Fingerprint image quality evaluation method and device, equipment and storage medium
By screening effective areas, detecting core points and calculating penalties, the problem of insufficient robustness and accuracy of existing fingerprint quality analysis methods is solved, and more accurate and flexible fingerprint image quality evaluation is achieved, which improves the system's Identify accuracy and security.
Patent Information
- Application Number
- CN202411183256.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-08-27
AI Technical Summary
The existing fingerprint quality analysis methods lack robustness and accuracy, making it difficult to adapt to the current changing application scenarios, resulting in identification errors and security vulnerabilities, affecting system performance and user experience.
By filtering the fingerprint image of the effective area based on the preset area, detect the core point and generate the core point coordinates and fingerprint confidence, calculate the offset, and use the penalty mechanism to calculate the first core score, otherwise calculate the second core score. , comprehensive scores for quality assessment.
It improves the accuracy and robustness of fingerprint image quality evaluation, can adapt to fingerprint image quality evaluation in different scenarios, reduces misjudgment and false rejection, and enhances system security and user experience.
Smart Images

Figure CN118968268A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of fingerprint image processing, and in particular to a fingerprint image quality assessment method, device, equipment and storage medium. Background Art
[0002] Fingerprint quality detection is important in various applications, especially in biometric and security systems. Low-quality fingerprint images may lead to incorrect or unrecognized recognition, thus affecting the overall performance of the system. By detecting and excluding low-quality fingerprint images, it is possible to ensure that the system uses high-quality data and improve recognition accuracy. In addition, low-quality fingerprints may lead to misjudgment (i.e., identifying the wrong fingerprint as the right one) or false rejection (i.e., failing to identify the right fingerprint). Fingerprint quality detection helps to reduce these errors and improve system reliability and user experience. Furthermore, in security systems, low-quality fingerprints may be exploited by attackers for forgery or deception. Detecting and excluding low-quality fingerprints can enhance system security and prevent potential security vulnerabilities. In addition, if the fingerprint submitted by the user is of low quality, it may take multiple attempts to successfully register or verify, resulting in a poor user experience. By detecting the fingerprint quality, feedback can be provided when the user submits it for the first time, helping the user to adjust the fingerprint collection and improve the success rate. It can be seen that the quality assessment of fingerprint images is a very important technology, so it has also become an important part of the fingerprint research and analysis process.
[0003] Existing fingerprint quality analysis methods are mostly based on traditional algorithms, which not only have poor robustness against different devices, but also have poor overall analysis accuracy. They are difficult to adapt to the current changing application scenarios and achieve good application results. Summary of the invention
[0004] The present application provides a fingerprint image quality assessment method, device, equipment and storage medium, which are used to solve the technical problem that existing fingerprint quality analysis methods lack robustness and accuracy and are difficult to meet application requirements.
[0005] In view of this, the first aspect of the present application provides a fingerprint image quality assessment method, comprising:
[0006] Based on the preset surface integral, a target fingerprint image with a qualified effective area is selected from the initial fingerprint image;
[0007] Detecting the core points in the target fingerprint image by using a preset detection model, and generating core point coordinates and fingerprint confidence;
[0008] After calculating the offset of the core point coordinates, determining whether the offset exceeds an offset threshold, and if so, calculating a first core score according to the core point coordinates and the fingerprint confidence based on a penalty mechanism;
[0009] If the offset does not exceed the offset threshold, calculating a second core score according to the core point coordinates and the fingerprint confidence;
[0010] The target fingerprint image is quality evaluated according to the first core score or the second core score to obtain a quality evaluation result.
[0011] Preferably, the method of screening a target fingerprint image with a qualified effective area from the initial fingerprint image based on a preset area integral includes:
[0012] Determine the area score of the initial fingerprint image through the fingerprint test library to obtain a preset area score;
[0013] Determine whether the preset area integral is greater than the area threshold, and if so, retain the corresponding image as the target fingerprint image;
[0014] If not, it is determined that the effective area of the initial fingerprint image is unqualified.
[0015] Preferably, the detecting the core point in the target fingerprint image by using a preset detection model and generating the core point coordinates and fingerprint confidence also includes:
[0016] If the core point of the target fingerprint image is not detected, the fingerprint quality is evaluated based on the area score corresponding to the target fingerprint image to obtain a rough evaluation result.
[0017] Preferably, after calculating the offset of the core point coordinates, determining whether the offset exceeds an offset threshold, and if so, calculating a first core score based on the core point coordinates and the fingerprint confidence based on a penalty mechanism, including:
[0018] The normalized calculation method is used to calculate the offset corresponding to the core point coordinates, wherein the offset includes an x-axis offset and a y-axis offset;
[0019] If the offset exceeds the offset threshold, a penalty score calculation formula is constructed based on the penalty mechanism;
[0020] Substitute the core point coordinates and the fingerprint confidence into the penalty score calculation formula to perform score calculation to obtain a first core score.
[0021] A second aspect of the present application provides a fingerprint image quality assessment device, comprising:
[0022] An area screening unit, used for screening target fingerprint images with qualified effective areas from the initial fingerprint images based on a preset area integral;
[0023] A core detection unit, used to detect core points in the target fingerprint image through a preset detection model, and generate core point coordinates and fingerprint confidence;
[0024] a first calculation unit, configured to determine whether the offset of the core point coordinates exceeds an offset threshold after calculating the offset of the core point coordinates, and if so, calculate a first core score according to the core point coordinates and the fingerprint confidence based on a penalty mechanism;
[0025] a second calculation unit, configured to calculate a second core score according to the core point coordinates and the fingerprint confidence if the offset does not exceed the offset threshold;
[0026] A quality assessment unit is used to perform quality assessment on the target fingerprint image according to the first core score or the second core score to obtain a quality assessment result.
[0027] Preferably, the area screening unit is specifically used for:
[0028] Determine the area score of the initial fingerprint image through the fingerprint test library to obtain a preset area score;
[0029] Determine whether the preset area integral is greater than the area threshold, and if so, retain the corresponding image as the target fingerprint image;
[0030] If not, it is determined that the effective area of the initial fingerprint image is unqualified.
[0031] Preferably, it also includes:
[0032] The area evaluation unit is used to perform fingerprint quality evaluation based on the area score corresponding to the target fingerprint image if the core point of the target fingerprint image is not detected, so as to obtain a rough evaluation result.
[0033] Preferably, the first computing unit is specifically configured to:
[0034] The normalized calculation method is used to calculate the offset corresponding to the core point coordinates, wherein the offset includes an x-axis offset and a y-axis offset;
[0035] If the offset exceeds the offset threshold, a penalty score calculation formula is constructed based on the penalty mechanism;
[0036] Substitute the core point coordinates and the fingerprint confidence into the penalty score calculation formula to perform score calculation to obtain a first core score.
[0037] A third aspect of the present application provides a fingerprint image quality assessment device, the device comprising a processor and a memory;
[0038] The memory is used to store program code and transmit the program code to the processor;
[0039] The processor is used to execute the fingerprint image quality assessment method described in the first aspect according to the instructions in the program code.
[0040] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program codes, and the program codes are used to execute the fingerprint image quality assessment method described in the first aspect.
[0041] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:
[0042] In the present application, a fingerprint image quality assessment method is provided, comprising: screening a target fingerprint image with a qualified effective area from an initial fingerprint image based on a preset surface integral; detecting core points in the target fingerprint image through a preset detection model, and generating core point coordinates and fingerprint confidence; after calculating the offset of the core point coordinates, determining whether the offset exceeds an offset threshold, and if so, calculating a first core score based on the core point coordinates and the fingerprint confidence based on a penalty mechanism; if the offset does not exceed the offset threshold, calculating a second core score based on the core point coordinates and the fingerprint confidence; and performing quality assessment on the target fingerprint image according to the first core score or the second core score to obtain a quality assessment result.
[0043] The fingerprint image quality assessment method provided by the present application analyzes the characteristics of the fingerprint image from different perspectives, determines the characteristic scores based on different calculation methods, and conducts targeted assessment of the fingerprint image quality by combining different scores, which can focus on the detailed characteristics of the fingerprint image and is more in line with the situation that fingerprints in different scenarios have different characteristics, and can ensure that the quality assessment results obtained based on this are accurate and reliable; and this process can adapt to the fingerprint image quality assessment of various scenarios and has good robustness. Therefore, the present application can solve the technical problem that the existing fingerprint quality analysis methods lack robustness and accuracy and are difficult to meet application requirements. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 A schematic diagram of a fingerprint image quality assessment method provided in an embodiment of the present application;
[0045] Figure 2 A schematic diagram of the structure of a fingerprint image quality assessment device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0046] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0047] For easier understanding, see Figure 1 , an embodiment of a fingerprint image quality assessment method provided by the present application includes:
[0048] Step 101: Screen target fingerprint images with qualified effective areas from initial fingerprint images based on preset surface integrals.
[0049] Furthermore, step 101 includes:
[0050] Determine the area score of the initial fingerprint image through the fingerprint test library to obtain a preset area score;
[0051] Determine whether the preset area integral is greater than the area threshold, if so, retain the corresponding image as the target fingerprint image;
[0052] If not, it is determined that the effective area of the initial fingerprint image is unqualified.
[0053] It should be noted that the fingerprint test library refers to the fingerprint surface integral test library, which refers to a database used to test small-area fingerprint recognition algorithms. This test library is mainly used for capacitive sensors of mobile terminals and computer terminals; it may contain fingerprint images of different individuals, which are used to evaluate and verify the performance of small-area fingerprint recognition algorithms. This embodiment can determine the area score corresponding to the initial fingerprint image based on the fingerprint test library, that is, the preset area integral.
[0054] Specifically, the preset area score is calculated. If the area exceeds the preset value, the full score of the fingerprint area is used as the preset area score. If it does not exceed, the current area is divided by the product of the preset value and the full score of the area as the preset area score.
[0055] Due to the different environments, scenarios and means of fingerprint extraction, not all fingerprint images have sufficient effective area. Therefore, it is necessary to screen out fingerprint images with sufficient effective area through the area threshold before entering the subsequent feature analysis and calculation process. It can be understood that the area threshold can be set according to the actual situation and is not limited here. If the preset area score is greater than the area threshold, it means that the fingerprint image has a large enough effective area, otherwise it does not; if there is enough effective area, it can be retained as the target fingerprint image for subsequent analysis, otherwise it can be preliminarily evaluated as a fingerprint image with unqualified effective area.
[0056] Step 102: Detect core points in the target fingerprint image using a preset detection model, and generate core point coordinates and fingerprint confidence.
[0057] Furthermore, step 102 further includes:
[0058] If the core point of the target fingerprint image is not detected, the fingerprint quality is evaluated based on the area score corresponding to the target fingerprint image to obtain a rough evaluation result.
[0059] It should be noted that the preset detection model is a target detection network. The network structure can be designed according to the actual situation. It is not limited here. As long as it can detect the core point of the fingerprint, output the corresponding coordinates, and generate the confidence. In this embodiment, the core point of the fingerprint image refers to the center point of the fingerprint, which is similar to a vortex point. The generated core point coordinates can be expressed as , the confidence can be expressed as .
[0060] It is understandable that fingerprint images are collected based on the results of sensors, and not all fingerprint images can ensure that the fingerprint is in the center and unbiased. Therefore, the preset detection model may not be able to detect the core point in the target fingerprint image. At this time, the corresponding core point coordinates and fingerprint confidence cannot be generated. Then, the fingerprint image quality can only be roughly evaluated based on the area score corresponding to the image, and the core point analysis of this fingerprint image is clearly unqualified. In addition, in the case of no core point or insufficient area, the fingerprint quality evaluation score is composed of the area score. Fingerprint images with insufficient effective area are not used for subsequent analysis in order to prevent insufficient feature extraction and affect the analysis results.
[0061] Step 103: After calculating the offset of the core point coordinates, determine whether the offset exceeds the offset threshold. If so, calculate the first core score based on the core point coordinates and the fingerprint confidence based on a penalty mechanism.
[0062] Furthermore, step 103 includes:
[0063] The normalized calculation method is used to calculate the offset corresponding to the core point coordinates, and the offset includes the x-axis offset and the y-axis offset;
[0064] If the offset exceeds the offset threshold, a penalty score calculation formula is constructed based on the penalty mechanism;
[0065] Substitute the core point coordinates and fingerprint confidence into the penalty score calculation formula to calculate the score and obtain the first core score.
[0066] It should be noted that the core point coordinates Both values in need to be normalized and calculated. The normalization range selected in this embodiment is 0~0.5; that is, the x-axis coordinate and the y-axis coordinate are expressed within 0.5, and the normalized value is the offset, which can be recorded as , including the x-axis offset and the y-axis offset. If the offset exceeds the offset threshold, it means that the core point is offset a lot, so a penalty mechanism is needed to calculate the evaluation score of the core point to prevent the core point from exceeding the offset range.
[0067] The penalty score calculation formula based on the penalty mechanism is expressed as:
[0068]
[0069] in, , , The offsets are The proportion of and confidence level; Score the first core; , , They are expressed as:
[0070]
[0071]
[0072]
[0073] in, , They are the weights corresponding to the two offsets, which can be expressed as:
[0074]
[0075]
[0076] By using the above calculation process, a first core score for quality assessment can be obtained, and quality assessment analysis of the current target fingerprint image can be implemented based on the first core score.
[0077] For example, if the core point coordinates are (0.9, 0.9), the confidence is 0.9; then the core point coordinates are normalized to the range of 0~0.5, then [0.9-0.5, 0.9-0.5]=(0.4, 0.4); that is, the core offset; the above formula can be used to calculate , ; If the full score of the score calculation process is defined as 50 points, then the proportion of x-axis offset, y-axis offset and confidence is , , ; Then based on the penalty score calculation formula, the first core score can be calculated .
[0078] Step 104: If the offset does not exceed the offset threshold, a second core score is calculated based on the core point coordinates and the fingerprint confidence.
[0079] For offsets that do not exceed the offset threshold , the calculation formula for the second core score can also be constructed, which is specifically expressed as:
[0080]
[0081] in, Represents the overall weight of the offset, represents the overall proportion of the offset, and , and It can be expressed as:
[0082]
[0083]
[0084]
[0085] For the case where the offset threshold is not exceeded, the second core score is mainly composed of two parts. Taking the above example, if the core point coordinates are (0.9, 0.9), the confidence is 0.9; then the above formula can be used to calculate , and Based on the obtained parameters and the calculation formula of the second core score, the second core score can be calculated. .
[0086] Step 105: Perform quality assessment on the target fingerprint image according to the first core score or the second core score to obtain a quality assessment result.
[0087] It is understandable that the first core score and the second core score should be determined by selecting one of them, and the specific determination method is as described above. In order to describe the fingerprint quality more accurately and reliably, this embodiment can also combine the score and the area score for quality assessment, that is, add the area score corresponding to the fingerprint image on the basis of the calculated score, that is, the preset area score; then perform quality assessment on the current fingerprint image based on the total score obtained to obtain a quality assessment result. Specifically, the first core score plus the preset area score is used as the total evaluation score, or the second core score plus the preset area score is used as the total evaluation score.
[0088] The fingerprint image quality assessment method provided in the embodiment of the present application analyzes the characteristics of the fingerprint image from different perspectives, determines the characteristic scores based on different calculation methods, and conducts targeted assessment of the fingerprint image quality by combining different scores, which can focus on the detailed characteristics of the fingerprint image, and is more in line with the situation that fingerprints in different scenes have different characteristics, and can ensure that the quality assessment results obtained based on this are accurate and reliable; and this process can adapt to the fingerprint image quality assessment of various scenes, and has good robustness. Therefore, the embodiment of the present application can solve the technical problem that the existing fingerprint quality analysis method lacks robustness and accuracy and is difficult to meet application requirements.
[0089] For easier understanding, see Figure 2 The present application provides an embodiment of a fingerprint image quality assessment device, comprising:
[0090] An area screening unit 201 is used to screen target fingerprint images with qualified effective areas from the initial fingerprint images based on a preset area integral;
[0091] The core detection unit 202 is used to detect the core points in the target fingerprint image through a preset detection model and generate the core point coordinates and fingerprint confidence;
[0092] A first calculation unit 203 is used to determine whether the offset of the core point coordinates exceeds the offset threshold after calculating the offset of the core point coordinates. If so, calculate a first core score according to the core point coordinates and the fingerprint confidence based on a penalty mechanism;
[0093] A second calculation unit 204 is configured to calculate a second core score according to the core point coordinates and the fingerprint confidence if the offset does not exceed the offset threshold;
[0094] The quality assessment unit 205 is used to perform quality assessment on the target fingerprint image according to the first core score or the second core score to obtain a quality assessment result.
[0095] Furthermore, the area screening unit 201 is specifically used for:
[0096] Determine the area score of the initial fingerprint image through the fingerprint test library to obtain a preset area score;
[0097] Determine whether the preset area integral is greater than the area threshold, if so, retain the corresponding image as the target fingerprint image;
[0098] If not, it is determined that the effective area of the initial fingerprint image is unqualified.
[0099] Furthermore, it also includes:
[0100] The area evaluation unit 206 is used to perform fingerprint quality evaluation based on the area score corresponding to the target fingerprint image if the core point of the target fingerprint image is not detected, so as to obtain a rough evaluation result.
[0101] Further, the first calculation unit 203 is specifically configured to:
[0102] The normalized calculation method is used to calculate the offset corresponding to the core point coordinates, and the offset includes the x-axis offset and the y-axis offset;
[0103] If the offset exceeds the offset threshold, a penalty score calculation formula is constructed based on the penalty mechanism;
[0104] Substitute the core point coordinates and fingerprint confidence into the penalty score calculation formula to calculate the score and obtain the first core score.
[0105] The present application also provides a fingerprint image quality assessment device, the device comprising a processor and a memory;
[0106] The memory is used to store the program code and transmit the program code to the processor;
[0107] The processor is used to execute the fingerprint image quality assessment method in the above method embodiment according to the instructions in the program code.
[0108] The present application also provides a computer-readable storage medium, which is used to store program codes, and the program codes are used to execute the fingerprint image quality assessment method in the above method embodiment.
[0109] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0110] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0111] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0112] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions for executing all or part of the steps of the method described in each embodiment of the present application through a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.
[0113] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A fingerprint image quality assessment method, characterized in that: include: Based on the preset surface integral, a target fingerprint image with a qualified effective area is selected from the initial fingerprint image; Detecting the core points in the target fingerprint image by using a preset detection model, and generating core point coordinates and fingerprint confidence; After calculating the offset of the core point coordinates, determining whether the offset exceeds an offset threshold, and if so, calculating a first core score according to the core point coordinates and the fingerprint confidence based on a penalty mechanism; If the offset does not exceed the offset threshold, calculating a second core score according to the core point coordinates and the fingerprint confidence; The target fingerprint image is quality evaluated according to the first core score or the second core score to obtain a quality evaluation result.
2. The fingerprint image quality assessment method according to claim 1, characterized in that: The method of screening a target fingerprint image with a qualified effective area from an initial fingerprint image based on a preset surface integral comprises: Determine the area score of the initial fingerprint image through the fingerprint test library to obtain a preset area score; Determine whether the preset area integral is greater than the area threshold, and if so, retain the corresponding image as the target fingerprint image; If not, it is determined that the effective area of the initial fingerprint image is unqualified.
3. The fingerprint image quality assessment method according to claim 1, characterized in that: The method of detecting the core point in the target fingerprint image by using a preset detection model and generating the core point coordinates and fingerprint confidence also includes: If the core point of the target fingerprint image is not detected, the fingerprint quality is evaluated based on the area score corresponding to the target fingerprint image to obtain a rough evaluation result.
4. The fingerprint image quality assessment method according to claim 1, characterized in that: After calculating the offset of the core point coordinates, determining whether the offset exceeds an offset threshold, and if so, calculating a first core score based on the core point coordinates and the fingerprint confidence based on a penalty mechanism, including: The normalized calculation method is used to calculate the offset corresponding to the core point coordinates, wherein the offset includes an x-axis offset and a y-axis offset; If the offset exceeds the offset threshold, a penalty score calculation formula is constructed based on the penalty mechanism; Substitute the core point coordinates and the fingerprint confidence into the penalty score calculation formula to perform score calculation to obtain a first core score.
5. A fingerprint image quality assessment device, characterized in that: include: An area screening unit, used for screening target fingerprint images with qualified effective areas from the initial fingerprint images based on a preset area integral; A core detection unit, used to detect core points in the target fingerprint image through a preset detection model, and generate core point coordinates and fingerprint confidence; a first calculation unit, configured to determine whether the offset of the core point coordinates exceeds an offset threshold after calculating the offset of the core point coordinates, and if so, calculate a first core score according to the core point coordinates and the fingerprint confidence based on a penalty mechanism; a second calculation unit, configured to calculate a second core score according to the core point coordinates and the fingerprint confidence if the offset does not exceed the offset threshold; A quality assessment unit is used to perform quality assessment on the target fingerprint image according to the first core score or the second core score to obtain a quality assessment result.
6. The fingerprint image quality assessment device according to claim 5, characterized in that: The area screening unit is specifically used for: Determine the area score of the initial fingerprint image through the fingerprint test library to obtain a preset area score; Determine whether the preset area integral is greater than the area threshold, and if so, retain the corresponding image as the target fingerprint image; If not, it is determined that the effective area of the initial fingerprint image is unqualified.
7. The fingerprint image quality assessment device according to claim 5, characterized in that: Also includes: The area evaluation unit is used to perform fingerprint quality evaluation based on the area score corresponding to the target fingerprint image if the core point of the target fingerprint image is not detected, so as to obtain a rough evaluation result.
8. The fingerprint image quality assessment device according to claim 5, characterized in that: The first computing unit is specifically configured to: The normalized calculation method is used to calculate the offset corresponding to the core point coordinates, wherein the offset includes an x-axis offset and a y-axis offset; If the offset exceeds the offset threshold, a penalty score calculation formula is constructed based on the penalty mechanism; Substitute the core point coordinates and the fingerprint confidence into the penalty score calculation formula to perform score calculation to obtain a first core score.
9. A fingerprint image quality assessment device, characterized in that: The device comprises a processor and a memory; The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the fingerprint image quality assessment method according to any one of claims 1 to 4 according to the instructions in the program code.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program codes, and the program codes are used to execute the fingerprint image quality assessment method according to any one of claims 1 to 4.
Citation Information
Patent Citations
Single-target tracking method and device, electronic equipment and storage medium
CN114155276A
Fingerprint image quality detection method and device, electronic equipment and storage medium
CN114332046A
Fingerprint anti-counterfeiting method and device and electronic equipment
CN117854122A
Fingerprint identification method and device, electronic equipment and storage medium
CN118397661A
Derived virtual quality parameters for fingerprint matching
US9626549B1
