Information identification method and device, equipment, storage medium and program product

Abstract

The invention provides an information identification method which can be applied to the technical field of big data and the technical field of information security. The information identification method comprises the following steps: acquiring a fingerprint picture to be matched; reading a standard fingerprint picture from a fingerprint database; extracting first sweat pore feature information and first minutia feature information from the to-be-matched fingerprint picture; extracting second sweat pore feature information and second minutia feature information from the standard fingerprint picture; performing first matching processing on the first sweat pore feature information and the second sweat pore feature information to obtain a reliable sweat pore feature information quantity, and performing second matching processing on the first minutia feature information and the second minutia feature information to obtain a reliable minutia feature information quantity; and based on the reliable sweat pore feature information quantity and the reliable minutia feature information quantity, generating an information identification result used for judging whether the identity authentication of the user is passed or not. The invention further provides an information identification device, equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the fields of big data technology and information security technology, and more specifically to an information identification method, apparatus, device, storage medium, and program product. Background Art

[0002] Related technologies usually perform identity authentication based on information entered by the user. The information entered by the user can be, for example, fingerprint information. Fingerprints are a biometric feature that is widely used at this stage and are a reproduction of the appearance of the epidermis of an individual's fingertips. Fingerprints are mainly composed of some unique ridge structures on the skin of the fingertips. The fingerprint image can be acquired by a contact acquisition device, and the singular point features, directional field features or detail point features of the fingerprint can be extracted from the fingerprint image, and the corresponding algorithm can be matched based on the ridge structure and detail points. In the process of realizing the concept of the present disclosure, the inventors found that there are at least the following problems in the related technology: the related fingerprint recognition method is usually based on only a single fingerprint feature for recognition, so the recognition method has poor security, low accuracy, and a large amount of calculation. Summary of the Invention

[0003] In view of the above problems, the present disclosure provides an information identification method, apparatus, device, storage medium and program product.

[0004] According to a first aspect of the present disclosure, an information identification method is provided, comprising: in response to a user's authorization to enter a fingerprint, obtaining a fingerprint image to be matched corresponding to the user; reading a standard fingerprint image corresponding to the fingerprint image to be matched from a pre-constructed fingerprint database; extracting first sweat pore feature information and first minutiae feature information from the fingerprint image to be matched; extracting second sweat pore feature information and second minutiae feature information from the standard fingerprint image; performing a first matching process on the first sweat pore feature information and the second sweat pore feature information to obtain a number of reliable sweat pore feature information, and performing a second matching process on the first minutiae feature information and the second minutiae feature information to obtain a number of reliable minutiae feature information; and generating an information identification result for determining whether the user's identity authentication has been passed based on the number of reliable sweat pore feature information and the number of reliable minutiae feature information.

[0005] According to an embodiment of the present disclosure, the first sweat pore characteristic information includes N first sweat pore position information, and the second sweat pore characteristic information includes M second sweat pore position information; performing a first matching process on the first sweat pore characteristic information and the second sweat pore characteristic information includes: for each first sweat pore position information, performing a sweat pore position matching process with the M second sweat pore position information respectively, to obtain N×M sweat pore position deviations corresponding to the N first sweat pore position information one by one; for each first sweat pore position information, when there is a target sweat pore position deviation in the M sweat pore position deviations, determining that the first sweat pore position information corresponding to the M sweat pore position deviations is reliable sweat pore characteristic information, wherein the target sweat pore position deviation is less than a first preset threshold.

[0006] According to an embodiment of the present disclosure, the first detail point feature information includes K first detail point position information, and the second detail point feature information includes L second detail point position information; performing a second matching process on the first detail point feature information and the second detail point feature information includes: for each first detail point position information, performing detail point position matching process with the L second detail point position information respectively, to obtain K×L detail point position deviations corresponding to the K first detail point position information; for each first detail point position information, when there is a target detail point position deviation in the L detail point position deviations, determining that the first detail point position information corresponding to the L detail point position deviations is reliable detail point feature information, wherein the target detail point position deviation is less than a second preset threshold.

[0007] According to an embodiment of the present disclosure, extracting the first sweat pore feature information and the first detail point feature information from the fingerprint image to be matched includes: extracting the first center detail point position information from the fingerprint image to be matched; determining the first screening area based on the first center detail point position information; determining the K first detail points and N first sweat pores included in the first screening area; determining the K first detail point position information corresponding one-to-one to the K first detail points, and the N first sweat pore position information corresponding one-to-one to the N first sweat pores.

[0008] According to an embodiment of the present disclosure, extracting the second sweat pore feature information and the second detail point feature information from the standard fingerprint image includes: extracting the second center detail point position information from the standard fingerprint image; determining the second screening area based on the second center detail point position information; determining the L second detail points and M second sweat pores included in the second screening area; determining the L second detail point position information corresponding one-to-one to the L second detail points, and the M second sweat pore positions corresponding one-to-one to the M second sweat pores.

[0009] According to an embodiment of the present disclosure, the information identification method also includes: determining the overlapping area between the fingerprint image to be matched and the standard fingerprint image; when the area of ​​the overlapping area is less than or equal to a third preset threshold, generating an information identification result for characterizing that the user's identity authentication has failed; when the area of ​​the overlapping area is greater than the third preset threshold, extracting the first sweat pore feature information and the first detail point feature information from the fingerprint image to be matched.

[0010] According to an embodiment of the present disclosure, based on the number of reliable sweat pore feature information and the number of reliable minutiae feature information, generating an information recognition result for determining whether the user's identity authentication is passed includes: calculating the ratio of the number of reliable minutiae feature information to the number of first minutiae feature information to obtain the reliable minutiae ratio; calculating the ratio of the number of reliable sweat pore feature information to the number of first sweat pore feature information to obtain the reliable sweat pore ratio; based on the reliable minutiae ratio and the reliable sweat pore ratio, generating a matching score corresponding to the fingerprint image to be matched; when the matching score meets the first preset numerical condition, generating an information recognition result of the user's identity authentication passing; when the matching score meets the second preset numerical condition, generating an information recognition result of the user's identity authentication failing.

[0011] The second aspect of the present disclosure provides an information identification device, including: an acquisition module, used to obtain a fingerprint image to be matched corresponding to the user in response to the user's authorization to enter a fingerprint; a reading module, used to read a standard fingerprint image corresponding to the fingerprint image to be matched from a pre-built fingerprint database; a first extraction module, used to extract first sweat pore feature information and first detail point feature information from the fingerprint image to be matched; a second extraction module, used to extract second sweat pore feature information and second detail point feature information from the standard fingerprint image; a matching processing module, used to perform a first matching process on the first sweat pore feature information and the second sweat pore feature information to obtain the number of reliable sweat pore feature information, and to perform a second matching process on the first detail point feature information and the second detail point feature information to obtain the number of reliable detail point feature information; a first generation module, used to generate an information identification result for determining whether the user's identity authentication is passed based on the number of reliable sweat pore feature information and the number of reliable detail point feature information.

[0012] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0013] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the computer program or instructions are executed by a processor.

[0014] A fifth aspect of the present disclosure provides a computer program product, comprising a computer program or instructions, which implement the steps of the above method when executed by a processor.

[0015] According to the embodiments of the present disclosure, by generating information recognition results based on both the number of reliable sweat pore feature information and the number of reliable minutiae feature information, rather than solely on a single fingerprint feature, the accuracy of the information recognition results can be improved, the computational complexity of the information recognition process can be reduced, and the efficiency of information recognition can be improved. Therefore, the technical problems of low accuracy and high computational complexity of fingerprint information recognition results in related technologies are at least partially overcome, thereby achieving the technical effect of efficiently and accurately generating information recognition results. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0017] Figure 1 Schematically illustrates an application scenario diagram of the information identification method, apparatus, device, storage medium, and program product according to an embodiment of the present disclosure;

[0018] Figure 2 The following schematically shows a flow chart of an information identification method according to an embodiment of the present disclosure;

[0019] Figure 3 A flowchart schematically illustrates a method for generating information recognition results according to an embodiment of the present disclosure;

[0020] Figure 4 Schematically shows a flow chart of an information identification method according to another embodiment of the present disclosure;

[0021] Figure 5 The following schematically shows a structural block diagram of an information identification device according to an embodiment of the present disclosure;

[0022] Figure 6 A block diagram of an electronic device suitable for implementing the information identification method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0023] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0024] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise," "include," etc. used herein indicate the presence of features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0025] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0026] When expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0027] It should be noted that the information identification method and device disclosed herein can be used in the technical fields of big data and information security in the field of financial technology, and can also be used in any field other than the field of financial technology. The application field of the information identification method and device disclosed herein is not limited.

[0028] In the technical solutions disclosed herein, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0029] In scenarios where personal information is used for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure all provide users with corresponding operation portals for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge, and skills, and have reached a certain level of professionalism.

[0030] Due to the high reproducibility of fingerprints and the ease of creating fingerprint impressions, fingerprint recognition technology is one of the most widely used identity authentication technologies. Fingerprint recognition typically requires consideration of both accuracy and convenience. Fingerprints have three layers of features. The first layer includes singular points and orientation fields, which are the visible ridges and valleys of the fingerprint. The second layer includes minutiae, which are the endpoints and bifurcations of the ridges. A fingerprint image of normal quality contains approximately 80 to 120 valid minutiae points. The third layer includes pores, with a complete fingerprint image typically containing over 1,000 pores. While the first and second layers can be obtained from 500dpi fingerprint images captured by traditional contact-based fingerprint collection devices, the third layer requires fingerprint images with a resolution exceeding 1,000dpi. The second layer of features is the primary feature used in current fingerprint recognition technology. In the process of realizing the concept of the present disclosure, the inventors found that there are at least the following problems in the related art: the related art usually performs identification based on only a single fingerprint feature, resulting in poor security of the identification process; and when identification is performed based only on the third feature, due to the large amount of sweat pore data in a complete fingerprint image, the computational complexity of the identification process is too large, the matching rate is low, and the convenience is poor.

[0031] In view of this, an embodiment of the present disclosure provides an information identification method, including obtaining a fingerprint image to be matched corresponding to the user in response to the user's authorization to enter a fingerprint; reading a standard fingerprint image corresponding to the fingerprint image to be matched from a pre-built fingerprint database; extracting first sweat pore feature information and first detail point feature information from the fingerprint image to be matched; extracting second sweat pore feature information and second detail point feature information from the standard fingerprint image; performing a first matching process on the first sweat pore feature information and the second sweat pore feature information to obtain the number of reliable sweat pore feature information, and performing a second matching process on the first detail point feature information and the second detail point feature information to obtain the number of reliable detail point feature information; based on the number of reliable sweat pore feature information and the number of reliable detail point feature information, generating an information identification result for determining whether the user's identity authentication is passed.

[0032] Figure 1 The application scenario diagram of the information identification method, apparatus, device, medium and program product according to the embodiments of the present disclosure is schematically shown.

[0033] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links or optical fiber cables.

[0034] A user may use a first terminal device 101, a second terminal device 102, or a third terminal device 103 to interact with a server 105 via a network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, or the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (for example only).

[0035] The first terminal device 101 , the second terminal device 102 , and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0036] The server 105 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process received data such as user requests, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the terminal devices.

[0037] It should be noted that the information identification method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the information identification device provided in the embodiment of the present disclosure can generally be set in the server 105. The information identification method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the information identification device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0038] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0039] The following will be based on Figure 1 The scene described by Figures 2 to 4 The information identification method of the disclosed embodiment is described in detail.

[0040] Figure 2 The flowchart of the information identification method according to the embodiment of the present disclosure is schematically shown. Figure 2As shown, the information identification method of this embodiment includes operations S210 to S260.

[0041] In operation S210 , in response to the user's authorization to enter a fingerprint, a fingerprint image to be matched corresponding to the user is obtained.

[0042] In operation S220, a standard fingerprint image corresponding to the fingerprint image to be matched is read from a pre-built fingerprint database.

[0043] In operation S230, first sweat pore feature information and first minutiae feature information are extracted from the fingerprint image to be matched.

[0044] In operation S240, second sweat pore feature information and second minutiae feature information are extracted from the standard fingerprint image.

[0045] In operation S250, a first matching process is performed on the first sweat pore feature information and the second sweat pore feature information to obtain a number of reliable sweat pore feature information, and a second matching process is performed on the first minutiae feature information and the second minutiae feature information to obtain a number of reliable minutiae feature information;

[0046] In operation S260, based on the number of reliable sweat pore feature information and the number of reliable minutiae feature information, an information recognition result is generated for determining whether the user's identity authentication is passed.

[0047] According to an embodiment of the present disclosure, user consent or authorization is required before obtaining user information. For example, before operation S210, a request to obtain user information is required. If the user consents or authorizes obtaining user information, operation S210 is performed. After the user consents or authorizes, an image of the user's entered fingerprint is captured to obtain a fingerprint image to be matched. The fingerprint image to be matched may include multiple first minutiae points and multiple first sweat pores.

[0048] According to an embodiment of the present disclosure, in operation S220, the fingerprint database may store pre-collected user fingerprint images, such as fingerprint images entered multiple times by the same user, or fingerprint images entered by different users.

[0049] According to an embodiment of the present disclosure, in operations S230-S240, the fingerprint image to be matched may include multiple first minutiae points and multiple first sweat pores. Position information of each of the multiple first minutiae points may be extracted to obtain first minutiae point feature information; position information of each of the multiple first sweat pores may also be extracted to obtain first sweat pore feature information. Correspondingly, the standard fingerprint image may include multiple second minutiae points and multiple second sweat pores. Position information of each of the multiple second minutiae points may be extracted to obtain second minutiae point feature information; position information of each of the multiple second sweat pores may also be extracted to obtain second sweat pore feature information.

[0050] According to an embodiment of the present disclosure, in operation S250, the first sweat pore feature and the second sweat pore feature may be matched, and the first minutiae feature and the second minutiae feature may be matched. If the first sweat pore feature and the second sweat pore feature have a high degree of match, and the first minutiae feature and the second minutiae feature have a high degree of match, it indicates that the fingerprint image to be matched and the standard fingerprint image correspond to the same finger fingerprint of the same user.

[0051] According to an embodiment of the present disclosure, in operation S260, the information recognition result may include a first information recognition result and a second information recognition result. A large number of reliable sweat pore feature information and a large number of reliable minutiae feature information indicate that the fingerprint image to be matched and the standard fingerprint image correspond to the same finger fingerprint of the same user, and therefore a first information recognition result indicating that the identity authentication is successful can be output. A small number of reliable sweat pore feature information and / or a small number of reliable minutiae feature information indicate that the fingerprint image to be matched and the standard fingerprint image may actually be from different users, or may be from different finger fingerprints of the same user, and therefore a second information recognition result indicating that the identity authentication is unsuccessful can be output.

[0052] According to the embodiments of the present disclosure, on the one hand, the information recognition result is generated based on both the number of reliable sweat pore feature information and the number of reliable minutiae feature information, rather than only based on a single fingerprint feature, thereby improving the accuracy of the information recognition result. On the other hand, since a fingerprint image includes a large number of sweat pores, if information matching is performed based only on sweat pore features, a large number of sweat pore features need to be extracted to improve the accuracy of the information matching result, resulting in a large amount of computation and low recognition efficiency. Compared with information recognition based only on sweat pore features, generating information recognition results based on both the number of reliable sweat pore feature information and the number of reliable minutiae feature information can reduce the amount of sweat pore feature information extracted, thereby reducing the computational complexity of the information recognition process while ensuring the accuracy of the information recognition result, thereby improving the information recognition efficiency.

[0053] According to an embodiment of the present disclosure, the first sweat pore characteristic information includes N pieces of first sweat pore position information, and the second sweat pore characteristic information includes M pieces of second sweat pore position information.

[0054] According to an embodiment of the present disclosure, N first sweat pores can be screened from the fingerprint image to be matched, and the position information of each of the N first sweat pores can be determined. The first sweat pore position information can be, for example, the coordinates of the first sweat pores. Correspondingly, M second sweat pores can be screened from the standard fingerprint image, and the position information of each second sweat pore can be extracted. The second sweat pore position information can be, for example, the coordinates of the second sweat pores.

[0055] According to an embodiment of the present disclosure, performing a first matching process on the first sweat pore characteristic information and the second sweat pore characteristic information includes: for each piece of first sweat pore position information, performing sweat pore position matching process with M pieces of second sweat pore position information respectively, to obtain N×M sweat pore position deviations corresponding one to one to the N pieces of first sweat pore position information; for each piece of first sweat pore position information, when there is a target sweat pore position deviation among the M sweat pore position deviations, determining that the first sweat pore position information corresponding to the M sweat pore position deviations is reliable sweat pore characteristic information, wherein the target sweat pore position deviation is less than a first preset threshold.

[0056] Each piece of first pore location information can be matched with each piece of second pore location information. For example, the pore location matching process can include calculating the similarity between each piece of first pore location information and each piece of second pore location information. Based on the similarity between the first pore location information and each piece of second pore location information, a pore location deviation can be determined. For each piece of first pore location information, if the pore location deviation between the first pore location information and a piece of second pore location information is less than a first preset threshold, it indicates that the first pore location information matches the piece of second pore location information. Therefore, the first pore location information can be determined as reliable pore location information, and the pore corresponding to the first pore location information is a reliable pore.

[0057] Furthermore, a first sweat pore location information may match multiple second sweat pore location information. For example, if multiple sweat pore location deviations generated by the first sweat pore location information and the multiple second sweat pore location information are all less than a first preset threshold, the first sweat pore location information is determined to match the multiple second sweat pore location information. When a first sweat pore location information matches multiple second sweat pore location information, the reliable sweat pore location information includes first reliable sweat pore location information and second reliable sweat pore location information. The first reliable sweat pore location information is the first sweat pore location information that matches the multiple second sweat pore location information; the second reliable sweat pore location information is the second sweat pore location information that matches the first reliable sweat pore location information.

[0058] For example, first sweat pore location information 1 through first sweat pore location information N are extracted from the fingerprint information to be matched; second sweat pore location information 1 through second sweat pore location information M are extracted from the standard fingerprint information. The first sweat pore location information 1 is matched with each of the M second sweat pore location information to obtain M sweat pore location deviations. If any sweat pore location deviation is less than a first preset threshold, the first sweat pore location information 1 is determined to be reliable sweat pore location information.

[0059] According to an embodiment of the present disclosure, the first minutiae feature information includes K first minutiae position information, and the second minutiae feature information includes L second minutiae position information. The first minutiae position information may include the coordinates of the first minutiae point, and the second minutiae position information may include the coordinates of the second minutiae point.

[0060] According to an embodiment of the present disclosure, performing a second matching process on the first detail point feature information and the second detail point feature information includes: for each piece of first detail point position information, performing detail point position matching process with L pieces of second detail point position information respectively, and obtaining K×L detail point position deviations corresponding to the K pieces of first detail point position information; for each piece of first detail point position information, when there is a target detail point position deviation in the L detail point position deviations, determining that the first detail point position information corresponding to the L detail point position deviations is reliable detail point feature information, wherein the target detail point position deviation is less than a second preset threshold.

[0061] According to an embodiment of the present disclosure, the minutiae position matching process may include: calculating, for each piece of first minutiae position information, a similarity between each piece of first minutiae position information and L pieces of second minutiae position information. If the position deviation of the minutiae point corresponding to the first minutiae position information is less than a second preset threshold, it indicates that the first minutiae position information matches the second minutiae position information, the first minutiae position information is reliable minutiae position information, and the first minutiae point corresponding to the first minutiae position information is a reliable minutiae point.

[0062] According to the embodiments of the present disclosure, by matching the sweat pore position deviation and the detail point position deviation with the first preset threshold and the second preset threshold respectively, reliable sweat pore feature information and reliable detail point feature information can be accurately screened out, thereby improving the accuracy of the information recognition results.

[0063] According to an embodiment of the present disclosure, after obtaining the original coordinates, polar coordinate conversion can be performed on the original coordinates. Specifically, N original sweat pore coordinates corresponding to the N first sweat pores can be obtained to obtain N first original sweat pore position information; and K original minutiae coordinates corresponding to the K first minutiae can be obtained to obtain K first original minutiae position information. The N first original sweat pore position information can constitute a first original sweat pore position information set H. The first original sweat pore position information set H is shown in Equation (1).

[0064] (1)

[0065] in, is the original coordinate of the first sweat pore, is the original coordinate of the Nth first sweat pore.

[0066] The K first original minutiae point position information can form a first original minutiae point position information set A. The first original minutiae point position information set A can be expressed as formula (2).

[0067] (2)

[0068] in, is the original coordinate of the first detail point, is the original coordinate of the Kth first detail point.

[0069] Correspondingly, for the standard fingerprint image, the M second original sweat pore position information can form the second original sweat pore position information set J. The second original sweat pore position information set J can be expressed as formula (3).

[0070] (3)

[0071] in, is the original coordinate of the first and second sweat pores, is the original coordinate of the Mth second sweat pore.

[0072] The L second original minutiae point position information can form a second original minutiae point position information set B. The second original minutiae point position information set B can be expressed as formula (4).

[0073] (4)

[0074] in, are the original coordinates of the first and second detail points, The original coordinates of the L-th second detail point.

[0075] In the above formulas, each element in the minutiae set is a triple, and each element in the pore set is a binary. x and y represent position, and θ represents direction. The original coordinates in the fingerprint image to be matched can be expressed as: (x0, y0, θ0); the original coordinates in the fingerprint image to be matched can be expressed as (x0, y0). The polar coordinate conversion process is shown in Equations (5) and (6).

[0076] (5)

[0077] (6)

[0078] In formula (5), is the coordinate of the current detail point to be converted, The coordinates of the target detail point converted from the current detail point to the polar coordinate system, r t is the polar diameter, e t is the polar angle, θt is the direction of the ridge line where the detail point is located relative to the center point. In formula (6), (x t ,y t ) is the current sweat pore coordinate to be converted, (r t ,e t ) is the coordinate of the target detail point converted from the current detail point to the polar coordinate system, r t is the polar diameter, e t is the polar angle.

[0079] For the standard fingerprint image, the method of performing polar coordinate conversion on the original coordinates of the detail points in the standard fingerprint image is to replace (x0, y0, θ0) in the above formula (5) with (0, 0, 0). The method of performing polar coordinate conversion on the original coordinates of the sweat pores in the standard fingerprint image is to replace (x0, y0) in the above formula (5) with (0, 0).

[0080] After the original coordinates in the fingerprint image to be matched and the standard fingerprint image are converted into polar coordinates, the first target sweat pore position information set H', the first target minutiae position information set A', the second target sweat pore position information set J', and the second target minutiae position information set B' can be obtained, as shown in Equations (7) to (10).

[0081] (7)

[0082] (8)

[0083] (9)

[0084] (10)

[0085] According to an embodiment of the present disclosure, extracting first sweat pore feature information and first minutiae feature information from a fingerprint image to be matched includes: extracting first central minutiae position information from the fingerprint image to be matched; determining a first screening area based on the first central minutiae position information; determining K first minutiae points and N first sweat pores included in the first screening area; and determining K pieces of first minutiae position information corresponding one-to-one to the K first minutiae points, and N pieces of first sweat pore position information corresponding one-to-one to the N first sweat pores.

[0086] According to an embodiment of the present disclosure, a first minutiae point can be randomly selected from the fingerprint image to be matched and used as the first central minutiae point. The coordinates of the first central minutiae point are then determined to obtain the position information of the first central minutiae point. Furthermore, based on the position information of the first central minutiae point, the first screening area can be determined by generating the first screening area with the first central minutiae point as the center and based on a predetermined side length of the first screening area.

[0087] Determining the K first minutiae points and N first sweat pores included in the first screening area may include extracting all or a predetermined number of first minutiae points and first sweat pores within the first screening area to obtain the K first minutiae points and N first sweat pores. Coordinate information for each first minutiae point and each first sweat pore may be determined to obtain K first minutiae point position information and N first sweat pore position information. For example, a first central minutiae point may be randomly selected from the image to be matched, and first sweat pores and first minutiae points within a 60-pixel perimeter around the first central minutiae point may be extracted, resulting in, for example, 15 to 30 sweat pores.

[0088] According to an embodiment of the present disclosure, extracting the second sweat pore feature information and the second detail point feature information from the standard fingerprint image includes: extracting the second center detail point position information from the standard fingerprint image; determining the second screening area based on the second center detail point position information; determining the L second detail points and M second sweat pores included in the second screening area; determining the L second detail point position information corresponding one-to-one to the L second detail points, and the M second sweat pore positions corresponding one-to-one to the M second sweat pores.

[0089] A second minutiae point can be randomly selected from the standard fingerprint image as the second central minutiae point. The coordinates of the second central minutiae point are determined to obtain position information of the second central minutiae point. Determining the second selection area based on the position information of the second central minutiae point can include generating the second screening area with the second central minutiae point as the center and based on a predetermined side length of the second screening area. The predetermined side length of the second screening area can be the same as or different from the predetermined side length of the first screening area.

[0090] Determining the L second minutiae points and M second sweat pores included in the second screening area may include extracting all or a predetermined number of the second minutiae points and second sweat pores in the second screening area to obtain K second minutiae points and N second sweat pores. Coordinate information of each second minutiae point and each second sweat pore is determined to obtain second minutiae point position information and second sweat pore position information.

[0091] According to the embodiments of the present disclosure, since a fingerprint image contains a large number of sweat pores, directly matching based on the characteristic information of all sweat pores would result in a large amount of computation and low matching efficiency. By predetermining the first and second screening areas and performing matching based only on the sweat pore characteristic information in the first and second screening areas, the computational effort can be reduced, thereby improving matching efficiency.

[0092] According to an embodiment of the present disclosure, the above-mentioned information identification method also includes: determining the overlapping area between the fingerprint image to be matched and the standard fingerprint image; when the area of ​​the overlapping area is less than or equal to a third preset threshold, generating an information identification result for characterizing that the user's identity authentication has failed; when the area of ​​the overlapping area is greater than the third preset threshold, extracting the first sweat pore feature information and the first detail point feature information from the fingerprint image to be matched.

[0093] The fingerprint image to be matched and the standard fingerprint image can be roughly aligned to determine the overlapping area between the fingerprint image to be matched and the standard fingerprint image. When the overlapping area between the fingerprint image to be matched and the standard fingerprint image is less than or equal to the third preset threshold, the subsequent first matching process and the second matching process can be abandoned, and the information recognition result indicating that the user's identity authentication has failed can be directly generated. On the contrary, when the area of ​​the overlapping area is greater than the third preset threshold, the subsequent first matching process and the second matching process can be continued. For example, the third preset threshold can be one-third of the area of ​​the fingerprint image to be identified. When the overlapping area is greater than one-third of the area of ​​the fingerprint image to be identified, the first matching process and the second matching process can be performed; when the overlapping area is less than or equal to one-third of the area of ​​the fingerprint image to be identified, the information recognition result indicating that the user's identity authentication has failed can be directly generated.

[0094] To determine the overlapping area, coordinate transformation processing can be performed on the original coordinates of the fingerprint image to be matched and the standard fingerprint image, respectively, so as to adjust the position and angle of the fingerprint image to be matched and the standard fingerprint image so that the fingerprint image to be matched and the standard fingerprint image are roughly aligned. For example, the original coordinates of the first sweat pore, the first minutiae point, the second sweat pore, and the second minutiae point can be obtained respectively, and the coordinate transformation processing can be performed on the above original coordinates to obtain the target coordinates, and the overlapping area is determined based on the target coordinates. The coordinate transformation processing can, for example, include: multiplying the above original coordinates by a transformation matrix and then adding a translation vector, as shown in Formula (11).

[0095] (11)

[0096] where x and y are the original coordinates, and are the transformed coordinates, , and are the horizontal translation, vertical translation and rotation angles respectively.

[0097] According to an embodiment of the present disclosure, when the overlapping area is less than or equal to the third preset threshold, there is no need to match the feature information of the detail points and the sweat pores. Instead, an information recognition result indicating that the user identity authentication has failed is directly generated. This can omit unnecessary steps in the information recognition method, reduce the amount of calculation, and improve the efficiency of information recognition.

[0098] Figure 3 The flowchart of the method for generating information recognition results according to an embodiment of the present disclosure is schematically shown. The method for generating information recognition results in this embodiment includes operations S310 to S350.

[0099] In operation S310 , a ratio of the number of reliable minutiae feature information to the number of first minutiae feature information is calculated to obtain a reliable minutiae ratio.

[0100] In operation S320 , a ratio of the number of reliable sweat pore feature information to the number of first sweat pore feature information is calculated to obtain a reliable sweat pore ratio.

[0101] In operation S330 , a matching score corresponding to the fingerprint image to be matched is generated based on the proportion of reliable minutiae points and the proportion of reliable sweat pores.

[0102] In operation S340 , when the matching score satisfies the first preset numerical condition, an information recognition result indicating that the user's identity authentication has passed is generated.

[0103] In operation S350 , when the matching score satisfies the second preset numerical condition, an information recognition result indicating that the user's identity authentication fails is generated.

[0104] According to an embodiment of the present disclosure, based on the proportion of reliable minutiae points and the proportion of reliable sweat pores, a matching score corresponding to the fingerprint image to be matched is generated as shown in formula (12).

[0105] (12)

[0106] Among them, k is the number of reliable minutiae feature information, K is the number of first minutiae position information; n is the number of first reliable sweat pore feature information, m is the number of second reliable sweat pore feature information; N is the number of first sweat pore position information, and M is the number of second sweat pore position information.

[0107] According to an embodiment of the present disclosure, the information recognition result may include a first information recognition result and a second information recognition result. The matching score meeting the first preset numerical condition may be that the matching score is greater than or equal to a preset score threshold. When the matching score is greater than or equal to the preset score threshold, it indicates that the ratio of reliable minutiae points to reliable minutiae points is high, indicating that the similarity between the fingerprint image to be matched and the standard fingerprint image is high, and therefore the fingerprint image to be matched and the standard fingerprint image both correspond to the same finger fingerprint of the same user. Therefore, a first information recognition result can be generated, and the first information recognition result can indicate that the user's identity authentication has been passed.

[0108] The matching score meeting the second preset numerical condition may be that the matching score is less than a preset score threshold. If the matching score is less than the preset score threshold, it indicates that the ratio of reliable minutiae points to reliable minutiae points is small, indicating that the similarity between the fingerprint image to be matched and the standard fingerprint image is low. Therefore, the fingerprint image to be matched and the standard fingerprint image may correspond to different users, or to different fingerprints of the same user. Therefore, a second information recognition result can be generated, which can indicate that the user's identity authentication has failed.

[0109] According to the embodiments of the present disclosure, by simultaneously matching based on detail point feature information and sweat pore feature information, on the one hand, non-liveness detection and reproducibility of fingerprints can be avoided, and on the other hand, the security, recognition accuracy, anti-counterfeiting ability and convenience of small-size fingerprint biometric recognition can be improved, and the computational complexity can be reduced, wherein small-size fingerprint biometric recognition can be to collect fingerprints in a limited space and perform fingerprint recognition.

[0110] Figure 4 The flowchart of the information identification method according to another embodiment of the present disclosure is schematically shown. Figure 4 As shown, the information identification method of this embodiment includes operations S410 to S440.

[0111] In operation S410, after obtaining the fingerprint image to be matched and the standard fingerprint image corresponding to the user, an overlapping area between the fingerprint image to be matched and the standard fingerprint image is determined.

[0112] In operation S420 , it is determined whether the area of ​​the overlapping region is smaller than or equal to a third preset threshold. If the area of ​​the overlapping region is smaller than or equal to the third preset threshold, the user identity authentication fails.

[0113] In operation S430 , when the area of ​​the overlapping region is greater than a third preset threshold, the number of reliable sweat pore feature information and the number of reliable minutiae feature information are determined.

[0114] In operation S440 , an information recognition result is generated based on the number of reliable sweat pore feature information and the number of reliable minutiae feature information.

[0115] According to an embodiment of the present disclosure, when a finger is pressed to collect a fingerprint image, the fingerprint of the finger will deform, which may change the position and direction of the fingerprint features, resulting in inaccurate extracted minutiae feature information and sweat pore feature information. For example, the extracted minutiae may contain pseudo-minutiae, true minutiae may be lost, or the position and direction of the minutiae may differ significantly. Therefore, before determining the overlapping area between the fingerprint image to be matched and the standard fingerprint image, the fingerprint image to be matched may be image calibrated to improve the accuracy of the collected feature information and increase the image matching speed. Image calibration of the fingerprint image to be matched may include: calibrating the minutiae in the fingerprint image to be matched and the standard fingerprint image. The calibration process is shown in Formula (13).

[0116] (13)

[0117] Among them, the standard fingerprint image is I temp , the calibration transformation model is G, p is a d-dimensional parameter vector, then I temp The converted image is I p .

[0118] Furthermore, when the standard fingerprint is 1 temp , in the case of the origin of the parameter vector space, At this time, the set of transformed images can be shown as formula (14).

[0119] (14)

[0120] Among them, I temp The definitions of R and p are as above and will not be repeated here. d is a d-dimensional real space, and I is the set of transformed images.

[0121] Based on the above formula (13) and formula (14), fingerprint calibration is to perform fingerprint calibration on the standard fingerprint image I temp , fingerprint image to be identified I input When the conversion model G of the two is known, the d-dimensional parameter vector p of the two fingerprint images is calculated.

[0122] When performing the second matching process on the first detail point feature information and the second detail point feature information, the first detail point feature information and the second detail point feature information may be the position information of the first detail point and the second detail point, so the conversion model The rotation angle of each detail point can be considered and coordinates . Assume that the standard fingerprint I in the fingerprint database temp The detail point feature information can be expressed as: , .in, is the total number of detail points, is the rectangular coordinate position information of the detail point, is the direction information of the detail point. The detail point feature information can be represented as , .

[0123] A detail point pair can be formed by randomly taking out a detail point feature information from the fingerprint image to be matched and the standard fingerprint image. To perform fingerprint calibration, the specific steps are as follows:

[0124] First, the fingerprint image coordinate transformation can be performed based on formula (15).

[0125] (15)

[0126] in, The calculation method of can be shown in formula (16). In formula (16), t x ,t y Respectively represent the translation of the fingerprint image on the x and y axes.

[0127] (16)

[0128] According to the embodiment of the present disclosure, when performing fingerprint calibration, on the one hand, it is necessary to consider the discretization order of the direction difference of the minutiae point. Specifically, the value range of the direction of the minutiae point of the fingerprint image is There are usually two methods to calculate the direction difference of detail points. The first method is to discretize the direction of the detail point pair and then take the difference of the discretized direction value; the second method is to calculate the direction difference of the detail point pair and then discretize the direction difference. In the case of the first method, the discretization degree can be represented by m, and the discretization degree of the two detail points θ is calculated. i and θj are discretized. Based on formula (17), Considering it as one unit may result in an error of two units. Formula (17) can be expressed as:

[0129] (17)

[0130] The second method only performs one discretization process, which can cause a direction error of one unit at most, which can be expressed by formula (18).

[0131] (18)

[0132] According to an embodiment of the present disclosure, the directional difference values ​​of the detail point pairs may be calculated first, and then the directional difference values ​​may be discretized to calculate the directional difference values.

[0133] When performing fingerprint calibration, on the other hand, it is necessary to consider the optimization problem of the angle range of the minutiae points. Specifically, the value range of the direction of the minutiae points in the fingerprint image can be , then the direction difference range of the detail point pair can be To reduce the directional error of detail points, the directional difference range can be changed to , the specific operation is shown in formula (19).

[0134] (19)

[0135] According to an embodiment of the present disclosure, in the direction difference After discretization, the final discretization angle can be obtained. temp and the fingerprint image to be matched I input , it can be estimated The optimal conversion parameters , so that I temp with I input The distance between them is the shortest, as shown in formula (20).

[0136] (20)

[0137] in, express with I temp The Euclidean distance of the image after transformation.

[0138] Furthermore, the distance between images can be calculated based on formula (21).

[0139] (twenty one)

[0140] in, ; Indicates whether the same type of minutiae points in the fingerprint image minutiae point set are the same; C Itemp with C Iinput is the detail point type matrix of the standard fingerprint image and the fingerprint image to be matched, is the category of the minutiae in the fingerprint image to be matched; is the height and width of the fingerprint image; is the area of ​​the overlapping region; g(n) is the area reduction formula for the overlapping region, which is used to prevent the overlapping part from being too small to be used for subsequent calculations. g(n) is shown in Formula (22).

[0141] (twenty two)

[0142] in: , , , , are the height and width of the standard fingerprint respectively.

[0143] When the image conversion parameters are optimized and the overlap area exceeds the preset overlap threshold, the angle information of the fingerprint image to be matched can be adjusted to achieve a rough alignment between the fingerprint image to be matched and the standard fingerprint image, and subsequent calculations can be performed on the overlap area. If the overlap area is less than the preset overlap threshold, the overlap area is too small to accurately match the fingerprints, so no further calculations are performed and the identification result, indicating that the user's identity authentication has failed, is directly output.

[0144] Based on the above information identification method, the present disclosure also provides an information identification device. Figure 5 The device is described in detail. Figure 5 The structural block diagram of the information identification device according to an embodiment of the present disclosure is schematically shown.

[0145] like Figure 5As shown, the information identification device 500 of this embodiment includes an acquisition module 510, a reading module 520, a first extraction module 530, a second extraction module 540, a matching processing module 550, and a first generation module 560. Among them, the acquisition module 510 is used to obtain the fingerprint image to be matched corresponding to the user in response to the user's authorization to enter the fingerprint. In one embodiment, the acquisition module 510 can be used to perform the operation S210 described above, which will not be repeated here. The reading module 520 is used to read the standard fingerprint image corresponding to the fingerprint image to be matched from a pre-built fingerprint database. In one embodiment, the reading module 520 can be used to perform the operation S220 described above, which will not be repeated here. The first extraction module 530 is used to extract the first sweat pore feature information and the first detail point feature information from the fingerprint image to be matched. In one embodiment, the first extraction module 530 can be used to perform the operation S230 described above, which will not be repeated here. The second extraction module 540 is used to extract the second sweat pore feature information and the second detail point feature information from the standard fingerprint image. In one embodiment, the second extraction module 540 can be used to perform the operation S240 described above, which will not be described in detail here. The matching processing module 550 is used to perform a first matching process on the first sweat pore feature information and the second sweat pore feature information to obtain the number of reliable sweat pore feature information, and to perform a second matching process on the first detail point feature information and the second detail point feature information to obtain the number of reliable detail point feature information. In one embodiment, the matching processing module 550 can be used to perform the operation S250 described above, which will not be described in detail here. The first generation module 560 is used to generate an information recognition result for determining whether the user's identity authentication is passed based on the number of reliable sweat pore feature information and the number of reliable detail point feature information. In one embodiment, the first generation module 560 can be used to perform the operation S260 described above, which will not be described in detail here.

[0146] According to an embodiment of the present disclosure, the matching processing module includes a pore position matching processing submodule and a first determination submodule. The pore position matching processing submodule is configured to perform pore position matching processing on each piece of first pore position information with M pieces of second pore position information, thereby obtaining N×M pore position deviations corresponding to the N pieces of first pore position information. The first determination submodule is configured to determine, for each piece of first pore position information, if a target pore position deviation exists among the M pore position deviations, that the first pore position information corresponding to the M pore position deviations is reliable pore feature information, wherein the target pore position deviation is less than a first preset threshold.

[0147] According to an embodiment of the present disclosure, the matching processing module further includes a detail point position matching processing submodule and a second determination submodule. The detail point position matching processing submodule is configured to perform detail point position matching processing on each piece of first detail point position information with L pieces of second detail point position information, thereby obtaining K×L detail point position deviations corresponding to the K pieces of first detail point position information; and the second determination submodule is configured to determine, for each piece of first detail point position information, that the first detail point position information corresponding to the L detail point position deviations is reliable detail point feature information if a target detail point position deviation exists among the L detail point position deviations, wherein the target detail point position deviation is less than a second preset threshold.

[0148] According to an embodiment of the present disclosure, the first extraction module includes a first extraction submodule, a third determination submodule, a fourth determination submodule, and a fifth determination submodule. The first extraction submodule is configured to extract first central minutiae location information from the fingerprint image to be matched; the third determination submodule is configured to determine a first screening area based on the first central minutiae location information; the fourth determination submodule is configured to determine K first minutiae and N first sweat pores included in the first screening area; and the fifth determination submodule is configured to determine K first minutiae location information corresponding one-to-one to the K first minutiae and N first sweat pore location information corresponding to the N first sweat pores.

[0149] According to an embodiment of the present disclosure, the second extraction module includes a second extraction submodule, a sixth determination submodule, a seventh determination submodule, and an eighth determination submodule. The second extraction submodule is configured to extract second central minutiae location information from the standard fingerprint image; the sixth determination submodule is configured to determine a second screening area based on the second central minutiae location information; the sixth determination submodule is configured to determine the L second minutiae and M second sweat pores included in the second screening area; and the eighth determination submodule is configured to determine the L second minutiae location information corresponding one-to-one to the L second minutiae and the M second sweat pore locations corresponding one-to-one to the M second sweat pores.

[0150] According to an embodiment of the present disclosure, the information recognition device further includes a determination module and a second generation module. The determination module is configured to determine the overlapping area between the fingerprint image to be matched and the standard fingerprint image; the second generation module is configured to generate an information recognition result indicating that the user's identity authentication has failed if the area of ​​the overlapping area is less than or equal to a third preset threshold. Furthermore, if the area of ​​the overlapping area is greater than the third preset threshold, first sweat pore feature information and first minutiae feature information are extracted from the fingerprint image to be matched.

[0151] According to an embodiment of the present disclosure, the first generation module includes a first calculation submodule, a second calculation submodule, a first generation submodule, a second generation submodule, and a third generation submodule. The first calculation submodule is used to calculate the ratio of the number of reliable minutiae feature information to the number of first minutiae feature information to obtain the reliable minutiae ratio; the second calculation submodule is used to calculate the ratio of the number of reliable sweat pore feature information to the number of first sweat pore feature information to obtain the reliable sweat pore ratio; the first generation submodule is used to generate a matching score corresponding to the fingerprint image to be matched based on the reliable minutiae ratio and the reliable sweat pore ratio; the second generation submodule is used to generate an information recognition result indicating that the user's identity authentication has passed if the matching score meets a first preset numerical condition; the third generation submodule is used to generate an information recognition result indicating that the user's identity authentication has failed if the matching score meets a second preset numerical condition.

[0152] According to embodiments of the present disclosure, any multiple of the acquisition module 510, reading module 520, first extraction module 530, second extraction module 540, matching processing module 550, and first generation module 560 may be combined into a single module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present disclosure, at least one of the acquisition module 510, reading module 520, first extraction module 530, second extraction module 540, matching processing module 550, and first generation module 560 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or may be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or may be implemented in any one of software, hardware, and firmware, or any suitable combination of these. Alternatively, at least one of the acquisition module 510, the reading module 520, the first extraction module 530, the second extraction module 540, the matching processing module 550, and the first generation module 560 can be at least partially implemented as a computer program module, which can perform the corresponding function when it is executed.

[0153] Figure 6 Schematically shows a block diagram of an electronic device suitable for implementing the information identification method according to an embodiment of the present disclosure. Figure 6As shown, electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 602 or programs loaded from a storage unit 608 into a random access memory (RAM) 603. Processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or related chipsets, and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)). Processor 601 may also include onboard memory for cache purposes. Processor 601 may include a single processing unit or multiple processing units for performing the various actions of the method flow according to the embodiment of the present disclosure. RAM 603 stores various programs and data required for the operation of electronic device 600. Processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. Processor 601 performs the various actions of the method flow according to the embodiment of the present disclosure by executing the programs in ROM 602 and / or RAM 603. It should be noted that programs may also be stored in one or more memories other than ROM 602 and RAM 603. The processor 601 may also execute various operations of the method flow according to the embodiment of the present disclosure by executing programs stored in one or more memories.

[0154] According to an embodiment of the present disclosure, electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to bus 604. Electronic device 600 may also include one or more of the following components connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 608 including a hard disk; and a communication section 609 including a network interface card such as a LAN card or modem. Communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. Removable media 611, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 610 as needed, so that computer programs read from the removable media can be installed into storage section 608 as needed.

[0155] The present disclosure provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently without being incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the methods of the present disclosure.

[0156] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 602 and / or RAM 603 described above, and / or one or more memories other than ROM 602 and RAM 603.

[0157] The embodiments of the present disclosure also include a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the information identification method provided by the embodiments of the present disclosure.

[0158] The computer program executes the above functions defined in the system / device of the embodiment of the present disclosure when the processor 601 executes the computer program. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0159] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0160] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from a removable medium 611. When the computer program is executed by the processor 601, the above-described functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0161] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0162] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0163] Those skilled in the art will appreciate that the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways, even if such combinations or couplings are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways without departing from the spirit and teachings of the present disclosure. All such combinations and / or couplings fall within the scope of the present disclosure.

[0164] The above describes the embodiments of the present disclosure. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be advantageously used in combination. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. An information identification method, characterized in that: The method comprises: In response to the user's authorization to enter the fingerprint, obtaining a fingerprint image to be matched corresponding to the user; Reading a standard fingerprint image corresponding to the fingerprint image to be matched from a pre-built fingerprint database; Extracting first sweat pore feature information and first minutiae feature information from the fingerprint image to be matched; Extracting second sweat pore feature information and second minutiae feature information from the standard fingerprint image; Performing a first matching process on the first sweat pore feature information and the second sweat pore feature information to obtain a number of reliable sweat pore feature information, and performing a second matching process on the first detail point feature information and the second detail point feature information to obtain a number of reliable detail point feature information; Based on the number of reliable sweat pore feature information and the number of reliable detail point feature information, an information recognition result is generated for determining whether the user's identity authentication has passed.

2. The method according to claim 1, characterized in that The first sweat pore characteristic information includes N first sweat pore position information, and the second sweat pore characteristic information includes M second sweat pore position information; The performing a first matching process on the first sweat pore characteristic information and the second sweat pore characteristic information comprises: For each of the first sweat pore position information, a sweat pore position matching process is performed with the M second sweat pore position information respectively to obtain N×M sweat pore position deviations corresponding to the N first sweat pore position information one by one; For each of the first sweat pore position information, when there is a target sweat pore position deviation among the M sweat pore position deviations, the first sweat pore position information corresponding to the M sweat pore position deviations is determined to be reliable sweat pore feature information, wherein the target sweat pore position deviation is less than a first preset threshold.

3. The method according to claim 2, characterized in that The first detail point feature information includes K first detail point position information, and the second detail point feature information includes L second detail point position information; The performing a second matching process on the first detail point feature information and the second detail point feature information comprises: For each of the first detail point position information, respectively perform detail point position matching processing with the L second detail point position information to obtain K×L detail point position deviations corresponding to the K first detail point position information; For each of the first detail point position information, when there is a target detail point position deviation among the L detail point position deviations, the first detail point position information corresponding to the L detail point position deviations is determined to be reliable detail point feature information, wherein the target detail point position deviation is less than a second preset threshold.

4. The method according to claim 3, characterized in that The step of extracting the first sweat pore feature information and the first minutiae feature information from the fingerprint image to be matched comprises: Extracting first center detail point position information from the fingerprint image to be matched; Determine a first screening area based on the first center detail point position information; Determine K first detail points and N first sweat pores included in the first screening area; Determine K first detail point position information corresponding one-to-one to the K first detail points, and N first sweat pore position information corresponding one-to-one to the N first sweat pores.

5. The method according to claim 3, characterized in that: The step of extracting the second sweat pore feature information and the second minutiae feature information from the standard fingerprint image comprises: Extracting the second center detail point position information from the standard fingerprint image; Determining a second screening area based on the second center detail point position information; Determine L second detail points and M second sweat pores included in the second screening area; Determine L second detail point position information corresponding one-to-one to the L second detail points, and M second sweat pore positions corresponding one-to-one to the M second sweat pores.

6. The method according to claim 1, characterized in that The method further comprises: Determine an overlapping area between the fingerprint image to be matched and the standard fingerprint image; When the area of ​​the overlapping region is less than or equal to a third preset threshold, generating an information recognition result indicating that the identity authentication of the user has failed; When the area of ​​the overlapping region is greater than a third preset threshold, first sweat pore feature information and first minutiae feature information are extracted from the fingerprint image to be matched.

7. The method according to claim 1, characterized in that The generating of the information recognition result for judging whether the user's identity authentication is passed based on the number of reliable sweat pore feature information and the number of reliable minutiae feature information includes: Calculating the ratio of the number of the reliable detail point feature information to the number of the first detail point feature information to obtain a reliable detail point ratio; Calculating the ratio of the number of reliable sweat pore characteristic information to the number of first sweat pore characteristic information to obtain a reliable sweat pore ratio; Based on the proportion of the reliable minutiae points and the proportion of the reliable sweat pores, generating a matching score corresponding to the fingerprint image to be matched; When the matching score satisfies a first preset numerical condition, generating an information recognition result of the user's identity authentication passing; When the matching score satisfies a second preset numerical condition, an information identification result indicating that the user's identity authentication fails is generated.

8. An information recognition device, characterized in that: The device comprises: An acquisition module, configured to acquire a fingerprint image to be matched corresponding to the user in response to the user's authorization to enter the fingerprint; A reading module, used to read a standard fingerprint image corresponding to the fingerprint image to be matched from a pre-built fingerprint database; A first extraction module, used to extract first sweat pore feature information and first minutiae feature information from the fingerprint image to be matched; A second extraction module, used to extract second sweat pore feature information and second minutiae feature information from the standard fingerprint image; a matching processing module, configured to perform a first matching process on the first sweat pore feature information and the second sweat pore feature information to obtain a number of reliable sweat pore feature information, and to perform a second matching process on the first detail point feature information and the second detail point feature information to obtain a number of reliable detail point feature information; The first generating module is used to generate an information recognition result for judging whether the identity authentication of the user is passed based on the number of reliable sweat pore feature information and the number of reliable detail point feature information.

9. An electronic device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images