Fingerprint recognition methods, devices, media and equipment

Abstract

This application discloses a fingerprint recognition method, apparatus, medium, and device, belonging to the field of biometric identification. When extracting fingerprint features, this application uses a public security algorithm to extract public security fingerprint features and a custom algorithm to extract custom fingerprint features. The extracted public security fingerprint features and custom fingerprint features are stored in their respective designated locations within the fingerprint minutiae data field of the binary format fingerprint feature value data. This ensures that the binary format fingerprint feature value data conforming to public security standards includes both public security fingerprint features and custom fingerprint features. During fingerprint comparison, it is compatible with fingerprint template data conforming to both public security algorithms and custom fingerprint features. Existing fingerprint template data using custom algorithms does not need to be modified or re-collected, saving significant manpower and time costs and improving the compatibility and success rate of fingerprint comparison.

Description

Technical Field

[0001] This application relates to the field of biometric identification, and in particular to a fingerprint identification method, device, medium and equipment. Background Technology

[0002] Biometric identification is becoming increasingly common, providing a convenient and quick way to verify identity for tasks such as unlocking devices, access control, and mobile payments. Fingerprint recognition technology is a biometric identification technology that uses the uniqueness and lifelong immutability of fingerprint features to authenticate an individual's identity.

[0003] The "Technical Specification for Fingerprint Collection and Comparison of Resident Identity Cards" (GA / T 1012-2019, hereinafter referred to as the "Fingerprint Specification") is an industry standard applicable to fingerprint collection and comparison for resident identity cards. Fingerprint algorithms conforming to the standard format of the "Fingerprint Specification" are called "Public Security Algorithms." According to the "Fingerprint Specification," the binary format of fingerprint feature values ​​is 512 bytes long, of which the total number of bytes for the fingerprint minutiae field is 480 bytes (see Table A.3 on page 8 of the "Fingerprint Specification" for an example of the fingerprint feature data file structure, "Field 12, relative position from 32-511," or as shown in Table 1 below). According to the definition in section A.1.2 of the "Fingerprint Specification," each fingerprint minutiae is represented by 4 bytes, meaning that there can be 120 fingerprint minutiae within 480 bytes.

[0004] Table 1: Binary format data of fingerprint feature values

[0005]

[0006] The "Fingerprint Specification" only defines the fingerprint feature data format, but it cannot be compatible with historical fingerprint data. If the data previously used was from a common algorithm (i.e., the fingerprint comparison algorithm of each enterprise, also known as a custom algorithm), and then the "Public Security Algorithm" is to be used, the format of the fingerprint template data of the previously existing common algorithm standard cannot be compared with the data collected according to the "Public Security Algorithm". It is necessary to re-collect fingerprint template data that conforms to the "Fingerprint Specification" according to the "Public Security Algorithm". Summary of the Invention

[0007] To address the shortcomings of existing technologies, this application provides a fingerprint recognition method, apparatus, medium, and device that, when using public security algorithms, is compatible with fingerprint template data from historical custom algorithms, increasing the flexibility and convenience of access and improving the fingerprint recognition pass rate.

[0008] The technical solution provided in this application is as follows:

[0009] In a first aspect, this application provides a fingerprint recognition method, the method comprising:

[0010] Obtain fingerprint image;

[0011] The fingerprint image is subjected to feature extraction using both a public security algorithm and a custom algorithm to obtain public security fingerprint features and custom fingerprint features; the public security fingerprint features and custom fingerprint features each include a predetermined number of fingerprint minutiae.

[0012] Generate fingerprint feature value binary format data that conforms to fingerprint specifications, and store the public security fingerprint features and custom fingerprint features in their respective designated positions in the fingerprint detail feature point data field of the fingerprint feature value binary format data;

[0013] The fingerprint feature value binary format data is compared with the fingerprint template data to determine whether the two come from the same finger;

[0014] Specifically, when the fingerprint template data conforms to the format of a custom fingerprint feature, the custom fingerprint feature of the binary format data of the fingerprint feature value is compared with the fingerprint template data; when the fingerprint template data conforms to the format of a public security fingerprint feature, the public security fingerprint feature of the binary format data of the fingerprint feature value is compared with the fingerprint template data.

[0015] Furthermore, the number of fingerprint detail points included in the public security fingerprint feature does not exceed 70, and the number of fingerprint detail points included in the custom fingerprint feature does not exceed 50.

[0016] Furthermore, the public security fingerprint features and the custom fingerprint features are stored in the first 280 bytes and the last 200 bytes of the fingerprint detail feature point data field of the binary format data of the fingerprint feature value, respectively.

[0017] Secondly, this application provides a fingerprint recognition device, the device comprising:

[0018] The data acquisition module is used to acquire fingerprint images;

[0019] The feature extraction module is used to extract features from the fingerprint image using both a public security algorithm and a custom algorithm, to obtain public security fingerprint features and custom fingerprint features; the public security fingerprint features and custom fingerprint features each include a predetermined number of fingerprint minutiae.

[0020] The feature generation module is used to generate fingerprint feature value binary format data that conforms to fingerprint specifications, and to store the public security fingerprint features and custom fingerprint features in their respective designated positions in the fingerprint detail feature point data field of the fingerprint feature value binary format data;

[0021] The fingerprint comparison module is used to compare the binary format data of the fingerprint feature value with the fingerprint template data to determine whether the two come from the same finger.

[0022] Specifically, when the fingerprint template data conforms to the format of a custom fingerprint feature, the custom fingerprint feature of the binary format data of the fingerprint feature value is compared with the fingerprint template data; when the fingerprint template data conforms to the format of a public security fingerprint feature, the public security fingerprint feature of the binary format data of the fingerprint feature value is compared with the fingerprint template data.

[0023] Furthermore, the number of fingerprint detail points included in the public security fingerprint feature does not exceed 70, and the number of fingerprint detail points included in the custom fingerprint feature does not exceed 50.

[0024] Furthermore, the public security fingerprint features and the custom fingerprint features are stored in the first 280 bytes and the last 200 bytes of the fingerprint detail feature point data field of the binary format data of the fingerprint feature value, respectively.

[0025] Thirdly, this application provides a computer-readable storage medium for fingerprint recognition, including a memory for storing processor-executable instructions that, when executed by the processor, implement the steps of the fingerprint recognition method described in the first aspect.

[0026] Fourthly, this application provides a device for fingerprint recognition, characterized in that it includes at least one processor and a memory storing computer-executable instructions, wherein the processor executes the instructions to implement the steps of the fingerprint recognition method described in the first aspect.

[0027] This application has the following beneficial effects:

[0028] When using public security algorithms, this application is compatible with fingerprint template data from historical custom algorithms, increasing the flexibility and convenience of access, saving costs for users, and without violating the "fingerprint specification" standard. Attached Figure Description

[0029] Figure 1 This is a flowchart of the fingerprint recognition method of this application;

[0030] Figure 2 This is a schematic diagram of the fingerprint recognition device of this application. Detailed Implementation

[0031] To make the technical problems, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0032] This application provides a fingerprint recognition method, such as... Figure 1 As shown, the method includes:

[0033] S100: Acquire fingerprint image.

[0034] This application does not limit the method of obtaining fingerprint images; it can be to collect fingerprint images on-site using a fingerprint scanner or to read fingerprint images that have already been collected and stored.

[0035] S200: The fingerprint image is subjected to feature extraction using the public security algorithm and the custom algorithm respectively, to obtain public security fingerprint features and custom fingerprint features; the public security fingerprint features and the custom fingerprint features each include a set number of fingerprint detail feature points.

[0036] In this application, "Public Security Algorithm" refers to a fingerprint algorithm conforming to the standard format of the "Technical Specification for Fingerprint Collection and Comparison of Resident Identity Cards" GA / T1012-2019, while "Custom Algorithm" refers to the fingerprint comparison algorithm specified by each enterprise itself, which was used by each enterprise before adopting the "Public Security Algorithm". The steps for fingerprint feature extraction using the Public Security Algorithm and the Custom Algorithm respectively comply with the "Fingerprint Specification" and the specific regulations of each enterprise, and will not be elaborated upon in this application. The extracted Public Security fingerprint features and Custom fingerprint features each include a set number of fingerprint detail feature points.

[0037] S300: Generates fingerprint feature value binary format data that conforms to fingerprint specifications, and stores public security fingerprint features and custom fingerprint features in their respective designated positions in the fingerprint detail feature point data field of the fingerprint feature value binary format data.

[0038] The fingerprint specification stipulates that the fingerprint minutiae data field (i.e., field 12) should total 480 bytes, with each minutiae represented by 4 bytes, allowing for a total of 120 minutiae. However, evaluation shows that the maximum number of minutiae is 70 (i.e., 280 bytes), which fully meets the fingerprint comparison requirements, leaving 200 bytes of space in field 12. Therefore, this application utilizes this 200-byte space to store fingerprint feature data from a custom algorithm. The data format of the custom algorithm is not mandatory, as long as the total data length of the public security fingerprint features and the custom fingerprint features does not exceed 480 bytes.

[0039] The binary format fingerprint feature data generated by this application includes both public security fingerprint features extracted by the public security algorithm that conform to the "fingerprint specification" and custom fingerprint features extracted by the custom algorithm that conform to the fingerprint algorithm standard previously used by the enterprise. When using this binary format fingerprint feature data for fingerprint comparison, it can be adapted to the newly adopted "public security algorithm" and is also compatible with the previously used custom algorithm.

[0040] In one implementation, the number of fingerprint detail points included in the public security fingerprint feature does not exceed 70, and the number of fingerprint detail points included in the custom fingerprint feature does not exceed 50.

[0041] Correspondingly, the public security fingerprint features and the custom fingerprint features are stored in the first 280 bytes and the last 200 bytes of the fingerprint detail feature point data field of the binary format data of the fingerprint feature value, respectively.

[0042] An example of field 12 of the binary format data of fingerprint feature values ​​is shown in the table below.

[0043]

[0044] S400: Compare the binary format data of the fingerprint feature value with the fingerprint template data to determine whether they come from the same finger.

[0045] Fingerprint comparison refers to the verification of fingerprint template data and fingerprint feature data to determine whether they come from the same finger.

[0046] Fingerprint template data is a set of data extracted from one or more fingerprint images after processing, which can characterize the inherent features of the fingerprint image. The fingerprint template data is pre-collected and processed during the registration stage and stored in the system database, and is compared with the newly collected fingerprint feature value binary format data during the identification stage.

[0047] The newly acquired fingerprint feature value binary format data during the identification stage is the fingerprint feature data, which is a set of data extracted after the fingerprint image is processed, and can characterize the inherent features of the fingerprint image. In this application, the data is generally acquired only once.

[0048] If a custom algorithm was previously used for fingerprint recognition, and a new public security algorithm is adopted, but fingerprint template data conforming to the public security algorithm has not yet been collected (meaning the system database only contains fingerprint template data that conforms to the previously used custom fingerprint features), then during fingerprint comparison, the custom fingerprint features in binary format will be compared with the fingerprint template data that conforms to those custom fingerprint features.

[0049] If a custom algorithm was not used for fingerprint recognition previously, and the public security algorithm was used directly, then fingerprint template data conforming to the public security algorithm needs to be collected from the database. During fingerprint comparison, the public security fingerprint features in binary format of the fingerprint characteristic values ​​will be compared with the fingerprint template data conforming to the public security algorithm.

[0050] If a custom algorithm was previously used for fingerprint recognition, and the new public security algorithm is adopted, and if fingerprint template data conforming to the public security algorithm has already been collected (meaning the system database contains both previously used fingerprint template data conforming to the custom fingerprint features and those conforming to the public security algorithm), then during fingerprint comparison, the custom fingerprint features and public security fingerprint features in binary format can be compared with their respective corresponding fingerprint template data.

[0051] This application uses a public security algorithm to extract public security fingerprint features and a custom algorithm to extract custom fingerprint features. The extracted public security fingerprint features and custom fingerprint features are stored in their respective designated locations within the fingerprint minutiae data field of the binary format fingerprint feature value data. This ensures that the binary format fingerprint feature value data conforming to public security standards includes both the public security fingerprint features extracted by the public security algorithm and the custom fingerprint features extracted by the custom algorithm. During fingerprint comparison, it is compatible with fingerprint template data conforming to both the public security algorithm and the custom fingerprint features. Existing fingerprint template data from the custom algorithm does not need to be modified or re-collected, saving significant manpower and time costs, improving fingerprint comparison compatibility, and increasing the fingerprint recognition pass rate.

[0052] Furthermore, existing technologies using public security algorithms are incompatible with the fingerprint template data of existing custom algorithms, thus requiring hardware upgrades and rendering the original hardware obsolete. The method described in this application eliminates the need to discard the existing hardware, saving equipment costs. When the public security algorithm is discontinued due to business needs, the original custom algorithm can be reverted to, and the existing hardware can be reused directly. In this case, both the fingerprint template data and fingerprint feature data conform to the custom algorithm, effectively reverting to the original ordinary fingerprint recognition method.

[0053] In summary, this application, when using public security algorithms, is compatible with fingerprint template data from historical custom algorithms, increasing the flexibility and convenience of access, saving costs for users, and without violating the "fingerprint specification" standard.

[0054] This application also provides a fingerprint recognition device, such as... Figure 2 As shown, the device includes:

[0055] Data acquisition module 1 is used to acquire fingerprint images.

[0056] Feature extraction module 2 is used to extract features from fingerprint images using public security algorithms and custom algorithms respectively, to obtain public security fingerprint features and custom fingerprint features; public security fingerprint features and custom fingerprint features each include a set number of fingerprint detail feature points.

[0057] The feature generation module 3 is used to generate fingerprint feature value binary format data that conforms to fingerprint specifications, and to store public security fingerprint features and custom fingerprint features in their respective designated positions in the fingerprint detail feature point data field of the fingerprint feature value binary format data.

[0058] The fingerprint comparison module 4 is used to compare the binary format data of fingerprint feature values ​​with the fingerprint template data to determine whether the two come from the same finger.

[0059] Specifically, when the fingerprint template data conforms to the format of the custom fingerprint feature, the custom fingerprint feature of the binary format fingerprint feature value is compared with the fingerprint template data. When the fingerprint template data conforms to the format of the public security fingerprint feature, the public security fingerprint feature of the binary format fingerprint feature value is compared with the fingerprint template data.

[0060] When using public security algorithms, this application is compatible with fingerprint template data from historical custom algorithms, increasing the flexibility and convenience of access, saving costs for users, and without violating the "fingerprint specification" standard.

[0061] In one example, the number of fingerprint detail points included in the public security fingerprint feature does not exceed 70, and the number of fingerprint detail points included in the custom fingerprint feature does not exceed 50.

[0062] Correspondingly, the public security fingerprint features and the custom fingerprint features are stored in the first 280 bytes and the last 200 bytes of the fingerprint detail feature point data field of the binary format data of the fingerprint feature value, respectively.

[0063] The apparatus provided in the above embodiments corresponds one-to-one with the embodiments of the aforementioned methods in terms of its implementation principle and the resulting technical effects. For the sake of brevity, any parts of the apparatus not mentioned in the embodiments can be referred to the corresponding content in the embodiments of the aforementioned methods. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the modules and units described in this apparatus can all be referred to the corresponding processes in the embodiments of the aforementioned methods, and will not be repeated here.

[0064] The fingerprint recognition method described in the above embodiments of this application can implement business logic through a computer program and record it on a storage medium. This storage medium can be read and executed by a computer, achieving the effects of the scheme described in the method embodiments of this specification. Therefore, embodiments of this application also provide a computer-readable storage medium for fingerprint recognition, including a memory for storing processor-executable instructions. When executed by a processor, these instructions implement the steps of the fingerprint recognition method included in the foregoing embodiments.

[0065] The storage medium may include a physical device for storing information, typically digitizing the information and then storing it using electrical, magnetic, or optical methods. The storage medium may include: devices that store information using electrical energy, such as various types of memory, like RAM and ROM; devices that store information using magnetic energy, such as hard disks, floppy disks, magnetic tapes, magnetic core memory, bubble memory, and USB flash drives; and devices that store information using optical methods, such as CDs or DVDs. Of course, there are other readable storage media, such as quantum memories and graphene memories.

[0066] The storage medium described above may also include other implementation methods according to the description of the method embodiments. The implementation principle and technical effects of this embodiment are the same as those of the foregoing method embodiments. For details, please refer to the description of the relevant method embodiments, which will not be repeated here.

[0067] This application also provides a device for fingerprint recognition. The device may be a standalone computer, or it may include an actual operating device that uses one or more of the methods or embodiments described in this specification. The fingerprint recognition device may include at least one processor and a memory storing computer-executable instructions. When the processor executes the instructions, it implements the steps of any one or more of the fingerprint recognition methods described above.

[0068] The device described above may also include other implementation methods according to the method embodiments. The implementation principle and technical effects of this embodiment are the same as those of the foregoing method embodiments. For details, please refer to the description of the relevant method embodiments, which will not be repeated here.

[0069] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A fingerprint recognition method, characterized in that, The method includes: Obtain fingerprint image; The fingerprint image is subjected to feature extraction using both a public security algorithm and a custom algorithm to obtain public security fingerprint features and custom fingerprint features; the public security fingerprint features and custom fingerprint features each include a predetermined number of fingerprint minutiae. Generate fingerprint feature value binary format data that conforms to fingerprint specifications, and store the public security fingerprint features and custom fingerprint features in their respective designated positions in the fingerprint detail feature point data field of the fingerprint feature value binary format data; The fingerprint feature value binary format data is compared with the fingerprint template data to determine whether the two come from the same finger; Specifically, when the fingerprint template data conforms to the format of a custom fingerprint feature, the custom fingerprint feature of the binary format data of the fingerprint feature value is compared with the fingerprint template data; when the fingerprint template data conforms to the format of a public security fingerprint feature, the public security fingerprint feature of the binary format data of the fingerprint feature value is compared with the fingerprint template data.

2. The fingerprint recognition method according to claim 1, characterized in that, The number of fingerprint detail points included in the public security fingerprint feature does not exceed 70, and the number of fingerprint detail points included in the custom fingerprint feature does not exceed 50.

3. The fingerprint recognition method according to claim 2, characterized in that, The public security fingerprint features and the custom fingerprint features are stored in the first 280 bytes and the last 200 bytes of the fingerprint detail feature point data field of the binary format data of the fingerprint feature value, respectively.

4. A fingerprint recognition device, characterized in that, The device includes: The data acquisition module is used to acquire fingerprint images; The feature extraction module is used to extract features from the fingerprint image using both a public security algorithm and a custom algorithm, to obtain public security fingerprint features and custom fingerprint features; the public security fingerprint features and custom fingerprint features each include a predetermined number of fingerprint minutiae. The feature generation module is used to generate fingerprint feature value binary format data that conforms to fingerprint specifications, and to store the public security fingerprint features and custom fingerprint features in their respective designated positions in the fingerprint detail feature point data field of the fingerprint feature value binary format data; The fingerprint comparison module is used to compare the binary format data of the fingerprint feature value with the fingerprint template data to determine whether the two come from the same finger. Specifically, when the fingerprint template data conforms to the format of a custom fingerprint feature, the custom fingerprint feature of the binary format data of the fingerprint feature value is compared with the fingerprint template data; when the fingerprint template data conforms to the format of a public security fingerprint feature, the public security fingerprint feature of the binary format data of the fingerprint feature value is compared with the fingerprint template data.

5. The fingerprint recognition device according to claim 4, characterized in that, The number of fingerprint detail points included in the public security fingerprint feature does not exceed 70, and the number of fingerprint detail points included in the custom fingerprint feature does not exceed 50.

6. The fingerprint recognition device according to claim 5, characterized in that, The public security fingerprint features and the custom fingerprint features are stored in the first 280 bytes and the last 200 bytes of the fingerprint detail feature point data field of the binary format data of the fingerprint feature value, respectively.

7. A computer-readable storage medium for fingerprint recognition, characterized in that, It includes a memory for storing processor-executable instructions, which, when executed by the processor, implement the steps of the fingerprint recognition method according to any one of claims 1-3.

8. A device for fingerprint recognition, characterized in that, It includes at least one processor and a memory storing computer-executable instructions, wherein the processor, when executing the instructions, implements the steps of the fingerprint recognition method according to any one of claims 1-3.

Images