the present application, a fingerprint template library including multiple fingerprint templates can be obtained, the splicing relationship between the fingerprint templates in the fingerprint template library can be determined, and according to the splicing relationship, a seed template, an auxiliary template, and an isolated template can be determined from the fingerprint template library, or, according to the splicing relationship, a seed template and an auxiliary template can be determined from the fingerprint template library, so as to divide the fingerprint templates in the fingerprint template library. Thus, when identifying a fingerprint image to be recognized, only some of the fingerprint templates in the fingerprint template library can be used to complete the recognition of the fingerprint image to be recognized, so as to reduce the number of fingerprint templates used for fingerprint recognition. For example, when the embodiments of the present application recognize a fingerprint image to be recognized, only the seed template may be used, or the seed template and the isolated template may be used, or a supplementary template determined by the seed template and some auxiliary templates may be used, or a supplementary template determined by the seed template, the isolated template, and some auxiliary templates may be used, etc., all of which are only using some of the fingerprint templates in the fingerprint template library.

[0060] As Figure 5 shown, as a feasible implementation manner, the process of obtaining a fingerprint template library including multiple fingerprint templates and determining the splicing relationship between the fingerprint templates in the fingerprint template library can include:

[0061] S310: Obtain a fingerprint image to be entered.

[0062] S320: Determine whether the number of stored fingerprint templates is zero.

[0063] S330: If the number of stored fingerprint templates is zero, generate a corresponding fingerprint template according to the fingerprint image to be entered, and store the generated fingerprint template.

[0064] S340: If the number of stored fingerprint templates is greater than zero, generate a corresponding fingerprint template based on the fingerprint image to be input, and by traversing the stored fingerprint templates, determine the splicing relationship between the generated fingerprint template and the stored fingerprint templates, and store the determined splicing relationship and the generated fingerprint template.

[0065] S350: Determine whether the number of stored fingerprint templates has reached a given template input threshold.

[0066] S360: If the number of stored fingerprint templates has not reached the template input threshold, obtain a new fingerprint image to be input until the number of stored fingerprint templates reaches the template input threshold.

[0067] S370: If the number of stored fingerprint templates has reached the template input threshold, stop obtaining the fingerprint images to be input, obtain a fingerprint template library based on the stored fingerprint templates, and obtain the splicing relationship between the fingerprint templates in the fingerprint template library based on the stored splicing relationship. The template input threshold can be less than or equal to the following template quantity threshold.

[0068] As Figure 6 shown, in some alternative embodiments, according to the splicing relationship, determine a seed template, an auxiliary template, and an isolated template from the fingerprint template library, including:

[0069] S231: According to the splicing relationship, determine a plurality of seed templates from the fingerprint template library, and the plurality of seed templates can be spliced into a connected first virtual jigsaw puzzle.

[0070] The connected first virtual jigsaw puzzle refers to a first virtual jigsaw puzzle with continuous interior. The connected first virtual jigsaw puzzle formed by splicing a plurality of seed templates in this step can be one.

[0071] S232: According to the splicing relationship, determine the fingerprint templates in the fingerprint template library that are other than the seed templates and are located within the first virtual jigsaw puzzle as auxiliary templates, wherein the overlap rate between the seed template corresponding to the position of the auxiliary template and the adjacent seed template is less than the overlap rate between the auxiliary template and the aforementioned adjacent seed template.

[0072] The seed template corresponding to the position of the auxiliary template can be the seed template that has an overlapping area with the auxiliary template. The overlap rate between a certain seed template and an adjacent seed template can be obtained by dividing the sum of the areas overlapping with each adjacent seed template on the seed template by the total area of the seed template.

[0073] S233: Determine the fingerprint templates in the fingerprint template library that are outside the first virtual puzzle as isolated templates according to the splicing relationship. Among the at least one second virtual puzzle formed by splicing the isolated templates, the area of any second virtual puzzle is smaller than the area of the first virtual puzzle, and the second virtual puzzle is a connected puzzle.

[0074] As a feasible implementation, according to the splicing relationship, first take the virtual puzzle with the largest area that can be formed by splicing the fingerprint templates in the fingerprint template library as the first virtual puzzle, and then, with the goal that the overlap rate between the seed template corresponding to the auxiliary template and the adjacent seed template is less than the overlap rate between this auxiliary template and this adjacent seed template, determine the seed template and the auxiliary template from the fingerprint templates within the range of the first virtual puzzle according to the splicing relationship.

[0075] In the embodiments of the present application, multiple seed templates that can be spliced into a connected first virtual puzzle can be determined from the fingerprint template library according to the splicing relationship, and according to the splicing relationship, the fingerprint templates in the fingerprint template library that are outside the seed templates and within the first virtual puzzle are determined as auxiliary templates. Among them, setting the overlap rate between the seed template corresponding to the auxiliary template and the adjacent seed template to be less than the overlap rate between this auxiliary template and this adjacent seed template can minimize the overlap rate between the seed template corresponding to the auxiliary template and the adjacent seed template as much as possible, so that the seed template has less duplicate information, which is convenient for reducing the number of seed templates required to splice the first virtual puzzle, that is, reducing the number of seed templates used to identify the fingerprint image to be recognized. In addition, determining the fingerprint templates in the fingerprint template library that are outside the first virtual puzzle as isolated templates according to the splicing relationship can quickly determine the isolated templates after determining the seed templates, which can improve the efficiency of determining the isolated templates.

[0076] In some optional embodiments, determining the seed template and the auxiliary template from the fingerprint template library includes:

[0077] Determine multiple seed templates from the fingerprint template library according to the splicing relationship. The multiple seed templates can be spliced into at least one first virtual puzzle, and the first virtual puzzle is a connected puzzle.

[0078] According to the splicing relationship, determine the fingerprint templates in the fingerprint template library that are outside the seed templates and within the first virtual puzzle as auxiliary templates, where the overlap rate between the seed template corresponding to the auxiliary template and the adjacent seed template is less than the overlap rate between this auxiliary template and this adjacent seed template.

[0079] As a feasible implementation, each non-connected virtual jigsaw puzzle that can be pieced together from the fingerprint templates in the fingerprint template library can be used as the first virtual jigsaw puzzle according to the piecing relationship. Then, with the goal that the overlap rate between the seed template corresponding to the auxiliary template in terms of position and the adjacent seed template is less than the overlap rate between this auxiliary template and the adjacent seed template, the seed template and the auxiliary template are determined from the fingerprint templates whose positions are within the range of the first virtual jigsaw puzzle according to the piecing relationship.

[0080] In the embodiments of the present application, multiple seed templates can be determined from the fingerprint template library according to the piecing relationship. The multiple seed templates can be pieced together into at least one first virtual jigsaw puzzle. The first virtual jigsaw puzzle is a connected jigsaw puzzle, and the first virtual jigsaw puzzles can be non-connected to each other. The first virtual jigsaw puzzles pieced together by the seed templates can cover all the virtual jigsaw puzzles pieced together from the fingerprint templates in the fingerprint template library, so that the seed templates can have sufficient fingerprint information, which is beneficial to improving the success rate of recognizing the fingerprint image to be recognized through multiple seed templates. According to the piecing relationship, the fingerprint templates in the fingerprint template library that are other than the seed templates and whose positions are within the first virtual jigsaw puzzle are determined as auxiliary templates. Among them, setting the overlap rate between the seed template corresponding to the auxiliary template in terms of position and the adjacent seed template to be less than the overlap rate between this auxiliary template and the adjacent seed template can minimize the overlap rate between the seed template corresponding to the auxiliary template and the adjacent seed template as much as possible, so that the seed template has less redundant information, which is convenient for reducing the number of seed templates required to piece together the first virtual jigsaw puzzle, that is, reducing the number of seed templates used to recognize the fingerprint image to be recognized.

[0081] In some alternative embodiments, after the recognition of the fingerprint image to be recognized fails through multiple seed templates and before determining at least one reference area on the first virtual jigsaw puzzle according to the similarity between the fingerprint image to be recognized and the multiple seed templates, the fingerprint recognition method provided by the present application may further include: recognizing the fingerprint image to be recognized through at least one isolated template.

[0082] Since there is no overlapping area between the isolated template and any seed template, and the isolated template contains more valid information than the auxiliary template, recognizing the fingerprint image to be recognized through at least one isolated template can, to a certain extent, improve the success rate of fingerprint recognition, which is convenient for omitting the process of recognizing the fingerprint image to be recognized through the supplementary template and reducing the number of fingerprint templates used for fingerprint recognition.

[0083] In some alternative embodiments, after the fingerprint image to be recognized fails to be recognized by the supplementary template, the fingerprint image to be recognized may be recognized by at least one isolated template, so as to improve the success rate of fingerprint recognition as much as possible. It should be understood that although the seed template, the supplementary template, and the isolated template may be successively used to recognize the fingerprint image to be recognized in this embodiment, the supplementary template may only be a part of the auxiliary templates, so that some of the auxiliary templates are still not used in the process of fingerprint recognition, thereby reducing the number of fingerprint templates used for fingerprint recognition.

[0084] In some alternative embodiments, the fingerprint recognition method provided by the embodiments of the present application further includes: after the fingerprint image to be recognized is successfully recognized, updating the fingerprint template library according to the fingerprint image to be recognized; based on the updated fingerprint template library, determining the seed template, the auxiliary template, and the isolated template, or determining the seed template and the auxiliary template, so as to update the seed template, the auxiliary template, and the isolated template, or update the seed template and the auxiliary template.

[0085] After the fingerprint image to be recognized is successfully recognized, a fingerprint template may be generated according to the fingerprint image to be recognized, and the fingerprint template library may be updated by using the fingerprint template. It should be understood that the embodiments of the present application do not limit that the above process of updating the fingerprint template library will be executed every time the fingerprint image to be recognized is successfully recognized. It may also be executed at intervals according to a predetermined frequency or other conditions for the case where the fingerprint image to be recognized is successfully recognized.

[0086] It should be noted that, based on the updated fingerprint template library, the splicing relationship between the included fingerprint templates may be determined, so that according to the splicing relationship, the seed template, the auxiliary template, and the isolated template may be determined; or, the seed template and the auxiliary template may be determined. The specific implementation manner may refer to the above embodiments and will not be elaborated here.

[0087] It should be understood that since the splicing relationship between the original fingerprint templates in the fingerprint template library has been determined in step 230 above, when determining the splicing relationship between the fingerprint templates in the updated fingerprint template library, the splicing relationship between the fingerprint templates in the updated fingerprint template library may be determined by determining the new fingerprint templates in the fingerprint template library, such as at least part of the fingerprint template of the following fingerprint image to be recognized, and other fingerprint templates, so as to improve the efficiency of determining the splicing relationship.

[0088] In the embodiments of the present application, after successfully recognizing the fingerprint image to be recognized, the fingerprint template library can be updated according to the fingerprint image to be recognized. Based on the updated fingerprint template library, the seed template, the auxiliary template, and the isolated template are re-determined, or the seed template and the auxiliary template are re-determined, so as to update the seed template, the auxiliary template, and the isolated template, so that the seed template, the auxiliary template, and the isolated template have a relatively new timeliness and ensure the effectiveness of the seed template, the auxiliary template, and the isolated template, or update the seed template and the auxiliary template so that the seed template and the auxiliary template have a relatively new timeliness and ensure the effectiveness of the seed template and the auxiliary template.

[0089] In some alternative embodiments, after successfully recognizing the fingerprint image to be recognized, updating the fingerprint template library according to the fingerprint image to be recognized includes:

[0090] If the number of fingerprint templates in the fingerprint template library is less than the template number threshold, the fingerprint image to be recognized is added to the fingerprint template library as a fingerprint template.

[0091] The template number threshold can be set by those skilled in the art according to needs. For example, it can be set to 40. It should be understood that if the image area of the fingerprint image to be recognized is large, the fingerprint image to be recognized can be cropped, and at least part of the fingerprint image to be recognized is added to the fingerprint template library as a fingerprint template.

[0092] If the number of fingerprint templates in the fingerprint template library is equal to the template number threshold, at least part of the fingerprint image to be recognized is added to the fingerprint template library as a fingerprint template, and the fingerprint template with the largest corresponding overlap rate is deleted from the fingerprint template library. It should be noted that if there is an existing fingerprint template in the fingerprint template library that completely overlaps with at least part of the fingerprint image to be recognized as a fingerprint template, the existing fingerprint template can be deleted.

[0093] The overlap rate corresponding to a fingerprint template can be obtained by dividing the sum of the areas overlapping with each other fingerprint template on the fingerprint template by the total area of the fingerprint template.

[0094] In the embodiments of the present application, if the number of fingerprint templates in the fingerprint template library is less than the template number threshold, the fingerprint image to be recognized is added to the fingerprint template library as a fingerprint template to expand the fingerprint template library. If the number of fingerprint templates in the fingerprint template library is equal to the template number threshold, at least part of the fingerprint image to be recognized is added to the fingerprint template library as a fingerprint template, and the fingerprint template with the largest corresponding overlap rate is deleted from the fingerprint template library to minimize the overlap rate corresponding to the fingerprint templates in the fingerprint template library as much as possible, thereby improving the effectiveness of the fingerprint templates in the fingerprint template library.

[0095] According to the second aspect of the embodiments of the present application, as Figure 7As shown, a fingerprint recognition device 700 is provided, including:

[0096] An acquisition module 710, configured to acquire a fingerprint image to be recognized.

[0097] A first recognition module 720, configured to recognize the fingerprint image to be recognized through a plurality of seed templates, wherein the plurality of seed templates are spliced into at least one first virtual puzzle, and there are overlapping regions between adjacent seed templates in the first virtual puzzle.

[0098] A reference module 730, configured to determine at least one reference region on the first virtual puzzle according to the similarity between the fingerprint image to be recognized and the plurality of seed templates when the recognition of the fingerprint image to be recognized through the plurality of seed templates fails.

[0099] A supplement module 740, configured to determine, as a supplementary template, a supplementary template in the plurality of supplementary templates whose overlap rate with any reference region is greater than the overlap rate threshold.

[0100] A second recognition module 750, configured to recognize the fingerprint image to be recognized through the supplementary template.

[0101] The fingerprint recognition device in this embodiment is based on the same inventive concept as the foregoing embodiment of the fingerprint recognition method, and is used to implement the corresponding fingerprint recognition method in the foregoing plurality of method embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here. In addition, the function implementation of each unit in the fingerprint recognition device in this embodiment can be referred to the description of the corresponding part in the foregoing method embodiment, which will not be elaborated here either.

[0102] According to the third aspect of the embodiments of the present application, an electronic device is provided, and the specific implementation of the electronic device is not limited in the specific embodiments of the present application.

[0103] As Figure 8 shown, the electronic device may include: a processor 802, a communication interface 804, a memory 806, and a communication bus 808.

[0104] Wherein:

[0105] The processor 802, the communication interface 804, and the memory 806 communicate with each other through the communication bus 808.

[0106] The communication interface 804 is configured to communicate with other electronic devices or servers.

[0107] The processor 802 is configured to execute a program 810, and specifically may execute the relevant steps in the foregoing embodiment of the fingerprint recognition method.

[0108] Specifically, the program 810 may include program code that includes executable instructions, and the executable instructions may be computer operation instructions.

[0109] The processor 802 may be a CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application. One or more processors included in the intelligent device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0110] The memory 806 is used to store the program 810. The memory 806 may include high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0111] The program 810 may include multiple executable instructions. Specifically, the program 810 may cause the processor 802 to perform the operations corresponding to the fingerprint recognition method described in any one of the foregoing multiple method embodiments through the multiple executable instructions.

[0112] For the specific implementation of each step in the program 810, reference may be made to the corresponding steps and descriptions in the corresponding units in the foregoing method embodiments, and the corresponding beneficial effects are achieved, which will not be elaborated here. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices and modules described above may refer to the corresponding process descriptions in the foregoing method embodiments, which will not be elaborated here.

[0113] According to the fourth aspect of the embodiments of the present application, a computer storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, it implements the method described in any one of the foregoing multiple method embodiments. The computer storage medium includes but is not limited to: Compact Disc Read-Only Memory (CD-ROM), Random Access Memory (RAM), floppy disk, hard disk, or magneto-optical disk, etc.

[0114] The embodiments of the present application also provide a computer program product, including computer instructions, and the computer instructions instruct a computing device to perform the operations corresponding to any one of the foregoing multiple fingerprint recognition methods.

[0115] It should be noted that, according to the needs of implementation, each component / step described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0116] Those of ordinary skill in the art can realize that the units and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of the present application.

[0117] The above embodiments are only used to illustrate the embodiments of the present application, rather than to limit the embodiments of the present application. Those of ordinary skill in the relevant technical field can also make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The patent protection scope of the embodiments of the present application shall be defined by the claims.

Claims

1. A fingerprint recognition method, characterized in that: include: Obtaining a fingerprint image to be identified; Identify the fingerprint image to be identified by using a plurality of seed templates, wherein the plurality of seed templates are spliced ​​into at least one first virtual puzzle, and adjacent seed templates in the first virtual puzzle have overlapping areas; If the fingerprint image to be identified fails to be identified by using the multiple seed templates, determining at least one reference area from the first virtual puzzle according to the similarity between the fingerprint image to be identified and the multiple seed templates; Determine, as a supplementary template, an auxiliary template whose overlap rate with any of the reference areas is greater than an overlap rate threshold among the multiple auxiliary templates; The fingerprint image to be identified is identified using the supplementary template.

2. The method according to claim 1, characterized in that The determining at least one reference area from the first virtual puzzle according to the similarity between the fingerprint image to be identified and the plurality of seed templates comprises: Determining a plurality of candidate areas in the first virtual puzzle, wherein the sizes of the candidate areas are determined based on the size of the fingerprint image to be identified; Determining the similarity between the fingerprint image to be identified and the plurality of candidate regions; The multiple candidate regions are sorted in descending order of similarity with the fingerprint image to be identified; and at least one candidate region ranked first is determined as the reference region.

3. The method according to claim 1, characterized in that The method further comprises: Acquire a fingerprint template library including a plurality of fingerprint templates; Determine a splicing relationship between fingerprint templates in the fingerprint template library, wherein the splicing relationship is used to indicate a relative position and an overlapping rate between fingerprint templates in the fingerprint template library; According to the splicing relationship, the seed template, the auxiliary template and the isolated template are determined from the fingerprint template library; or, according to the splicing relationship, the seed template and the auxiliary template are determined from the fingerprint template library.

4. The method according to claim 3, characterized in that Determining the seed template, the auxiliary template, and the isolated template from the fingerprint template library according to the splicing relationship includes: According to the splicing relationship, a plurality of seed templates are determined from the fingerprint template library, and the plurality of seed templates can be spliced ​​into a connected first virtual puzzle; According to the splicing relationship, the fingerprint template in the fingerprint template library other than the seed template and located in the first virtual puzzle is determined as the auxiliary template, wherein the overlap rate between the seed template corresponding to the auxiliary template and the adjacent seed template is less than the overlap rate between the auxiliary template and the adjacent seed template; According to the splicing relationship, the fingerprint template in the fingerprint template library that is located outside the first virtual puzzle is determined as the isolated template, wherein, in at least one second virtual puzzle formed by splicing the isolated template, the area of ​​any second virtual puzzle is smaller than the area of ​​the first virtual puzzle, and the second virtual puzzle is a connected puzzle.

5. The method according to claim 3, characterized in that: The step of determining the seed template and the auxiliary template from the fingerprint template library comprises: According to the splicing relationship, a plurality of seed templates are determined from the fingerprint template library, and the plurality of seed templates can be spliced ​​into at least one first virtual puzzle, and the first virtual puzzle is a connected puzzle; According to the stitching relationship, the fingerprint template in the fingerprint template library other than the seed template and located within the first virtual puzzle is determined as the auxiliary template, wherein the overlap rate between the seed template corresponding to the auxiliary template and the adjacent seed template is less than the overlap rate between the auxiliary template and the adjacent seed template.

6. The method according to claim 3, characterized in that After the fingerprint image to be identified fails to be identified by the multiple seed templates, and before determining at least one reference area from the first virtual puzzle according to the similarity between the fingerprint image to be identified and the multiple seed templates, the method further includes: identifying the fingerprint image to be identified by at least one isolated template, wherein there is no overlapping area between the isolated template and any of the seed templates.

7. The method according to any one of claims 3 to 6, characterized in that: The method further comprises: After the fingerprint image to be identified is successfully identified, the fingerprint template library is updated according to the fingerprint image to be identified; Based on the updated fingerprint template library, the seed template, the auxiliary template and the isolated template are determined, or the seed template and the auxiliary template are determined.

8. The method according to claim 7, characterized in that After the fingerprint image to be identified is successfully identified, updating the fingerprint template library according to the fingerprint image to be identified includes: If the number of fingerprint templates in the fingerprint template library is less than the template number threshold, adding at least part of the fingerprint image to be identified as a fingerprint template to the fingerprint template library; If the number of fingerprint templates in the fingerprint template library is equal to the template number threshold, at least part of the fingerprint image to be identified is added as a fingerprint template to the fingerprint template library, and the fingerprint template with the largest corresponding overlap rate is deleted from the fingerprint template library.

9. A fingerprint recognition device, characterized in that: include: An acquisition module is used to acquire a fingerprint image to be identified; A first recognition module, configured to recognize the fingerprint image to be recognized by using a plurality of seed templates, wherein the plurality of seed templates are spliced ​​into at least one first virtual puzzle, and adjacent seed templates in the first virtual puzzle have overlapping areas; A reference module, configured to determine at least one reference area from the first virtual puzzle according to the similarity between the fingerprint image to be identified and the multiple seed templates when the fingerprint image to be identified fails to be identified by using the multiple seed templates; A supplementing module, configured to determine, as a supplementing template, an auxiliary template whose overlap rate with any of the reference areas among the multiple auxiliary templates is greater than an overlap rate threshold; The second recognition module is used to recognize the fingerprint image to be recognized by using the supplementary template.

10. An electronic device, comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute any method according to claims 1-8.

11. A computer storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images