Fingerprint splicing method and device and electronic equipment

Abstract

The invention provides a fingerprint splicing method, a fingerprint splicing device and electronic equipment. The fingerprint splicing method comprises the following steps: acquiring continuous multi-frame to-be-spliced fingerprint images generated in a user finger rolling process through rolling fingerprint acquisition equipment; calculating a relative gray value of each pixel in each frame of fingerprint image to be spliced; determining a fingerprint valley line area and a fingerprint ridge line area in the to-be-spliced fingerprint image according to the relative gray value; furthermore, according to the distribution characteristics of the relative gray values, determining boundary parameters of the fingerprint area of the fingerprint image to be spliced in the column direction; according to the contrast difference between the fingerprint valley line region and the fingerprint ridge line region, determining a splicing path with the maximum gray scale accumulated value in the fingerprint region as a target path; and based on the target path and the boundary parameter, splicing the to-be-spliced fingerprint image to obtain a spliced fingerprint image. According to the method, the fingerprint splicing error can be reduced, and the recognition reliability is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a fingerprint splicing method, device and electronic equipment. Background Art

[0002] Fingerprint recognition technology, with its advantages such as ease of acquisition, feature stability, high recognition rate, and low-cost equipment, has become one of the most widely used and practical technologies in the biometrics field. However, the key performance indicators of fingerprint recognition systems—the False Rejection Rate (FRR) and False Acceptance Rate (FAR)—still face challenges. In particular, when fingerprint image quality is insufficient in complex scenarios, the system is prone to misjudgment, resulting in low fingerprint recognition accuracy. Summary of the Invention

[0003] The purpose of the present invention is to provide a fingerprint stitching method, device and electronic device to alleviate the technical problem that the fingerprint image obtained by the existing fingerprint recognition system is of poor quality, resulting in low fingerprint recognition accuracy, so as to improve the quality of the fingerprint image and further improve the fingerprint recognition accuracy.

[0004] In a first aspect, an embodiment of the present invention provides a fingerprint stitching method, comprising: step A1: obtaining multiple consecutive frames of fingerprint images to be stitched generated during the rolling process of a user's finger through a rolling fingerprint acquisition device; step A2: calculating the relative grayscale value of each pixel in the above-mentioned fingerprint image to be stitched in each frame; step A3: determining the fingerprint valley area and the fingerprint ridge area in the above-mentioned fingerprint image to be stitched based on the above-mentioned relative grayscale values; and, based on the distribution characteristics of the above-mentioned relative grayscale values, determining the boundary parameters of the fingerprint area in the column direction of the above-mentioned fingerprint image to be stitched; step A4: determining the stitching path with the largest grayscale cumulative value in the above-mentioned fingerprint area as the target path based on the contrast difference between the above-mentioned fingerprint valley area and the above-mentioned fingerprint ridge area; step A5: stitching the above-mentioned fingerprint images to be stitched based on the above-mentioned target path and the above-mentioned boundary parameters to obtain a stitched fingerprint image.

[0005] In a preferred embodiment of the present invention, after the step of splicing the fingerprint images to be spliced ​​based on the target path and the boundary parameters to obtain the spliced ​​fingerprint image, the method includes: step B1: calculating the pixel negative value ratio of the spliced ​​fingerprint image; step B2: when the pixel negative value ratio is less than a preset threshold, performing image enhancement on the spliced ​​fingerprint image based on preset parameters to obtain an enhanced fingerprint image; when the pixel negative value ratio is greater than or equal to the preset threshold, repeating steps A1 to A5 and steps B1 to B2 until the preset number of times is reached.

[0006] In a preferred embodiment of the present invention, the step of determining the boundary parameters of the fingerprint area of ​​the fingerprint image in the column direction based on the distribution characteristics of the relative grayscale values ​​includes: determining the starting position and the ending position of the fingerprint area of ​​the fingerprint image to be spliced ​​in the column direction based on the distribution characteristics of the relative grayscale values; and the step of splicing the fingerprint images to be spliced ​​based on the target path and the boundary parameters to obtain a spliced ​​fingerprint image includes: splicing the fingerprint images to be spliced ​​based on the target path, the starting position and the ending position to obtain a spliced ​​fingerprint image.

[0007] In a preferred embodiment of the present invention, the step of calculating the relative grayscale value of each pixel in the fingerprint image to be spliced ​​in each frame includes: subtracting the grayscale value of each pixel in the fingerprint image to be spliced ​​in each frame from the grayscale mean of a preset area around each pixel to obtain a grayscale difference; and determining the grayscale difference as the relative grayscale value.

[0008] In a preferred embodiment of the present invention, the preset area is 13 rows by 13 columns around each pixel.

[0009] In a preferred embodiment of the present invention, after the step of determining the boundary parameters of the fingerprint area of ​​the fingerprint image to be spliced ​​in the column direction according to the distribution characteristics of the relative grayscale values, the method further includes: determining the center point of the fingerprint area according to the boundary parameters; determining the target path with the maximum grayscale cumulative value in the fingerprint area according to the fingerprint valley area and the fingerprint ridge area, including: selecting a translation window with the center point as the center and a width as a preset parameter according to the fingerprint valley area and the fingerprint ridge area; translating the translation window in a preset direction to generate multiple translation sub-images; multiplying the pixels of the translation sub-images to calculate the target path with the maximum grayscale cumulative value in the fingerprint area.

[0010] In a preferred embodiment of the present invention, the step of multiplying the pixels of the above-mentioned translation sub-image to calculate the target path with the maximum grayscale cumulative value in the above-mentioned fingerprint area includes: multiplying the pixels of the above-mentioned translation sub-image to calculate the maximum position of the grayscale cumulative value of the column and the offset of the above-mentioned translation sub-image in the above-mentioned preset direction; according to the above-mentioned maximum position of the grayscale cumulative value and the above-mentioned offset, calculating the target path with the maximum grayscale cumulative value in the above-mentioned fingerprint area.

[0011] In a preferred embodiment of the present invention, after the step of obtaining multiple frames of fingerprint images to be stitched generated during the rolling process of the user's finger by a rolling fingerprint collection device, the method further includes: determining whether to obtain the multiple frames of fingerprint images to be stitched of the user; if not, generating a prompt message to prompt the user to re-acquire the multiple frames of fingerprint images to be stitched of the user.

[0012] In a second aspect, an embodiment of the present invention further provides a fingerprint stitching device, comprising: a data acquisition module, configured to acquire, through a rolling fingerprint acquisition device, a plurality of continuous frames of fingerprint images to be stitched generated during the rolling process of a user's finger; a calculation module, configured to calculate the relative grayscale value of each pixel in the fingerprint image to be stitched of each frame; based on the relative grayscale value, determining the fingerprint valley area and the fingerprint ridge area in the fingerprint image to be stitched; and, based on the distribution characteristics of the relative grayscale value, determining the boundary parameters of the fingerprint area in the column direction of the fingerprint image to be stitched; a path selection module, configured to determine, based on the contrast difference between the fingerprint valley area and the fingerprint ridge area, a stitching path with the largest grayscale cumulative value in the fingerprint area as a target path; and a stitching module, configured to stitch the fingerprint images to be stitched based on the target path and the boundary parameters to obtain a stitched fingerprint image.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the fingerprint splicing method.

[0014] The embodiments of the present invention have the following beneficial technical effects:

[0015] Embodiments of the present invention provide a fingerprint stitching method, apparatus, and electronic device, comprising: step A1: acquiring multiple consecutive frames of fingerprint images to be stitched, generated during a user's finger rolling process, using a rolling fingerprint acquisition device; step A2: calculating the relative grayscale value of each pixel in each frame of the fingerprint image to be stitched; step A3: determining the fingerprint valley and fingerprint ridge regions in the fingerprint image to be stitched based on the relative grayscale values; and determining the boundary parameters of the fingerprint region in the column direction of the fingerprint image to be stitched based on the distribution characteristics of the relative grayscale values; step A4: determining the stitching path with the maximum grayscale cumulative value in the fingerprint region as a target path based on the contrast difference between the fingerprint valley and fingerprint ridge regions; and step A5: stitching the fingerprint images to be stitched based on the target path and the boundary parameters to obtain a stitched fingerprint image. This method combines the acquisition of multiple consecutive fingerprint images with grayscale analysis to accurately identify fingerprint ridge patterns and boundary parameters, and stitches them based on the optimal grayscale path, effectively improving the integrity and feature continuity of the fingerprint image, reducing stitching errors, and enhancing recognition reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 A schematic diagram of a fingerprint splicing method according to an embodiment of the present invention;

[0018] Figure 2 A schematic diagram of a fingerprint image to be spliced ​​provided by an embodiment of the present invention;

[0019] Figure 3 A schematic diagram of a stitching process for a fingerprint image to be stitched provided in an embodiment of the present invention;

[0020] Figure 4 A schematic diagram of a spliced ​​fingerprint image provided by an embodiment of the present invention;

[0021] Figure 5 A schematic flow chart of another fingerprint splicing method provided by an embodiment of the present invention;

[0022] Figure 6 A schematic structural diagram of a fingerprint splicing device provided by an embodiment of the present invention;

[0023] Figure 7A schematic structural diagram of an electronic device provided by an embodiment of the present invention.

[0024] Icons: 61 - data acquisition module; 62 - calculation module; 63 - path selection module; 64 - splicing module; 41 - memory; 42 - processor; 43 - bus; 44 - communication interface. DETAILED DESCRIPTION

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0026] Fingerprint recognition technology, with its core advantages such as contactless collection convenience, unique biometric stability, high-precision recognition efficiency, and low equipment cost, has rapidly become the most widely used and technologically superior core solution in the field of identity authentication. However, key system performance indicators—the false rejection rate (FRR) and false acceptance rate (FAR)—still face significant challenges in practical applications. This is particularly true in complex scenarios such as low lighting, worn fingerprints, or insufficient image resolution. Degraded fingerprint image quality can easily lead to system misjudgments, limiting overall recognition accuracy.

[0027] Based on this, embodiments of the present invention provide a fingerprint stitching method, device, and electronic device. This method accurately identifies fingerprint ridges and boundary parameters by capturing multiple frames of continuous fingerprint images and combining them with grayscale analysis. Stitching is then performed based on an optimal grayscale path, effectively improving the integrity and feature continuity of the fingerprint image, reducing stitching errors, and enhancing recognition reliability. To facilitate understanding, a fingerprint stitching method is first introduced.

[0028] Example 1

[0029] In this embodiment, Figure 1 A schematic flow chart of a fingerprint splicing method provided by an embodiment of the present invention.

[0030] Depend on Figure 1 As can be seen, the method includes:

[0031] Step A1: a rolling fingerprint collection device is used to obtain multiple frames of fingerprint images to be stitched that are generated during the rolling process of the user's finger.

[0032] For ease of understanding, Figure 2 A schematic diagram of a fingerprint image to be stitched provided by an embodiment of the present invention.

[0033] In actual operation, the rolling fingerprint collection device obtains multiple frames of continuous fingerprint images to be spliced ​​generated during the rolling process of the user's finger, so as to cover the complete area of ​​the fingerprint (such as the spiral or arch structure of the entire fingerprint) and avoid partial or incomplete images caused by a single press.

[0034] Step A2: Calculate the relative grayscale value of each pixel in the fingerprint image to be spliced ​​in each frame.

[0035] In some examples, the difference between each pixel in each of the fingerprint images to be stitched and the average value of the surrounding 13×13 area is calculated to obtain a relative grayscale value.

[0036] Furthermore, the fingerprint valley area is marked; if the result is negative, it is marked as the fingerprint ridge area. Here, the contrast of the fingerprint concavity and convexity is enhanced by relative grayscale to facilitate subsequent processing.

[0037] Step A3: Determine the fingerprint valley area and fingerprint ridge area in the fingerprint image to be stitched based on the relative grayscale values; and determine the boundary parameters of the fingerprint area in the column direction of the fingerprint image to be stitched based on the distribution characteristics of the relative grayscale values.

[0038] Here, the fingerprint effective area is located through the above step A3, background noise is removed, and a coordinate reference is provided for subsequent stitching.

[0039] Step A4: According to the contrast difference between the fingerprint valley area and the fingerprint ridge area, a splicing path with the maximum grayscale cumulative value in the fingerprint area is determined as the target path.

[0040] In actual operation, since the finger may be slightly displaced during the scrolling process, the ridge and valley positions of adjacent images are aligned by finding the local maximum grayscale cumulative value to reduce the misalignment during stitching.

[0041] Step A5: Based on the target path and the boundary parameters, the fingerprint images to be spliced ​​are spliced ​​to obtain a spliced ​​fingerprint image.

[0042] For ease of understanding, Figure 3 A schematic diagram of a stitching process for a fingerprint image to be stitched provided in an embodiment of the present invention; Figure 4 A schematic diagram of a spliced ​​fingerprint image provided by an embodiment of the present invention.

[0043] In actual operation, first, according to the boundary parameters (i.e. the left and right or upper and lower boundaries of the fingerprint area in the column direction), the effective fingerprint area of ​​the multi-frame fingerprint image is preliminarily located to eliminate the interference of background noise or invalid areas. Then, using the target path as the main reference line for splicing, the feature areas corresponding to the path in the adjacent frame fingerprint images are aligned frame by frame to ensure that the key texture features such as the ridges and valleys of the fingerprint are seamlessly connected at the splicing point, as mentioned above. Figure 3 In this process, the overlapping area of ​​the image blocks is further optimized by combining the boundary parameters, and the displacement deviation or distortion caused by rolling acquisition between frames is eliminated through the fusion algorithm of gray value or texture features. Finally, the multiple frames of fingerprint images collected continuously are spliced ​​layer by layer along the optimal path to generate a complete, continuous and high-quality fingerprint image without obvious splicing marks as shown above. Figure 4 As shown, the accuracy and reliability of feature extraction in subsequent fingerprint recognition are significantly improved.

[0044] An embodiment of the present invention provides a fingerprint stitching method, comprising: step A1: acquiring multiple consecutive frames of fingerprint images to be stitched, generated during the rolling process of a user's finger, using a rolling fingerprint acquisition device; step A2: calculating the relative grayscale value of each pixel in the fingerprint images to be stitched, for each frame; step A3: determining the fingerprint valley and fingerprint ridge regions in the fingerprint images to be stitched based on the relative grayscale values; and determining the boundary parameters of the fingerprint regions in the fingerprint images to be stitched in the column direction based on the distribution characteristics of the relative grayscale values; step A4: determining the stitching path with the maximum grayscale cumulative value in the fingerprint regions as a target path based on the contrast difference between the fingerprint valley and fingerprint ridge regions; and step A5: stitching the fingerprint images to be stitched based on the target path and the boundary parameters to obtain a stitched fingerprint image. This method combines the acquisition of multiple consecutive fingerprint images with grayscale analysis to accurately identify fingerprint ridge patterns and boundary parameters, and stitches them based on the optimal grayscale path, effectively improving the integrity and feature continuity of the fingerprint images, reducing stitching errors, and enhancing recognition reliability.

[0045] Example 2

[0046] Based on the above embodiments, Figure 5 A schematic flow chart of another fingerprint splicing method provided by an embodiment of the present invention.

[0047] Depend on Figure 5 As can be seen, the method includes:

[0048] Step A1: a rolling fingerprint collection device is used to obtain multiple frames of fingerprint images to be stitched that are generated during the rolling process of the user's finger.

[0049] Here, after the step of obtaining multiple frames of continuous fingerprint images to be stitched generated during the rolling process of the user's finger through the rolling fingerprint collection device, the above method further includes: determining whether the multiple frames of continuous fingerprint images to be stitched of the user are obtained; if not, generating a prompt message to prompt the user to re-acquire the multiple frames of continuous fingerprint images to be stitched of the user.

[0050] Step A2: Calculate the relative grayscale value of each pixel in the fingerprint image to be spliced ​​in each frame.

[0051] Specifically, the step of calculating the relative grayscale value of each pixel in the fingerprint image to be spliced ​​in each frame includes: subtracting the grayscale value of each pixel in the fingerprint image to be spliced ​​in each frame from the grayscale mean of a preset area around each pixel to obtain a grayscale difference; and determining the grayscale difference as the relative grayscale value.

[0052] The preset area is 13 rows by 13 columns around each pixel.

[0053] Step A3: Determine the fingerprint valley area and fingerprint ridge area in the fingerprint image to be stitched based on the relative grayscale values; and determine the boundary parameters of the fingerprint area in the column direction of the fingerprint image to be stitched based on the distribution characteristics of the relative grayscale values.

[0054] Step A4: According to the contrast difference between the fingerprint valley area and the fingerprint ridge area, a splicing path with the maximum grayscale cumulative value in the fingerprint area is determined as the target path.

[0055] Step A5: Based on the target path and the boundary parameters, the fingerprint images to be spliced ​​are spliced ​​to obtain a spliced ​​fingerprint image.

[0056] Step B1: Calculate the percentage of negative pixel values ​​in the stitched fingerprint image.

[0057] Step B2: When the proportion of negative pixel values ​​is less than a preset threshold, the stitched fingerprint image is enhanced based on preset parameters to obtain an enhanced fingerprint image; when the proportion of negative pixel values ​​is greater than or equal to the preset threshold, repeat steps A1 to A5 and steps B1 to B2 until the preset number of times is reached.

[0058] In practical applications, the enhanced fingerprint image can meet the preset requirements.

[0059] In one embodiment, the step of determining the boundary parameters of the fingerprint area of ​​the fingerprint image in the column direction based on the distribution characteristics of the relative grayscale values ​​includes: determining the starting position and the ending position of the fingerprint area of ​​the fingerprint image to be spliced ​​in the column direction based on the distribution characteristics of the relative grayscale values; and the step of splicing the fingerprint images to be spliced ​​based on the target path and the boundary parameters to obtain a spliced ​​fingerprint image includes: splicing the fingerprint images to be spliced ​​based on the target path, the starting position and the ending position to obtain a spliced ​​fingerprint image.

[0060] Furthermore, after the step of determining the boundary parameters of the fingerprint area of ​​the fingerprint image to be spliced ​​in the column direction based on the distribution characteristics of the relative grayscale values, the method further includes: determining the center point of the fingerprint area based on the boundary parameters; determining the target path with the largest grayscale cumulative value in the fingerprint area based on the fingerprint valley area and the fingerprint ridge area, including: selecting a translation window with the center point as the center and a width as a preset parameter based on the fingerprint valley area and the fingerprint ridge area; translating the translation window in a preset direction to generate multiple translation sub-images; and multiplying the pixels of the translation sub-images to calculate the target path with the largest grayscale cumulative value in the fingerprint area.

[0061] Furthermore, the step of multiplying the pixels of the above-mentioned translation sub-image to calculate the target path with the largest grayscale cumulative value in the above-mentioned fingerprint area includes: multiplying the pixels of the above-mentioned translation sub-image to calculate the maximum position of the grayscale cumulative value of the column and the offset of the above-mentioned translation sub-image in the above-mentioned preset direction; according to the above-mentioned maximum position of the grayscale cumulative value and the above-mentioned offset, calculating the target path with the largest grayscale cumulative value in the above-mentioned fingerprint area.

[0062] In actual operation, a translation sub-image with a width of 20 pixels is taken according to the center point, and then the 5 positive and negative displacement sub-images in the upper, lower, left and right directions are multiplied to calculate the maximum position of the column and the upper, lower, left and right offsets. Based on the maximum position and the area with a maximum left and right offset of 10 pixels, a path with the least negative value and the largest cumulative value is found, which is the target path.

[0063] An embodiment of the present invention provides a fingerprint stitching method, comprising: step A1: acquiring multiple frames of fingerprint images to be stitched generated during the rolling process of a user's finger through a rolling fingerprint acquisition device; step A2: calculating the relative grayscale value of each pixel in the fingerprint image to be stitched in each frame; step A3: determining the fingerprint valley area and the fingerprint ridge area in the fingerprint image to be stitched based on the relative grayscale values; and determining the boundary parameters of the fingerprint area in the column direction of the fingerprint image to be stitched based on the distribution characteristics of the relative grayscale values; step A4: determining the fingerprint valley area and the fingerprint ridge area based on the contrast difference between the fingerprint valley area and the fingerprint ridge area. The stitching path with the maximum cumulative grayscale value in the fingerprint region is used as the target path. Step A5: Based on the target path and the boundary parameters, the fingerprint images to be stitched are stitched to obtain a stitched fingerprint image. Step B1: Calculate the percentage of negative pixel values ​​in the stitched fingerprint image. Step B2: When the percentage of negative pixel values ​​is less than a preset threshold, enhance the stitched fingerprint image based on preset parameters to obtain an enhanced fingerprint image. When the percentage of negative pixel values ​​is greater than or equal to the preset threshold, repeat Steps A1 to A5 and Steps B1 to B2 until a preset number of times has been reached. This method transforms the fingerprint stitching problem into a series of lightweight local computational tasks through local grayscale analysis, simplified boundary parameter location, dynamic optimization of path search, and the inherent advantages of multiple frames of continuous imagery, avoiding complex global processing and the use of high-order algorithms. Furthermore, the continuity of fingerprint ridges and the overlapping characteristics of rolling acquisition are utilized to further reduce redundant computations, ultimately achieving efficient computation while ensuring accuracy.

[0064] Example 3

[0065] Based on the above embodiments, Figure 6 A schematic structural diagram of a fingerprint splicing device provided by an embodiment of the present invention.

[0066] Depend on Figure 6 As can be seen, the device includes:

[0067] The data acquisition module 61 is used to acquire multiple frames of fingerprint images to be spliced ​​generated during the rolling process of the user's finger through a rolling fingerprint acquisition device.

[0068] The calculation module 62 is used to calculate the relative grayscale value of each pixel in the fingerprint image to be stitched in each frame; determine the fingerprint valley area and fingerprint ridge area in the fingerprint image to be stitched based on the relative grayscale value; and determine the boundary parameters of the fingerprint area in the fingerprint image to be stitched in the column direction based on the distribution characteristics of the relative grayscale value.

[0069] The path selection module 63 is configured to determine, based on the contrast difference between the valley area and the ridge area, a splicing path with the largest grayscale cumulative value in the fingerprint area as a target path.

[0070] The stitching module 64 is configured to stitch the fingerprint images to be stitched based on the target path and the boundary parameters to obtain a stitched fingerprint image.

[0071] The data acquisition module 61 , the calculation module 62 , the path selection module 63 and the splicing module 64 are connected in sequence.

[0072] In one embodiment, the stitching module 64 is further used to stitch the fingerprint images to be stitched based on the target path and the boundary parameters to obtain the stitched fingerprint image, and then execute step B1: calculate the pixel negative value ratio of the stitched fingerprint image; step B2: when the pixel negative value ratio is less than a preset threshold, perform image enhancement on the stitched fingerprint image based on preset parameters to obtain an enhanced fingerprint image; when the pixel negative value ratio is greater than or equal to the preset threshold, repeat steps A1 to A5 and steps B1 to B2 until the preset number of times is reached.

[0073] In one embodiment, the calculation module 62 is further configured to determine the starting position and the ending position of the fingerprint region of the fingerprint image to be spliced ​​in the column direction according to the distribution characteristics of the relative grayscale values; and splice the fingerprint image to be spliced ​​based on the target path, the starting position, and the ending position to obtain a spliced ​​fingerprint image.

[0074] In one embodiment, the calculation module 62 is further configured to obtain a grayscale difference by subtracting the grayscale value of each pixel in the fingerprint image to be spliced ​​in each frame from the grayscale mean of a preset area surrounding the pixel; and determining the grayscale difference as the relative grayscale value.

[0075] In one embodiment, the path selection module 63 is further used to determine the center point of the above-mentioned fingerprint area based on the above-mentioned boundary parameters; select a translation window with the above-mentioned center point as the center and a width as a preset parameter based on the above-mentioned fingerprint valley area and the above-mentioned fingerprint ridge area; translate the above-mentioned translation window in a preset direction to generate multiple translation sub-images; multiply the pixels of the above-mentioned translation sub-images to calculate the target path with the largest grayscale cumulative value in the above-mentioned fingerprint area.

[0076] In one embodiment, the path selection module 63 is further used to multiply the pixels of the above-mentioned translation sub-image, calculate the maximum position of the grayscale cumulative value of the column and the offset of the above-mentioned translation sub-image in the above-mentioned preset direction; based on the above-mentioned maximum position of the grayscale cumulative value and the above-mentioned offset, calculate the target path with the maximum grayscale cumulative value in the above-mentioned fingerprint area.

[0077] In one embodiment, the data acquisition module 61 is further configured to determine whether to obtain multiple consecutive frames of fingerprint images to be spliced ​​from the user; if not, generate a prompt message to prompt the user to re-acquire multiple consecutive frames of fingerprint images to be spliced ​​from the user.

[0078] The fingerprint stitching device provided in the embodiment of the present invention has the same technical features as the fingerprint stitching method provided in the above embodiment, and therefore can solve the same technical problems and achieve the same technical effects. Those skilled in the art will clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the above method embodiment and will not be repeated here.

[0079] Example 4

[0080] This embodiment provides an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the steps of the fingerprint splicing method.

[0081] This embodiment provides a computer-readable storage medium storing a computer program, which implements the steps of the fingerprint splicing method when executed by a processor.

[0082] See also Figure 7 The structure diagram of an electronic device shown in FIG. 4 includes a memory 41 and a processor 42. The memory 41 stores a computer program that can be run on the processor 42. When the processor executes the computer program, the steps provided by the above-mentioned fingerprint splicing method are implemented.

[0083] like Figure 7 As shown, the device further includes: a bus 43 and a communication interface 44, and a processor 42, a communication interface 44 and a memory 41 are connected via the bus 43; the processor 42 is used to execute executable modules stored in the memory 41, such as computer programs.

[0084] The memory 41 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage. The system network element communicates with at least one other network element via at least one communication interface 44 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0085] The bus 43 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 7 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0086] Memory 41 is used to store programs, and processor 42 executes the programs after receiving execution instructions. The methods performed by the fingerprint splicing device disclosed in any of the aforementioned embodiments of the present invention can be applied to or implemented by processor 42. Processor 42 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the aforementioned method can be completed by hardware integrated logic circuits in processor 42 or by software instructions. Processor 42 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules within the decoding processor. The software modules can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in memory 41, and processor 42 reads the information in memory 41 and, in conjunction with its hardware, completes the steps of the method described above.

[0087] Furthermore, an embodiment of the present invention also provides a machine-readable storage medium, which stores machine-executable instructions. When the machine-executable instructions are called and executed by the processor 42, the machine-executable instructions prompt the processor 42 to implement the above-mentioned fingerprint splicing method.

[0088] The electronic device and computer-readable storage medium provided by the embodiments of the present invention have the same technical features, and therefore can solve the same technical problems and achieve the same technical effects.

[0089] In addition, in the description of the embodiments of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical connections or electrical connections; they may refer to direct connections or indirect connections through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

Claims

1. A fingerprint splicing method, characterized in that: include: Step A1: acquiring multiple consecutive frames of fingerprint images to be stitched generated during the rolling process of the user's finger through a rolling fingerprint collection device; Step A2: Calculating the relative grayscale value of each pixel in the fingerprint image to be spliced ​​in each frame; Step A3: determining the fingerprint valley area and the fingerprint ridge area in the fingerprint image to be stitched according to the relative grayscale value; and, determining boundary parameters of the fingerprint region of the fingerprint image to be spliced ​​in the column direction according to the distribution characteristics of the relative grayscale values; Step A4: determining, based on the contrast difference between the fingerprint valley area and the fingerprint ridge area, a splicing path with the largest grayscale cumulative value in the fingerprint area as the target path; Step A5: Based on the target path and the boundary parameters, the fingerprint images to be spliced ​​are spliced ​​to obtain a spliced ​​fingerprint image.

2. The fingerprint splicing method according to claim 1, characterized in that: After the step of stitching the fingerprint images to be stitched based on the target path and the boundary parameters to obtain a stitched fingerprint image, the method includes: Step B1: Calculating the percentage of negative pixel values ​​in the stitched fingerprint image; Step B2: When the proportion of negative pixel values ​​is less than a preset threshold, the stitched fingerprint image is enhanced based on preset parameters to obtain an enhanced fingerprint image; when the proportion of negative pixel values ​​is greater than or equal to the preset threshold, repeat steps A1 to A5 and steps B1 to B2 until the preset number of times is reached.

3. The fingerprint splicing method according to claim 1, characterized in that: The step of determining the boundary parameters of the fingerprint area of ​​the fingerprint image in the column direction according to the distribution characteristics of the relative grayscale values ​​comprises: Determining the starting position and the ending position of the fingerprint area of ​​the fingerprint image to be stitched in the column direction according to the distribution characteristics of the relative grayscale values; The step of stitching the fingerprint images to be stitched based on the target path and the boundary parameters to obtain a stitched fingerprint image includes: Based on the target path, the starting position, and the ending position, the fingerprint images to be spliced ​​are spliced ​​to obtain a spliced ​​fingerprint image.

4. The fingerprint splicing method according to claim 1, characterized in that: The step of calculating the relative grayscale value of each pixel in the fingerprint image to be spliced ​​in each frame includes: Subtract the grayscale value of each pixel in the fingerprint image to be spliced ​​in each frame from the grayscale mean value of the preset area around each pixel to obtain a grayscale difference; The grayscale difference is determined as the relative grayscale value.

5. The fingerprint splicing method according to claim 4, characterized in that: The preset area is 13 rows by 13 columns around each pixel.

6. The fingerprint splicing method according to claim 1, characterized in that: After the step of determining the boundary parameters of the fingerprint region of the fingerprint image to be stitched in the column direction according to the distribution characteristics of the relative grayscale values, the method further includes: Determining the center point of the fingerprint area according to the boundary parameters; The step of determining a target path having a maximum grayscale cumulative value in the fingerprint area according to the fingerprint valley area and the fingerprint ridge area comprises: According to the fingerprint valley area and the fingerprint ridge area, a translation window with the center point as the center and a width as a preset parameter is selected; The translation window is translated in a preset direction to generate a plurality of translation sub-images; The pixels of the translated sub-image are multiplied to calculate the target path with the maximum grayscale cumulative value in the fingerprint area.

7. The fingerprint splicing method according to claim 6, characterized in that: The step of multiplying the pixels of the translated sub-image to calculate the target path with the maximum grayscale cumulative value in the fingerprint area includes: Multiplying the pixels of the translated sub-image, calculating the maximum position of the grayscale cumulative value of the column and the offset of the translated sub-image in the preset direction; A target path with the maximum grayscale cumulative value in the fingerprint area is calculated according to the maximum grayscale cumulative value position and the offset.

8. The fingerprint splicing method according to claim 1, characterized in that: After the step of acquiring, by a rolling fingerprint collection device, a plurality of continuous frames of fingerprint images to be spliced ​​generated during the rolling process of the user's finger, the method further comprises: Determining whether to obtain multiple consecutive frames of fingerprint images to be spliced ​​of the user; If not, a prompt message is generated to prompt the user to re-acquire multiple frames of fingerprint images to be spliced.

9. A fingerprint splicing device, characterized in that: include: A data acquisition module is used to acquire multiple frames of fingerprint images to be spliced ​​generated during the rolling process of the user's finger through a rolling fingerprint acquisition device; a calculation module, configured to calculate the relative grayscale value of each pixel in the fingerprint image to be spliced ​​in each frame; and determine the fingerprint valley area and fingerprint ridge area in the fingerprint image to be spliced ​​according to the relative grayscale value; and, determining boundary parameters of the fingerprint region of the fingerprint image to be spliced ​​in the column direction according to the distribution characteristics of the relative grayscale values; A path selection module, configured to determine, based on the contrast difference between the valley area and the ridge area, a splicing path with the largest grayscale cumulative value in the fingerprint area as a target path; The splicing module is used to splice the fingerprint images to be spliced ​​based on the target path and the boundary parameters to obtain a spliced ​​fingerprint image.

10. An electronic device, characterized in that: The electronic device includes a processor and a memory, the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the fingerprint splicing method according to any one of claims 1 to 8.

Images