A method, system, device and storage medium for repairing a background of a fingerprint image

Abstract

This application relates to a fingerprint image background restoration method, system, device, and storage medium, applied in the field of capacitive fingerprint sensors. The method includes: acquiring a background image of the fingerprint sensor at a default gain; dividing the background image into several regions to be restored according to a preset grayscale range, recording the positions of the regions to be restored relative to the background image, and determining the region to be restored containing the most pixels as a standard region; determining the average grayscale value of the standard region as a standard grayscale value, and determining the difference between the average grayscale value of the several regions to be restored and the standard grayscale value as several gain compensation values; successively adjusting the gain of the fingerprint sensor according to the several gain compensation values, and successively acquiring the fingerprint image to be restored after the gain adjustment of the fingerprint sensor; extracting regions from the several fingerprint images to be restored according to the positions of the regions to be restored relative to the background image, and integrating the extracted regions to obtain the restored fingerprint image.

Description

Technical Field

[0001] This application relates to the technical field of capacitive fingerprint sensors, and in particular to a fingerprint image background restoration method, system, device, and storage medium. Background Technology

[0002] With technological advancements and increasing security demands, fingerprint recognition technology has gradually become a common biometric technology. Capacitive fingerprint sensors are a key device widely used in fingerprint recognition systems. They acquire fingerprint images by measuring changes in capacitance over the fingerprint area. Their small size and low power consumption have led to their widespread adoption in the market. In recent years, to reduce costs and improve production efficiency, even lower-cost capacitive fingerprint sensors have emerged. However, while these low-cost sensors reduce costs, they also introduce a new problem: unevenness in the fingerprint image background.

[0003] Current solutions to the problem of uneven background in fingerprint images include remapping the grayscale values ​​of the fingerprint image using image equalization technology. This stretches the grayscale value distribution in the original fingerprint image to the entire grayscale range, thereby enhancing the contrast and details of the fingerprint image, correcting uneven background brightness areas, and making the background of the entire fingerprint image more uniform.

[0004] Since image equalization technology processes the entire fingerprint image, it cannot accurately handle local features within the fingerprint image. For fingerprint images with uneven lighting or complex backgrounds, equalization technology can lead to the loss or blurring of local details, thus negatively impacting subsequent fingerprint feature extraction and fingerprint recognition. Summary of the Invention

[0005] In order to accurately process the local features of fingerprint images and reduce the loss or blurring of local details in fingerprint images during the fingerprint image background restoration process, this application provides a fingerprint image background restoration method, system, device and storage medium.

[0006] In a first aspect, this application provides a fingerprint image background restoration method, employing the following technical solution: the method includes:

[0007] Obtain the background image of the fingerprint sensor at the default gain;

[0008] The background image is divided into several regions to be repaired according to a preset grayscale range. The grayscale range includes several grayscale ranges. The positions of several regions to be repaired relative to the background image are recorded, and the region to be repaired containing the most pixels is determined as the standard region.

[0009] The average gray value of the standard area is determined as the standard gray value, and the difference between the average gray value of several areas to be repaired and the standard gray value is determined as several gain compensation values.

[0010] The gain of the fingerprint sensor is adjusted sequentially according to several gain compensation values, and the fingerprint image to be repaired is acquired sequentially after the gain of the fingerprint sensor is adjusted.

[0011] Based on the position of the area to be repaired relative to the background image, regions are extracted from several fingerprint images to be repaired, and the extracted regions are integrated to obtain the repaired fingerprint image.

[0012] The above technical solution divides the background image under the sensor's default gain into several regions to be repaired. Gain compensation is applied to these regions to obtain several fingerprint images to be repaired. Then, based on the position of each region relative to the background image, region extraction is performed on each of these fingerprint images. The extracted regions are then integrated to obtain the repaired fingerprint image. This allows for adaptive adjustment of the gain based on the grayscale characteristics of different regions, rather than applying a single gain compensation to the entire image. This precise processing of problematic local areas reduces the possibility of losing local details, improves the accuracy of fingerprint image background repair, and consequently enhances the effectiveness of subsequent fingerprint feature extraction and fingerprint recognition.

[0013] In one specific implementation, the background image is divided into several regions to be repaired according to a preset grayscale range, wherein the grayscale range includes several grayscale ranges, including:

[0014] Traverse all pixels of the background image and obtain the grayscale value corresponding to each pixel of the background image;

[0015] The grayscale values ​​of the pixels in the background image are compared one by one with several grayscale ranges;

[0016] The regions corresponding to pixels whose gray values ​​belong to the same gray range are divided into the regions to be repaired.

[0017] The above technical solution compares the gray values ​​of each pixel in the background image with the gray range one by one, and then divides the regions corresponding to pixels whose gray values ​​belong to the same gray range into regions to be repaired. This method of dividing regions can group pixels into different regions to be repaired based on their gray values, which can more accurately locate the regions to be repaired, reduce the possibility of incorrectly including pixels in the repair range, improve the accuracy and reliability of background image region division, and thus improve the effect of subsequent fingerprint image background repair.

[0018] In one specific implementation, the step of extracting regions from several fingerprint images to be repaired based on the position of the region to be repaired relative to the background image includes:

[0019] Determine the target gain compensation value corresponding to the fingerprint image to be repaired;

[0020] Determine the region to be repaired corresponding to the target gain compensation value;

[0021] Based on the position of the area to be repaired relative to the background image, the area to be stitched is determined in the fingerprint image to be repaired;

[0022] Region extraction is performed on the area to be stitched within the fingerprint image to be repaired.

[0023] By employing the aforementioned technical solution, the fingerprint image to be repaired is found based on the gain compensation value corresponding to the area to be repaired. Then, based on the position of the area to be repaired relative to the background image, the stitching area in the fingerprint image to be repaired is determined. This allows for more precise positioning of the area used to repair the fingerprint image background, improving the accuracy of fingerprint image background repair. Furthermore, by extracting the stitching area of ​​the fingerprint image to be repaired, it is helpful to subsequently match these stitching areas with the areas to be repaired in the background image and perform subsequent stitching operations, thereby improving the effect of subsequent fingerprint image background repair.

[0024] In one specific implementation, the step of integrating the extracted regions to obtain the repaired fingerprint image includes:

[0025] Determine the area to be repaired corresponding to the area to be spliced;

[0026] Based on the position of the area to be repaired relative to the background image, determine the stitching positions of several areas to be stitched together;

[0027] The first fingerprint image is obtained by splicing several regions to be spliced ​​according to the splicing position;

[0028] The repaired fingerprint image was determined based on the first fingerprint image.

[0029] By identifying the corresponding repair area to be stitched, the above technical solution allows for precise selection of the areas requiring repair and stitching, mitigating the risk of stitching errors or omissions, ensuring the accuracy and reliability of the repair operation, and thus improving the quality of the repair results. Based on the position of the repair area relative to the background image, several areas are stitched together to obtain the first fingerprint image. This method helps to fully utilize the information in multiple fingerprint images to be repaired, making the repair effect more accurate in local areas, reducing the possibility of over-repairing or unnecessary modifications to the entire image, and improving the accuracy, quality, and visualization of the repair results. This step can also be applied to multiple fingerprint images to be repaired simultaneously. By stitching together the areas to be stitched from multiple images, the repair process can be performed on multiple fingerprint images simultaneously, improving the efficiency and practicality of fingerprint image background repair.

[0030] In one specific implementation, determining the repaired fingerprint image based on the first fingerprint image includes:

[0031] The second fingerprint image is obtained by subtracting the standard gray value from the gray value corresponding to the pixel of the first fingerprint image.

[0032] Set the second fingerprint image as the repaired fingerprint image.

[0033] By subtracting the standard grayscale value from the grayscale value of the pixels in the repaired fingerprint image using the above technical solution, background noise or interference in the fingerprint image can be effectively reduced. For example, there may be interference signals from different sources in the fingerprint image, such as changes in illumination and sensor noise. These interference signals can negatively affect the quality and reliability of the fingerprint image. By subtracting the background, these background noises or interferences can be weakened or eliminated, improving the visibility of the texture and details of the fingerprint image. Since the influence of the background is removed, the texture and details in the fingerprint image are enhanced, making the features in the fingerprint more clearly visible, which helps to improve the accuracy and reliability of fingerprint recognition. The background-reduced fingerprint image provides clearer and more recognizable fingerprint features, enabling the fingerprint recognition system to better match and identify them. In the background-reducing operation, the standard grayscale value can be adaptively adjusted according to the grayscale situation of the standard area to achieve the best background reduction effect. This adaptive processing makes the generation of background-reduced fingerprint images more flexible and adaptable, and can cope with fingerprint images of different types and qualities, thereby improving the effect of subsequent fingerprint feature extraction and fingerprint recognition.

[0034] Secondly, this application provides a fingerprint acquisition system, which adopts the following technical solution: the system includes:

[0035] The background image acquisition module is used to acquire the background image of the fingerprint sensor under the default gain.

[0036] The region division module is used to divide the background image into several regions to be repaired according to a preset grayscale range. The grayscale range includes several grayscale ranges. The module records the positions of several regions to be repaired relative to the background image and determines the region to be repaired containing the most pixels as the standard region.

[0037] The gain determination module is used to determine the average gray value of the standard area as the standard gray value, and to determine the difference between the average gray value of several areas to be repaired and the standard gray value as several gain compensation values.

[0038] The fingerprint image acquisition module is used to adjust the gain of the fingerprint sensor according to several gain compensation values, and acquire the fingerprint image to be repaired after the gain of the fingerprint sensor is adjusted.

[0039] The fingerprint image restoration module is used to extract regions from several fingerprint images to be restored based on the position of the region to be restored relative to the background image, and then integrate the extracted regions to obtain the restored fingerprint image.

[0040] Thirdly, this application provides a computer device that adopts the following technical solution: it includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as any of the fingerprint image background restoration methods described above.

[0041] Fourthly, this application provides a computer-readable storage medium that stores a computer program capable of being loaded by a processor and executing any of the above-mentioned fingerprint image background restoration methods.

[0042] In summary, this application has at least the following beneficial technical effects:

[0043] This application's solution divides the background image of the fingerprint sensor under its default gain into several regions to be repaired. Gain compensation is applied to these regions to obtain several fingerprint images to be repaired. Then, based on the position of each region relative to the background image, region extraction is performed on each of these fingerprint images. The extracted regions are then integrated to obtain the repaired fingerprint image. This approach adaptively adjusts the gain based on the grayscale characteristics of different regions, rather than applying a single gain compensation to the entire image. This precisely addresses problematic local areas, reduces the possibility of losing local details, and improves the accuracy of fingerprint image background repair, thereby enhancing the performance of subsequent fingerprint feature extraction and fingerprint recognition. Attached Figure Description

[0044] Figure 1This is a flowchart of the fingerprint image background restoration method in the embodiments of this application.

[0045] Figure 2 This is a schematic diagram used in the embodiments of this application to illustrate the division of the area to be repaired.

[0046] Figure 3 This is a structural block diagram of the fingerprint acquisition system in an embodiment of this application.

[0047] Figure 4 This is a schematic diagram used to illustrate a computer device in the embodiments of this application.

[0048] Reference numerals: 301, Background image acquisition module; 302, Region division module; 303, Gain determination module; 304, Fingerprint image acquisition module; 305, Fingerprint image restoration module. Detailed Implementation

[0049] The following is in conjunction with the appendix Figure 1-4 This application will be described in further detail.

[0050] This application discloses a fingerprint image background restoration method. This method is used to restore the background of fingerprint images acquired by a fingerprint sensor. The reason for needing to restore the fingerprint image background is that the background of the fingerprint image may have problems such as uneven illumination, shadows, or reflections, which reduce the quality and clarity of the fingerprint image. Existing image equalization techniques process the entire fingerprint image and cannot accurately handle local features within the fingerprint image, leading to the loss or blurring of local details, thus negatively impacting subsequent fingerprint feature extraction and fingerprint recognition. This method is applied to a fingerprint acquisition system, which should at least include a fingerprint sensor for acquiring fingerprint images. The fingerprint sensor has a gain register that can adjust the amplification of the sensor input signal to adjust the grayscale value of the fingerprint image acquired by the fingerprint sensor. The fingerprint acquisition system should also include a restoration unit that can be connected to the fingerprint sensor to perform a series of restoration operations on the fingerprint image. The fingerprint acquisition system should also include a database accessible to the restoration unit for storing the grayscale ranges corresponding to pixels in the background image. The execution entity of the fingerprint image background restoration method disclosed in this application is the aforementioned restoration unit.

[0051] like Figure 1 As shown, the method includes the following steps:

[0052] S10, acquire the background image of the fingerprint sensor at the default gain.

[0053] Specifically, the background image of the fingerprint sensor at the default gain is acquired during the fingerprint sensor initialization phase, at which time no real fingerprint image is captured, so the background image does not contain the fingerprint.

[0054] S20: Divide the background image into several regions to be repaired according to the preset grayscale range, record the position of several regions to be repaired relative to the background image, and determine the region to be repaired containing the most pixels as the standard region.

[0055] Specifically, each pixel in the background image has a corresponding grayscale value. The grayscale range is preset by the fingerprint collector and stored in the database. Based on the grayscale range, the area where the pixels in the background image are located can be divided into several areas to be repaired. The position of each area to be repaired relative to the background image is recorded. The position can be represented by pixel coordinates or a two-dimensional array. After the areas to be repaired are divided, the area containing the most pixels is selected as the standard area.

[0056] It should be noted that recording the positions of several areas to be repaired relative to the background image can be achieved in several ways. For example, a coordinate system can be established to record the coordinates of each pixel in the background image, or all pixels of the background image can be stored in a two-dimensional array. If a two-dimensional array is used, the size of the array is consistent with the size of the background image, and each pixel of the background image has a value at the corresponding position in the two-dimensional array. In addition, the values ​​of the standard areas at their corresponding positions in the array can all be set to 0 for differentiation. This two-dimensional array can be used as a mapping table for the background image and stored in Flash to prevent loss.

[0057] S30, the average gray value of the standard area is determined as the standard gray value, and the difference between the average gray value and the standard gray value of several areas to be repaired is determined as several gain compensation values.

[0058] Specifically, the average gray value of all pixels in each region to be repaired is calculated, and the average gray value of the standard region is determined as the standard gray value. The purpose of this is to reduce the possibility of pixels in other extreme gray ranges affecting the average value. Then, the average gray value of several regions to be repaired is compared with the standard gray value to obtain the difference. The difference can be used as a gain compensation value, and each gain compensation value has a corresponding region to be repaired.

[0059] S40, adjust the gain of the fingerprint sensor according to several gain compensation values ​​one by one, and acquire the fingerprint image to be repaired after the gain of the fingerprint sensor is adjusted one by one.

[0060] Specifically, this step occurs during actual fingerprint acquisition. The gain register of the fingerprint sensor is adjusted successively according to several gain compensation values, so that the fingerprint sensor acquires the fingerprint image to be repaired successively under different gain compensation values. Since the gain register adjustment of the fingerprint sensor is for the entire image, theoretically, the number of adjustments required is one less than the number of areas to be repaired (the gain register of the standard area does not need to be adjusted, and the fingerprint image is acquired directly under the default gain). Finally, the number of fingerprint images to be repaired is the same as the number of areas to be repaired.

[0061] S50, based on the position of the area to be repaired relative to the background image, extract regions from several fingerprint images to be repaired, and integrate the extracted regions to obtain the repaired fingerprint image.

[0062] Specifically, based on the position of the area to be repaired relative to the background image, a region with the same position can be located in the fingerprint image to be repaired. Then, the region located in the fingerprint image to be repaired is extracted so that the extracted region is the same size as the area to be repaired. The extracted region is then further processed to obtain the repaired fingerprint image.

[0063] This scheme divides the background image into multiple regions to be repaired using a preset grayscale range. This region division method takes into account the grayscale characteristics of different regions to be repaired and accurately processes local region features in the background image, making the repair process more targeted. By recording the positions of several regions to be repaired relative to the background image, subsequent region extraction and integration operations can be easily performed on the fingerprint image to be repaired. By comparing the difference between the average grayscale value of the regions to be repaired and the standard region, several gain compensation values ​​are determined for obtaining the fingerprint image for repair. This compensation mechanism adaptively adjusts the gain according to the grayscale characteristics of different regions, rather than performing a single gain compensation on the entire image. Even for images with uneven lighting or complex backgrounds, it can accurately process problematic local areas, reducing the possibility of losing local details and improving the accuracy of fingerprint image background restoration. Based on the position of the area to be restored relative to the background image, it extracts regions from several fingerprint images to be restored, which can efficiently and accurately extract the regions in the fingerprint images to be restored, improving the quality and accuracy of fingerprint image background restoration. Integrating the extracted regions to obtain the restored fingerprint image can not only preserve the local details of the fingerprint image, but also make the restored fingerprint image visually consistent and continuous, thereby improving the effect of subsequent fingerprint feature extraction and fingerprint recognition.

[0064] In one embodiment, to facilitate subsequent targeted repair of local features of the background image, the background image is divided into several regions to be repaired according to a preset grayscale range. The step of dividing the grayscale range into several grayscale increments can be specifically performed as follows:

[0065] The fingerprint collector pre-sets grayscale ranges and enters them into the database. Each grayscale range contains several grayscale values. The repair unit first traverses all pixels in the background image, obtains the grayscale value corresponding to each pixel, and compares the grayscale value of each pixel with several grayscale ranges stored in the database one by one. The area corresponding to pixels whose grayscale values ​​belong to the same grayscale range is divided into the area to be repaired. This reduces the possibility of incorrectly including pixels in the repair range, improves the accuracy and reliability of background image area division, and thus improves the effect of subsequent fingerprint image background repair.

[0066] It should be noted that because the repair unit divides the area to be repaired based on the grayscale values ​​of pixels, the resulting area may be irregular or even discontinuous in shape. For example... Figure 2 As shown, the image acquired by the sensor is an 8-bit bitmap, which has 256 grayscale values. The fingerprint collector sets the grayscale interval length to 8 grayscale values. In practice, the grayscale values ​​of the background image acquired by the sensor are generally evenly and concentrated, and some extreme grayscale values ​​will not exist. Based on the grayscale interval of 8 grayscale values, the image can be divided into 3 regions to be repaired. The region to be repaired at the bottom of the image contains the most pixels and is determined as the standard region. Region 1 to be repaired is located in the upper left and upper right of the image, and region 2 to be repaired is located in the middle of the two regions 1 to be repaired.

[0067] In one embodiment, in order to accurately locate the area to be repaired in the fingerprint image to be repaired, the step of extracting regions from several fingerprint images to be repaired based on the position of the area to be repaired relative to the background image can be specifically performed as follows:

[0068] The repair unit determines the target gain compensation value corresponding to the fingerprint image to be repaired. The repair unit then determines the region to be repaired corresponding to the target gain compensation value, thus establishing a correspondence between the fingerprint image to be repaired and the region to be repaired. Based on the position of the region to be repaired relative to the background image, the repair unit determines the region to be stitched in the fingerprint image to be repaired. This process involves the shape and boundaries of the region to be repaired. For example, if the position of the region to be repaired relative to the background image is recorded in a two-dimensional array, then the position of each pixel in the region to be repaired will be recorded in the two-dimensional array. The region to be repaired can be determined based on the position of the pixels in the region to be repaired. The system identifies pixels at the same location in the fingerprint image to determine the stitching region in the fingerprint image to be repaired. It's important to note that since there's a one-to-one correspondence between the fingerprint image to be repaired and the stitching region, there will only be one stitching region for each fingerprint image to be repaired. After determining the stitching region, the repair unit performs region extraction. Various methods can be used for region extraction, such as edge detection algorithms or image segmentation algorithms, to more accurately locate the region used for fingerprint image background repair, improving the accuracy of fingerprint image background repair and thus enhancing the subsequent fingerprint image background repair effect.

[0069] In one embodiment, after the repair unit completes the extraction of regions from several fingerprint images to be repaired, the step of integrating the extracted regions to obtain the repaired fingerprint image can be specifically performed as follows:

[0070] After performing region extraction steps on several fingerprint images to be repaired, the repair unit first determines the repair region corresponding to the region to be stitched in the fingerprint image to be repaired. Based on the position of the repair region relative to the background image, the repair unit determines the stitching position of several regions to be stitched. The repair unit stitches these regions together to obtain a first fingerprint image, and then determines the repaired fingerprint image based on the first fingerprint image. For example, if the position of the repair region relative to the background image is recorded in the form of a two-dimensional array, the position of the pixel in the repair region can be used to determine the region to be stitched where the pixel in the fingerprint image at the same position is located. Then, the pixels in the two-dimensional array of the repair region are replaced with the corresponding pixels of the region to be stitched, completing the stitching of the regions to be stitched to obtain the first fingerprint image. This makes the repair effect more accurate in local areas, reducing the possibility of over-repairing or unnecessary modification of the entire image, and improving the accuracy of the repair result. Because the stitching of the regions to be stitched from multiple images to be repaired allows the repair process to be performed simultaneously on multiple fingerprint images to be repaired, improving the efficiency and practicality of fingerprint image background repair.

[0071] In one embodiment, to effectively reduce background noise or interference in a fingerprint image, the step of determining the repaired fingerprint image based on the first fingerprint image can be specifically performed as follows:

[0072] The repair unit iterates through each pixel in the first fingerprint image and subtracts the standard gray value from the gray value of each pixel to obtain the second fingerprint image. The repair unit then sets the second fingerprint image as the repaired fingerprint image. For example, if the first fingerprint image is recorded in the form of a two-dimensional array, the gray value of each pixel stored in the two-dimensional array can be subtracted from the standard gray value to obtain a two-dimensional array after subtracting the background gray value. Then, the two-dimensional array after subtracting the background gray value is converted into the repaired fingerprint image according to the format requirements of the image object. This enhances the texture and details in the fingerprint image after subtracting the background, which helps to improve the accuracy and reliability of fingerprint recognition, thereby improving the effect of subsequent fingerprint feature extraction and fingerprint recognition.

[0073] Figure 1 This is a flowchart illustrating a fingerprint image background restoration method in one embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows; unless explicitly stated otherwise, there is no strict order requirement for the execution of these steps, and they can be executed in other orders; and Figure 1 At least some of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0074] Based on the above method, this application also discloses a fingerprint acquisition system.

[0075] Reference Figure 3 The system includes the following modules:

[0076] Background image acquisition module 301 is used to acquire the background image of the fingerprint sensor under default gain;

[0077] The region division module 302 is used to divide the background image into several regions to be repaired according to a preset grayscale range, record the position of several regions to be repaired relative to the background image, and determine the region to be repaired containing the most pixels as the standard region.

[0078] The gain determination module 303 is used to determine the average gray value of the standard area as the standard gray value, and to determine the difference between the average gray value of several areas to be repaired and the standard gray value as several gain compensation values.

[0079] The fingerprint image acquisition module 304 is used to adjust the gain of the fingerprint sensor according to several gain compensation values ​​one by one, and acquire the fingerprint image to be repaired after the gain of the fingerprint sensor is adjusted one by one.

[0080] The fingerprint image repair module 305 is used to extract regions from several fingerprint images to be repaired based on the position of the region to be repaired relative to the background image, and then integrate the extracted regions to obtain the repaired fingerprint image.

[0081] In one embodiment, the region segmentation module 302 is specifically used to traverse all pixels of the background image, obtain the grayscale value corresponding to the pixel of the background image; compare the grayscale value of the pixel of the background image with several grayscale ranges one by one; and divide the region corresponding to the pixel whose grayscale value belongs to the same grayscale range into the region to be repaired.

[0082] In one embodiment, the fingerprint image repair module 305 is specifically used to determine a target gain compensation value corresponding to the fingerprint image to be repaired; determine the region to be repaired corresponding to the target gain compensation value; determine the region to be stitched in the fingerprint image to be repaired based on the position of the region to be repaired relative to the background image; and perform region extraction on the region to be stitched in the fingerprint image to be repaired.

[0083] In one embodiment, the fingerprint image repair module 305 is specifically used to determine the repair area corresponding to the area to be stitched; determine the stitching position of several areas to be stitched according to the position of the area to be repaired relative to the background image; stitch the several areas to be stitched according to the stitching position to obtain a first fingerprint image; and determine the repaired fingerprint image according to the first fingerprint image.

[0084] In one embodiment, the fingerprint image repair module 305 is specifically used to subtract the standard gray value from the gray value corresponding to the pixel of the first fingerprint image to obtain the second fingerprint image; and to set the second fingerprint image as the repaired fingerprint image.

[0085] The fingerprint acquisition system provided in this application embodiment can be applied to the fingerprint image background restoration method provided in the above embodiment. For relevant details, please refer to the above method embodiment. The implementation principle and technical effect are similar, and will not be repeated here.

[0086] It should be noted that the fingerprint acquisition system provided in this embodiment is only illustrated by the above-described division of functional modules / units when performing fingerprint image background restoration. In practical applications, the above functions can be assigned to different functional modules / units as needed, that is, the internal structure of the fingerprint acquisition system can be divided into different functional modules / units to complete all or part of the functions described above. Furthermore, the implementation method of the fingerprint image background restoration method provided in the above method embodiment and the implementation method of the fingerprint acquisition system provided in this embodiment belong to the same concept. The specific implementation process of the fingerprint acquisition system provided in this embodiment is detailed in the above method embodiment and will not be repeated here.

[0087] This application also discloses a computer device.

[0088] Specifically, such as Figure 4 As shown, the computer device can be a desktop computer, laptop computer, handheld computer, or cloud server, etc. The computer device may include, but is not limited to, a processor and memory. The processor and memory can be connected via a bus or other means. The processor can be a Central Processing Unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, graphics processing units (GPUs), embedded neural network processing units (NPUs) or other dedicated deep learning coprocessors, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips.

[0089] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods in the above embodiments of this application. The processor executes various functional applications and data processing by running the non-transitory software programs, instructions, and modules stored in the memory, thereby implementing the methods in the above embodiments. The memory may include a program storage area and a data storage area, wherein the program storage area may store the control unit and the application program required for at least one function; the data storage area may store data created by the processor, etc. Furthermore, the memory may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0090] This application also discloses a computer-readable storage medium.

[0091] Specifically, the computer-readable storage medium is used to store a computer program, which, when executed by a processor, implements the methods described in the above-described method embodiments. Those skilled in the art will understand that implementing all or part of the processes in the methods described in the above-described embodiments of this application can be accomplished by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0092] This specific embodiment is merely an explanation of the present invention and is not intended to limit the invention. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they are within the scope of the claims of the present invention.

Claims

1. A method for fingerprint image background restoration, characterized in that, The method is applied to a fingerprint acquisition system, the system including a fingerprint sensor for acquiring fingerprint images, and the method includes: Obtain the background image of the fingerprint sensor at the default gain; The background image is divided into several regions to be repaired according to a preset grayscale range. The grayscale range includes several grayscale ranges. The positions of several regions to be repaired relative to the background image are recorded, and the region to be repaired containing the most pixels is determined as the standard region. The average gray value of the standard area is determined as the standard gray value, and the difference between the average gray value of several areas to be repaired and the standard gray value is determined as several gain compensation values. The gain of the fingerprint sensor is adjusted sequentially according to several gain compensation values, and the fingerprint image to be repaired is acquired sequentially after the gain of the fingerprint sensor is adjusted. Based on the position of the area to be repaired relative to the background image, regions are extracted from several fingerprint images to be repaired, and the extracted regions are integrated to obtain the repaired fingerprint image.

2. The method according to claim 1, characterized in that, The background image is divided into several regions to be repaired according to a preset grayscale range, wherein the grayscale range includes several grayscale ranges, including: Traverse all pixels of the background image and obtain the grayscale value corresponding to each pixel of the background image; The grayscale values ​​of the pixels in the background image are compared one by one with several grayscale ranges; The regions corresponding to pixels whose gray values ​​belong to the same gray range are divided into the regions to be repaired.

3. The method according to claim 1, characterized in that, The step of extracting regions from several fingerprint images to be repaired based on the position of the region to be repaired relative to the background image includes: Determine the target gain compensation value corresponding to the fingerprint image to be repaired; Determine the region to be repaired corresponding to the target gain compensation value; Based on the position of the area to be repaired relative to the background image, the area to be stitched is determined in the fingerprint image to be repaired; Region extraction is performed on the area to be stitched within the fingerprint image to be repaired.

4. The method according to claim 3, characterized in that, The process of integrating the extracted regions to obtain the repaired fingerprint image includes: Determine the area to be repaired corresponding to the area to be spliced; Based on the position of the area to be repaired relative to the background image, determine the stitching positions of several areas to be stitched together; The first fingerprint image is obtained by splicing several regions to be spliced ​​according to the splicing position; The repaired fingerprint image was determined based on the first fingerprint image.

5. The method according to claim 4, characterized in that, The step of determining the repaired fingerprint image based on the first fingerprint image includes: The second fingerprint image is obtained by subtracting the standard gray value from the gray value corresponding to the pixel of the first fingerprint image. Set the second fingerprint image as the repaired fingerprint image.

6. A fingerprint acquisition system, characterized in that, The system includes a fingerprint sensor for acquiring fingerprint images, and the system includes: The background image acquisition module (301) is used to acquire the background image of the fingerprint sensor under the default gain. The region division module (302) is used to divide the background image into several regions to be repaired according to a preset grayscale range, wherein the grayscale range includes several grayscale ranges, record the position of several regions to be repaired relative to the background image, and determine the region to be repaired containing the most pixels as the standard region. The gain determination module (303) is used to determine the average gray value of the standard area as the standard gray value, and to determine the difference between the average gray value of several areas to be repaired and the standard gray value as several gain compensation values. The fingerprint image acquisition module (304) is used to adjust the gain of the fingerprint sensor according to several gain compensation values, and acquire the fingerprint image to be repaired after the gain adjustment of the fingerprint sensor. The fingerprint image repair module (305) is used to extract regions from several fingerprint images to be repaired according to the position of the region to be repaired relative to the background image, and integrate the extracted regions to obtain the repaired fingerprint image.

7. A computer device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and executed according to any one of claims 1 to 5.

Images