Fingerprint image processing method and device, storage medium and electronic device

Abstract

The application discloses a kind of fingerprint image processing method, device and storage medium and electronic equipment, wherein method includes: obtaining fingerprint original image, fingerprint original image is used to obtain fingerprint target image;Determine the first target pixel in fingerprint target image in the first mapping point of fingerprint area in fingerprint original image;Determine the target tangent of first mapping point in fingerprint original image, and according to target tangent, determine the first weight of first initial pixel around first mapping point in preset quantity;According to the pixel value of each first initial pixel and the first weight of each first initial pixel, calculate the first pixel value of first target pixel;According to the first pixel value of each first target pixel in fingerprint target image, generate the fingerprint area image of fingerprint target image;The technical scheme provided by the application strengthens fingerprint information, improves fingerprint target image quality, improves the accuracy of fingerprint identification.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of image processing, and particularly relate to a fingerprint image processing method and device, a storage medium and an electronic device. BACKGROUND

[0002] With the wide application of fingerprint recognition technology, various fingerprint collection devices have appeared on the market. In the fingerprint recognition technology, in order to improve the accuracy of fingerprint recognition, the fingerprint image needs to be enhanced.

[0003] At present, the interpolation method for the fingerprint image is to use common algorithms such as nearest-neighbor interpolation, bilinear interpolation, bicubic interpolation, etc. However, the existing image interpolation method has problems such as non-smooth ridge lines of the interpolated image, much noise, low signal-to-noise ratio, poor visual effect, etc., which reduces the quality of the target image and further reduces the accuracy of fingerprint recognition. SUMMARY

[0004] Embodiments of the present application provide a fingerprint image processing method and device, a storage medium and an electronic device to improve the quality of the fingerprint target image and improve the accuracy of fingerprint recognition.

[0005] In a first aspect, embodiments of the present application provide a fingerprint image processing method, comprising:

[0006] obtaining a fingerprint original image, the fingerprint original image being used to obtain a fingerprint target image, the fingerprint target image and the fingerprint original image being images with different resolutions;

[0007] determining a first mapping point of a first target pixel in the fingerprint target image in the fingerprint original image; the fingerprint target image comprises a fingerprint region, and the first target pixel is a pixel in the fingerprint region;

[0008] determining a target tangent line of the first mapping point in the fingerprint original image, and determining a first weight of a first initial pixel around the first mapping point according to the target tangent line;

[0009] calculating a first pixel value of the first target pixel according to a pixel value of each first initial pixel and the first weight of each first initial pixel;

[0010] generating a fingerprint region image of the fingerprint target image according to the first pixel value of each first target pixel in the fingerprint target image.

[0011] Optionally, the first mapping point is a point on a fingerprint ridge line or a fingerprint valley line of the fingerprint original image.

[0012] The determining the target tangent line of the first mapping point in the fingerprint original image comprises:

[0013] If the first mapping point is a pixel in the fingerprint original image, a tangent line of the first mapping point on the fingerprint ridge line or the fingerprint valley line is determined as the target tangent line;

[0014] If the first mapping point is a sub-pixel in the fingerprint original image, a pixel closest to the first mapping point on the fingerprint original image is determined, and a tangent line of the pixel closest to the first mapping point on the fingerprint ridge line or the fingerprint valley line is determined as the target tangent line.

[0015] Optionally, the determining the first weight of the first initial pixel around the first mapping point according to the target tangent line comprises:

[0016] calculating a first distance of each first initial pixel to the target tangent line;

[0017] determining the first weight of each first initial pixel according to the first distance of each first initial pixel to the target tangent line, the first distance and the first weight being in a negative correlation relationship.

[0018] Optionally, the determining the first weight of each first initial pixel according to the first distance of each first initial pixel to the target tangent line comprises:

[0019] in a case where the first distance of the first initial pixel to the target tangent line is less than or equal to a preset distance, calculating the first weight of the first initial pixel according to a preset weight calculation formula and the first distance of the first initial pixel to the target tangent line;

[0020] in a case where the first distance of the first initial pixel to the target tangent line is greater than the preset distance, determining a preset weight value as the first weight of the first initial pixel.

[0021] Optionally, before the determining the pixel value of the first target pixel according to the first pixel value, the method further comprises:

[0022] calculating a second distance between each first initial pixel and the first mapping point respectively, and calculating a second pixel value of the first target pixel according to the pixel value of each first initial pixel and the second distance;

[0023] The generating the fingerprint region image of the fingerprint target image according to the first pixel value of each first target pixel in the fingerprint target image comprises:

[0024] determine a pixel value of the first target pixel according to the first pixel value of the first target pixel, the second pixel value of the first target pixel and respective weight proportion coefficients;

[0025] generate the fingerprint region image according to the pixel value of each first target pixel in the fingerprint target image;

[0026] Optionally, the pixel value of the first target pixel is determined based on:

[0027] F(x, y) = G1*r1 + G2*r2;

[0028] wherein F(x, y) is the pixel value of the first target pixel (x, y); G1 is the first pixel value; G2 is the second pixel value; r1 is the weight proportion coefficient of the first pixel value, and r2 is the weight proportion coefficient of the second pixel value; r1 = 1 - r2, and the range of r2 includes [0, 1].

[0029] Optionally, if the first mapping point is a fingerprint line singular point, the weight proportion coefficient of the second pixel value is equal to 1, and the weight proportion coefficient of the first pixel value is equal to 0;

[0030] If the first mapping point is not the fingerprint line singular point, the weight proportion coefficient of the first pixel value and the weight proportion coefficient of the second pixel value are both greater than 0;

[0031] wherein the angle difference between the fingerprint line tangent direction of the fingerprint line singular point and the fingerprint line tangent direction of the adjacent fingerprint pixel of the fingerprint line singular point is greater than a preset angle.

[0032] Optionally, the fingerprint target image further includes a background region, the background region is located in a region around the fingerprint region; the method further includes:

[0033] determine a second mapping point of a second target pixel in the fingerprint target image in the fingerprint original image; the second target pixel is a pixel in the background region;

[0034] respectively calculate third distances between a preset number of second initial pixels around the second mapping point and the second mapping point, and calculate the pixel value of the second target pixel according to the pixel value of each second initial pixel and the third distance;

[0035] generate a background region image of the fingerprint target image according to the pixel value of each second target pixel in the fingerprint target image.

[0036] In a second aspect, an embodiment of the present application provides a fingerprint image processing device, including:

[0037] An original image acquisition module is configured to acquire a fingerprint original image, wherein the fingerprint original image is used to obtain a fingerprint target image, and the fingerprint target image and the fingerprint original image are images with different resolutions.

[0038] A mapping point determination module is configured to determine a first mapping point of a first target pixel in the fingerprint target image in the fingerprint original image, wherein the fingerprint target image comprises a fingerprint region, and the first target pixel is a pixel in the fingerprint region.

[0039] A first weight determination module is configured to determine a target tangent line of the first mapping point in the fingerprint original image, and determine first weights of a preset number of first initial pixels around the first mapping point according to the target tangent line.

[0040] A first pixel value calculation module is configured to calculate a first pixel value of the first target pixel according to pixel values of the first initial pixels and the first weights of the first initial pixels.

[0041] A fingerprint target image generation module is configured to generate a fingerprint region image of the fingerprint target image according to the first pixel value of each first target pixel in the fingerprint target image.

[0042] In a third aspect, an embodiment of the present application provides a storage medium, which stores computer instructions, and the computer instructions are used to enable a processor to implement the fingerprint image processing method in any one of the first aspect.

[0043] In a fourth aspect, an embodiment of the present application provides an electronic device, which comprises:

[0044] at least one processor; and

[0045] a memory connected with the at least one processor; wherein

[0046] the memory stores computer programs executable by the at least one processor, and the computer programs are executed by the at least one processor to enable the at least one processor to execute the fingerprint image processing method in any one of the first aspect.

[0047] The embodiment of the present application provides a fingerprint image processing method, device, storage medium and electronic equipment, wherein the fingerprint image processing method comprises the following steps: obtaining a fingerprint original image, the fingerprint original image is used to obtain a fingerprint target image, the fingerprint target image and the fingerprint original image are images with different resolutions; determining a first mapping point of a first target pixel in the fingerprint target image in the fingerprint original image; the fingerprint target image comprises a fingerprint area, and the first target pixel is a pixel in the fingerprint area; determining a target tangent line of the first mapping point in the fingerprint original image, and determining a first weight of a first initial pixel around the first mapping point according to the target tangent line; calculating a first pixel value of the first target pixel according to a pixel value of each first initial pixel and the first weight of each first initial pixel; and generating a fingerprint area image of the fingerprint target image according to the first pixel value of each first target pixel in the fingerprint target image. The technical scheme provided by the embodiment of the present application determines the target tangent line of the first mapping point in the fingerprint original image to determine the ridge line direction of the mapping point; and calculates the first weight (direction weight) of the initial pixel around the mapping point relative to the target tangent line, takes the ridge line direction (fingerprint direction field) as a parameter to participate in calculation, strengthens the fingerprint information, smoothes the ridge line, suppresses noise, improves the image visual effect, thereby improving the quality of the fingerprint target image, and more favorably extracting feature points, and further improving the accuracy of fingerprint identification. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 is a comparison chart of the resolution of a fingerprint image provided in the prior art;

[0049] Figure 2 is a flowchart of a fingerprint image processing method provided by the embodiment of the present application;

[0050] Figure 3 is a flowchart of another fingerprint image processing method provided by the embodiment of the present application;

[0051] Figure 4 is a schematic diagram of a fingerprint ridge line and a fingerprint valley line in a fingerprint provided by the embodiment of the present application;

[0052] Figure 5 is a coordinate diagram of a direction weight function and a ridge line tangent function provided by the embodiment of the present application;

[0053] Figure 6 is a flowchart of another fingerprint image processing method provided by the embodiment of the present application;

[0054] Figure 7 is a schematic diagram of a singular point in a fingerprint provided by the embodiment of the present application;

[0055] Figure 8 is a structural block diagram of a fingerprint image processing device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0056] The application will be further described below in conjunction with the accompanying drawings and examples. It should be understood that the specific examples described herein are intended to be illustrative only and are not intended to limit the scope of the application. In addition, it should be understood that the drawings are not necessarily to scale and that the specific examples described herein are merely illustrative of the application and are not intended to limit the scope of the application.

[0057] As described in the background, with the wide application of fingerprint identification technology, there are various fingerprint collection devices on the market. In the fingerprint identification application, it is often necessary to compare the fingerprints collected by different collection devices, which requires that the collected fingerprint images all follow the same standard, and the most critical one is the image resolution DPI (Dots Per Inch). Different DPIs will cause the same fingerprint comparison to fail, which requires that the fingerprint image be converted to a predetermined standard DPI using an interpolation algorithm first. Figure 1 is a comparison chart of fingerprint image resolution provided in the prior art, referring to Figure 1 For example, the image (original image) collected by the fingerprint collection device is 300 DPI, and the resolution of the standard comparison image is 500 DPI. When the fingerprint image in the fingerprint library is used for actual identification comparison, the 300 DPI image needs to be interpolated to 500 DPI, and then the features are extracted and identified.

[0058] The interpolation method for the fingerprint image at present is to use common algorithms, such as nearest neighbor interpolation, bilinear interpolation, bicubic interpolation, etc. Nearest neighbor interpolation method: the gray value of the nearest pixel to the standard image pixel in the original image is selected as the interpolation result. The nearest interpolation valve is simple and fast in difference calculation, but it will cause the image to have obvious sawtooth and large noise. Bilinear interpolation method: the interpolation result is obtained according to the surrounding 4 pixels of the position of the pixel in the standard image mapped to the original image. The bilinear interpolation is based on linear distance in the row and column directions of the pixel, and the bilinear interpolated fingerprint image is slightly blurred, but the edge transition is more natural. Cubic convolution interpolation: also known as cubic convolution interpolation, 16 surrounding pixels of the position of the pixel in the standard image mapped to the original image are used for cubic interpolation calculation to obtain the interpolation result, which can produce smoother edges than bilinear interpolation, and the processed image has less image quality loss and better effect.

[0059] However, since the three common image interpolation methods adopt the same processing mode for the ridge part and the non-ridge part, neither the noise is suppressed nor the effective fingerprint information is increased, and problems such as non-smooth image ridge, much noise, low signal-to-noise ratio, poor visual effect and the like exist, which reduces the quality of the target image and further leads to the reduction of the accuracy of the fingerprint recognition.

[0060] In view of this, the embodiment of the present application provides a fingerprint image processing method, Figure 2 is a flowchart of the fingerprint image processing method provided by the embodiment of the present application, referring to Figure 2 , the fingerprint image processing method comprises:

[0061] S110, obtaining a fingerprint original image, the fingerprint original image is used to obtain a fingerprint target image, the fingerprint target image and the fingerprint original image are images with different resolutions.

[0062] Specifically, before the fingerprint image processing, the pixel value of each initial pixel in the fingerprint original image is a known quantity, and the pixel value of each target pixel in the fingerprint target image is a to-be-solved quantity. The fingerprint original image can be obtained by a fingerprint collection device, and the pixel value of each initial pixel in the fingerprint original image can be determined. The fingerprint original image can be understood as an image with a resolution that does not meet a preset comparison resolution, i.e. an image with a resolution that does not meet the comparison requirement after being collected by the fingerprint collection device. The fingerprint target image is an image with a resolution that meets the comparison requirement after the image processing, i.e. an image with a resolution that meets the preset comparison resolution. The number of pixels in the fingerprint target image can be greater than the number of pixels in the fingerprint original image, in which case the resolution of the fingerprint target image is greater than the resolution of the fingerprint original image. The number of pixels in the fingerprint target image can also be less than the number of pixels in the fingerprint original image, in which case the resolution of the fingerprint target image is less than the resolution of the fingerprint original image.

[0063] S120, determining a first mapping point of a first target pixel in the fingerprint target image in the fingerprint original image; the fingerprint target image comprises a fingerprint region, and the first target pixel is a pixel in the fingerprint region.

[0064] Specifically, the fingerprint target image includes a fingerprint region, each first target pixel in the fingerprint region has a corresponding first mapping point in the fingerprint original image, and the first target pixel in the fingerprint target image is in one-to-one correspondence with the first mapping point. The position of the first mapping point can be determined according to the position coordinates of each first target pixel in the fingerprint target image, and the scaling multiple between the resolution of the fingerprint target image and the resolution of the fingerprint original image. For example, the fingerprint target image includes 16 first target pixels, and the 16 first target pixels are distributed in the form of an array with a height of 4 pixels and a width of 4 pixels. The fingerprint original image includes 9 pixels, and the 9 pixels are distributed in the form of an array with a height of 3 pixels and a width of 3 pixels. That is, the fingerprint original image is enlarged by about 1.33 times in the horizontal and vertical directions to obtain the fingerprint target image. For the first target pixel with position coordinates (3, 3) in the fingerprint target image, the corresponding first mapping point has position coordinates (2.25, 2.25) in the fingerprint original image.

[0065] In S130, a target tangent line of the first mapping point in the fingerprint original image is determined, and a first weight of a first initial pixel around the first mapping point is determined according to the target tangent line.

[0066] Specifically, the fingerprint line can be understood as a fingerprint ridge. The tangent direction of the fingerprint line at a certain point is the ridge direction at the position. The target tangent line is a tangent line on the fingerprint line. For the first mapping point falling in the fingerprint region, the ridge direction of the first mapping point can be determined to determine the tangent direction of the target tangent line. The first weight of each first initial pixel around the first mapping point relative to the target tangent line can be understood as the direction weight of each first initial pixel around relative to the ridge direction. The first weight is related to the deviation degree of the first initial pixel relative to the target tangent line. If the deviation degree is greater, the direction weight of the first initial pixel relative to the ridge direction is smaller; on the contrary, if the deviation degree is smaller, the direction weight of the first initial pixel relative to the ridge direction is greater. The number of the preset number of first initial pixels can be 4 or 16, or other numbers.

[0067] In S140, a first pixel value of the first target pixel is calculated according to the pixel value of each first initial pixel and the first weight of each first initial pixel.

[0068] Specifically, the first pixel value of the corresponding first target pixel in the fingerprint target image can be determined by determining the pixel value of the first mapping point. The pixel value of the first mapping point is determined according to each first initial pixel located around the first mapping point, the number of the first initial pixels around the first mapping point includes a plurality, for example, the 4 points or 16 points described above, and the pixel value of the first mapping point is calculated according to the first weight of each first initial pixel and the pixel value of the first initial pixel based on the bilinear interpolation algorithm or the cubic convolution interpolation algorithm. Further, the first pixel value of the first target pixel is calculated according to the pixel value of each first initial pixel and the first weight of each first initial pixel. By introducing the direction weight (the first weight) as a parameter into the calculation, the direction weight changes with the different direction of the fingerprint line, and then the direction of the fingerprint is introduced into the processing of the image resolution, which can enhance the fingerprint information in the fingerprint target image, reduce the sawtooth, play a role in smoothing the fingerprint line, improve the visual effect, and be more conducive to extracting the feature point.

[0069] S150, generating the fingerprint region image of the fingerprint target image according to the first pixel value of each first target pixel in the fingerprint target image.

[0070] Specifically, the first pixel value can be a gray value, and after the first pixel value of each first target pixel is calculated, the gray value of each pixel in the fingerprint region of the fingerprint target image can be determined, so as to determine the fingerprint region image of the fingerprint target image.

[0071] Exemplarily, the fingerprint region image in the fingerprint original image can be a 3*3 256-level gray image, that is, an image with a height of 3 pixels and a width of 3 pixels, and the gray value of each pixel can be 0-255, representing the brightness of the pixel. 255 can represent the brightest, that is, white, and 0 represents the darkest, that is, black. Enlarging this image to a 4*4 image, the fingerprint region image in the fingerprint target image is an image with a height of 4 pixels and a width of 4 pixels, and there are 16 pixels in total. In the fingerprint target image, the fingerprint region image pixel matrix is as follows:

[0072]

[0073] The fingerprint region image can be determined according to the fingerprint region image pixel matrix.

[0074] The fingerprint image processing method provided by the embodiment of the present application is based on the interpolation algorithm in the prior art, and the first pixel value of the corresponding first target pixel is determined according to the pixel value of the first initial pixel located around the first mapping point; the ridge line direction (fingerprint direction field) is taken as a parameter to participate in the calculation by determining the ridge line direction of the first mapping point and calculating the direction weight of the first initial pixel around the first mapping point relative to the ridge line direction; the parameter of the image ridge line direction is introduced into the calculation of the first pixel value of each first target pixel. By the interpolation method of the fingerprint image according to the direction field, the fingerprint information in the fingerprint target image can be enhanced, the effect of smoothing the ridge line can be achieved, the visual effect can be improved, the effect of improving the quality of the target image is achieved, the feature points are more beneficial to be extracted, and the accuracy of the fingerprint recognition is improved.

[0075] Figure 3 is a flowchart of another fingerprint image processing method provided by the embodiment of the present application, referring to Figure 3 , the fingerprint image processing method comprises:

[0076] S210, acquiring a fingerprint original image, the fingerprint original image is used to obtain a fingerprint target image, the fingerprint target image and the fingerprint original image are images with different resolutions.

[0077] S220, determining a first mapping point of a first target pixel in the fingerprint target image in the fingerprint original image; the fingerprint target image comprises a fingerprint region, and the first target pixel is a pixel in the fingerprint region.

[0078] S230, if the first mapping point is a pixel in the fingerprint original image, determining a tangent of the first mapping point on a fingerprint ridge line or a fingerprint valley line as a target tangent; if the first mapping point is a sub-pixel in the fingerprint original image, determining a pixel closest to the first mapping point on the fingerprint original image, and determining a tangent of the pixel closest to the first mapping point on the fingerprint ridge line or the fingerprint valley line as the target tangent.

[0079] Specifically, Figure 4 is a schematic diagram of a fingerprint ridge line and a fingerprint valley line in a fingerprint, referring to Figure 4 , the fingerprint line can be divided into a fingerprint ridge line and a fingerprint valley line 2, the first mapping point is a point on the fingerprint ridge line 1 or the fingerprint valley line 2 of the fingerprint original image. If the first mapping point is on the fingerprint ridge line 1 of the fingerprint original image, the target tangent is a tangent of the first mapping point on the fingerprint ridge line 1; if the first mapping point is on the fingerprint valley line 2 of the fingerprint original image, the target tangent is a tangent of the first mapping point on the fingerprint valley line 2.

[0080] Part of the first target pixels correspond to the first mapping points in the fingerprint original image are pixels of the fingerprint original image, and part of the first target pixels correspond to the first mapping points in the fingerprint original image are sub-pixels of the fingerprint original image. The sub-pixel can be understood as a virtual pixel of a position point between two adjacent pixels. The virtual pixel is a non-existent pixel. The pixel value of the sub-pixel is not included in the fingerprint original image obtained by the fingerprint acquisition device. For example, the fingerprint original image is an image with a height of 3 pixels and a width of 3 pixels, and there are a total of 9 pixels. The fingerprint target image is an image with a height of 4 pixels and a width of 4 pixels, and there are a total of 16 pixels. Among them, 9 first target pixels correspond to the first mapping points in the fingerprint original image are pixels of the fingerprint original image, and 7 first target pixels correspond to the first mapping points in the fingerprint original image are sub-pixels of the fingerprint original image.

[0081] The position coordinates of the first mapping point include the coordinate value of the row where the first mapping point is located and the coordinate value of the column where the first mapping point is located. If the two coordinate values of the first mapping point are integers, the first mapping point is a pixel in the fingerprint original image. Then, determining the target tangent line of the first mapping point in the fingerprint original image includes: determining the tangent line of the first mapping point on the fingerprint ridge line or the fingerprint valley line as the target tangent line. It can be understood that the target tangent line is a tangent line determined by taking the first mapping point as a tangent point and taking the ridge line direction of the first mapping point as the line tangent direction.

[0082] If at least one of the two coordinate values of the first mapping point is a decimal, the first mapping point is a sub-pixel in the fingerprint original image. Then, determining the target tangent line of the first mapping point in the fingerprint original image includes: determining the pixel closest to the first mapping point on the fingerprint original image, and determining the tangent line of the pixel closest to the first mapping point on the fingerprint ridge line or the fingerprint valley line as the target tangent line. It can be understood that the target tangent line is a tangent line determined by taking the pixel closest to the first mapping point as a tangent point and taking the ridge line direction of the pixel closest to the first mapping point as the line tangent direction.

[0083] For example, the original fingerprint image is a 100*100 256-level grayscale image, including 100 pixels in each row and 100 pixels in each column. The target fingerprint image is a 300*300 256-level grayscale image, including 300 pixels in each row and 300 pixels in each column. The original fingerprint image is enlarged by 3 times in the horizontal and vertical directions to obtain the target fingerprint image. The coordinate of the first target pixel in the 9th row and the 9th column of the target fingerprint image is (9, 9); the coordinate of the first mapping point corresponding to the first target pixel in the 9th row and the 9th column of the target fingerprint image in the original fingerprint image is (3, 3); at this time, both coordinate values of the first mapping point are integers, the first mapping point is a pixel in the original fingerprint image, and the coordinate of the pixel as the first mapping point is (3, 3). The coordinate of the first target pixel in the 4th row and the 9th column of the target fingerprint image is (4, 9); the coordinate of the first mapping point corresponding to the first target pixel in the 4th row and the 9th column of the target fingerprint image in the original fingerprint image is (1.33, 3); at this time, one of the two coordinate values of the first mapping point is a decimal, the first mapping point is a sub-pixel in the original fingerprint image, and the coordinate of the sub-pixel as the first mapping point is (1.33, 3). The coordinate of the first target pixel in the 2nd row and the 2nd column of the target fingerprint image is (2, 2); the coordinate of the first mapping point corresponding to the first target pixel in the 2nd row and the 2nd column of the target fingerprint image in the original fingerprint image is (0.66, 0.66); at this time, both coordinate values of the first mapping point are decimals, the first mapping point is a sub-pixel in the original fingerprint image, and the coordinate of the sub-pixel as the first mapping point is (0.66, 0.66).

[0084] For example, the coordinate of the first mapping point is (3, 3), the first mapping point (3, 3) is taken as the tangent point, the fingerprint tangent line determined by taking the ridge line direction of the first mapping point (3, 3) as the line tangent direction is taken as the target tangent line. For example, the coordinate of the first mapping point is (1.33, 3), the pixel (1, 3) closest to the first mapping point (1.33, 3) is taken as the tangent point, the fingerprint tangent line determined by taking the ridge line direction of the pixel (1, 3) as the line tangent direction is taken as the target tangent line; for example, the coordinate of the first mapping point is (0.66, 0.66), the pixel (1, 1) closest to the first mapping point (0.66, 0.66) is taken as the tangent point, the fingerprint tangent line determined by taking the ridge line direction of the pixel (1, 1) as the line tangent direction is taken as the target tangent line.

[0085] Optionally, with reference to Figure 3 , the first weight of the first initial pixel in the preset number of first initial pixels around the first mapping point is determined according to the target tangent line, including:

[0086] S240, calculating a first distance of each first initial pixel to the target tangent line; determining a first weight of each first initial pixel according to the first distance of each first initial pixel to the target tangent line, the first distance and the first weight being in a negative correlation.

[0087] Specifically, Figure 5 is a coordinate graph of a direction weight function and a line tangent function provided by an embodiment of the present application, for reference Figure 5 , taking a row where a pixel is located as an abscissa axis, taking a column where the pixel is located as an ordinate axis, and taking a tangent point as an origin o to establish a rectangular coordinate system; a target tangent line equation passing through the tangent point is determined based on the following:

[0088] y=tan(θ)*x,

[0089] wherein θ is a line direction, x is an abscissa in the coordinate system, and y is an ordinate in the coordinate system. According to a point-to-line distance formula, a distance of a point P(x0, y0) outside a line to the line is The position coordinates of each first initial pixel around the first mapping point are correspondingly converted into coordinates in the above rectangular coordinate system, so that a distance of each first initial pixel relative to the target tangent line is correspondingly obtained. A row coordinate in an image corresponds to an ordinate in the rectangular coordinate system, and a column coordinate in the image corresponds to an abscissa in the rectangular coordinate system. For example, a first mapping point in a fingerprint original image is located at the third row and the fourth column, and the position coordinates of the first mapping point are (3, 4). Taking the first mapping point as the origin o in the rectangular coordinate system, the coordinate point of the first mapping point in the rectangular coordinate system is (0, 0). A first initial pixel located at the second row and the fourth column near the first mapping point has position coordinates (2, 4), and the coordinate point of the first initial pixel in the above rectangular coordinate system is (0, -1) after being correspondingly converted. A first initial pixel located at the third row and the fifth column near the first mapping point has position coordinates (3, 5), and the coordinate point of the first initial pixel in the above rectangular coordinate system is (1, 0) after being correspondingly converted.

[0090] If the origin o in the rectangular coordinate system is not located at the tangent point, the target tangent line equation can be adjusted to a line equation in a corresponding rectangular coordinate system, and the coordinates of each first initial pixel around the first mapping point are correspondingly converted into coordinates in the corresponding rectangular coordinate system, so that a distance of each first initial pixel in the fingerprint original image relative to the target tangent line is correspondingly obtained.

[0091] Optionally, the first weight of each first initial pixel is determined according to the first distance of each first initial pixel to the target tangent line, and the method comprises the following steps.

[0092] In a case where the first distance of the first initial pixel to the target tangent line is less than or equal to a preset distance, the first weight of the first initial pixel is calculated according to a preset weight calculation formula and the first distance of the first initial pixel to the target tangent line.

[0093] In a case that the first distance between the first initial pixel and the target tangent line is greater than the preset distance, the preset weight value is determined as the first weight of the first initial pixel.

[0094] In an embodiment of the present application, the first weight of each first initial pixel is determined according to the first distance between each first initial pixel and the target tangent line, and the determination is based on the following determination:

[0095]

[0096] wherein w'(l) is the first weight, and l is the first distance between the first initial pixel in the original fingerprint image and the target tangent line; a is a coefficient, and the range includes -1.5-0.5. According to actual calculation, when a=-1, the accuracy of the determined target fingerprint image is higher. Then the first weight calculation formula is simplified as:

[0097]

[0098] When the distance between the first initial pixel in the original fingerprint image and the target tangent line is greater than 1, the weight value is 0. The weight value of the pixel in the direction of the ridge line can be increased while the weight value of the pixel in the direction perpendicular to the ridge line is decreased, so as to avoid the influence of the gray value of the initial pixel with a relatively far distance from the target tangent line on the target gray value. When the interpolation of the fingerprint image is performed, other weight calculation formulas can be used.

[0099] Optionally, with reference back to Figure 3 After S240, the fingerprint image processing method further includes:

[0100] S250, performing normalization processing on the first weight, and determining a first weight pixel value of each pixel according to the product of the pixel value of each pixel around the first mapping point and the normalized first weight corresponding to each pixel.

[0101] Optionally, with reference back to Figure 3 After S250, the fingerprint image processing method further includes:

[0102] S260, performing summation calculation on the first weight pixel value of each pixel around the first mapping point to determine a first pixel value of a first target pixel corresponding to the first mapping point.

[0103] Specifically, the normalization processing is to ensure that the sum of the first weights of the pixels around the first mapping point is 1, so as to ensure that the gray value of the pixel and the gray value range of the target pixel are 0-255.

[0104] For example, the first pixel value of the first target pixel is obtained by performing convolution on the 4*4 points around the first mapping point (j+u, i+v) after the first weight normalization. Wherein, the first pixel value of the first target pixel is calculated based on the first weight and the pixel value of each first initial pixel around the first mapping point according to the following determination:

[0105]

[0106] Wherein, (i+v, j+u) represents the position coordinate of the first mapping point of the first target pixel (x, y) in the original fingerprint image; G1(i+v, j+u) represents the first pixel value of the first target pixel corresponding to the first mapping point; (i+row, j+col) is the position coordinate of the first initial pixel around the first mapping point; f(i+row, j+col) is the pixel value (such as gray value) of the first initial pixel around the first mapping point; w'(l) is the first weight of the first initial pixel around the first mapping point. row is the difference between the coordinate of the row where the first initial pixel around the first mapping point is located and the integer part i of the coordinate of the row where the first mapping point is located, and col is the difference between the coordinate of the column where the first initial pixel around the first mapping point is located and the integer part j of the coordinate of the column where the first mapping point is located; v is the decimal part of the row coordinate point in the first mapping point, and u is the decimal part of the column coordinate point in the first mapping point.

[0107] It should be noted that if the first mapping point is a boundary point or close to the boundary point in the original fingerprint image, and there are less than 16 initial pixels around the first mapping point, the initial pixels around the first mapping point can be determined according to the existing pixels.

[0108] S270, according to the first pixel value of each first target pixel in the fingerprint target image, generating a fingerprint region image of the fingerprint target image.

[0109] Optionally, in one or more embodiments of the present application, before determining the pixel value of the first target pixel according to the first pixel value, the fingerprint image processing method further comprises:

[0110] respectively calculating the second distance between each first initial pixel and the first mapping point, and calculating the second pixel value of the first target pixel according to the pixel value of each first initial pixel and the second distance.

[0111] According to the first pixel value of each first target pixel in the fingerprint target image, generating a fingerprint region image of the fingerprint target image, comprising:

[0112] determining the pixel value of the first target pixel according to the first pixel value of the first target pixel, the second pixel value of the first target pixel, and the respective weight proportion coefficient;

[0113] According to the pixel value of each first target pixel in the fingerprint target image, a fingerprint region image is generated.

[0114] The following describes how to calculate the second pixel value and how to determine the pixel value of the first target pixel according to the first pixel value, the second pixel value, and the respective weight proportion coefficient. Figure 6

[0115] Figure 6 is a flowchart of another fingerprint image processing method provided by an embodiment of the present application, which is described with reference to Figure 6 , the fingerprint image processing method comprises:

[0116] S310, a fingerprint original image is acquired, the fingerprint original image is used to obtain a fingerprint target image, the fingerprint target image and the fingerprint original image are images with different resolutions.

[0117] S320, a first mapping point of a first target pixel in the fingerprint target image in the fingerprint original image is determined; the fingerprint target image comprises a fingerprint region, and the first target pixel is a pixel in the fingerprint region.

[0118] S330, if the first mapping point is a pixel in the fingerprint original image, a tangent of the first mapping point on a fingerprint ridge line or a fingerprint valley line is determined as a target tangent; if the first mapping point is a sub-pixel in the fingerprint original image, a pixel closest to the first mapping point on the fingerprint original image is determined, and a tangent of the pixel on the fingerprint ridge line or the fingerprint valley line is determined as the target tangent.

[0119] S340, a first distance of each first initial pixel to the target tangent is calculated; according to the first distance of each first initial pixel to the target tangent, a first weight of each first initial pixel is determined, and the first distance and the first weight are in a negative correlation relationship.

[0120] S350, the first weight is normalized, and a first weight pixel value of each pixel is determined according to a product of a pixel value of each pixel around the first mapping point and a normalized first weight corresponding to the pixel.

[0121] S360, a first pixel value of the first target pixel corresponding to the first mapping point is determined by performing summation calculation on the first weight pixel value of each pixel around the first mapping point.

[0122] S370, a second distance between each first initial pixel and the first mapping point is calculated respectively, and a second pixel value of the first target pixel is calculated according to a pixel value of each first initial pixel and the second distance.

[0123] ​Specifically, the second pixel value can be determined using a cubic convolution. For example, based on the 4*4 initial pixels surrounding the mapping point (j+u, i+v), the second pixel value of the corresponding target pixel is determined based on the following:

[0124]

[0125] Where (i+v,j+u) ​​represents the position coordinates of the first target pixel (x,y) in the original fingerprint image as the first mapping point; G1(i+v,j+u) ​​represents the second pixel value of the target pixel corresponding to the first mapping point; f(i+row,j+col) is the pixel value of the first initial pixel located around the first mapping point; w(row-v)w(col-u) is the second weight of the first initial pixel located around the first mapping point; the second weight is determined based on the product of the row coordinate distance weight and the ordinate distance weight. row is the difference between the coordinate of the row where the first initial pixel is located around the first mapping point and the integer part i of the coordinate of the row where the mapping point is located; col is the difference between the coordinate of the column where the first initial pixel is located around the first mapping point and the integer part j of the coordinate of the column where the mapping point is located; v is the decimal part of the row coordinate of the mapping point; u is the decimal part of the column coordinate of the mapping point. The second distance includes the horizontal coordinate distance between the first initial pixel and the first mapping point, and the vertical coordinate distance between the first initial pixel and the first mapping point.

[0126] The row coordinate distance weight and the y-coordinate distance weight are determined based on the following:

[0127]

[0128] Similarly, 'a' is a coefficient ranging from -1.5 to -0.5. Based on actual calculations, when a = -1, the accuracy of the determined fingerprint target image is relatively high. For the row coordinate distance weight, x = row - v; substituting the value of x into the above weight formula yields the row coordinate distance weight. For the column coordinate distance weight, x = col - u; substituting the value of x into the above weight formula yields the column coordinate distance weight.

[0129] S380. Determine the pixel value of the first target pixel based on the first pixel value of the first target pixel, the second pixel value of the first target pixel, and their respective weight ratio coefficients.

[0130] Optionally, the pixel value of the first target pixel is determined based on the first pixel value, the second pixel value of the first target pixel, and their respective weight ratio coefficients, and is determined based on the following:

[0131] F(x, y) = G1*r1 + G2*r2;

[0132] Wherein, F(x, y) is the pixel value of the first target pixel (x, y) in the fingerprint target image; G1 is the first pixel value; G2 is the second pixel value; r1 is the weight proportion coefficient of the first pixel value, and r2 is the weight proportion coefficient of the second pixel value; r1 = 1-r2, and the range of r2 includes [0, 1]. The weight proportion coefficient r1 is proportional to the change degree of the surrounding direction. For example, r2 can be set as 0.5. Wherein, the sum of the weight proportion coefficients of the first pixel value and the second pixel value is 1, so that the sum of the proportions of the first pixel value and the second pixel value is 100%.

[0133] Optionally, if the first mapping point is a fingerprint line singular point, the weight proportion coefficient of the second pixel value is equal to 1, and the weight proportion coefficient of the first pixel value is equal to 0.

[0134] If the first mapping point is not the fingerprint line singular point, the weight proportion coefficient of the first pixel value and the weight proportion coefficient of the second pixel value are both greater than 0.

[0135] Wherein, the fingerprint line singular point is a point whose angle difference between the fingerprint line tangent direction and the fingerprint line tangent direction of the adjacent fingerprint pixel is greater than a preset angle.

[0136] Specifically, Figure 7 is a schematic diagram of a fingerprint singular point provided by an embodiment of the present application, with reference to Figure 5 The characteristics of the fingerprint lines include that the directions of each fingerprint line (fingerprint ridge line and fingerprint valley line) are gradually changed; in a local area, except the areas near the center point B and the delta point A, the direction difference of adjacent fingerprint lines is small. The fingerprint line singular points include the center point B and the delta point A (the point on the triangular fingerprint line). The direction field of these singular points changes greatly, and if the direction field of these singular points is used for interpolation calculation, the calculation result will be inaccurate, so the calculation of these singular points does not consider the direction field. If the first mapping point is in the area of the fingerprint line singular point, the weight proportion coefficient r1 of the first pixel value is equal to 0, and the weight proportion coefficient r2 of the second pixel value is equal to 1. Compared with the general interpolation method used in the prior art at the fingerprint line singular point, the direction field is not considered, and after the combination of the direction field, the present embodiment can make the details of the fingerprint line end point and the intersection point in the fingerprint target image clearer, the background more natural, and the feature position shift prevented.

[0137] S390, generating a fingerprint area image according to the pixel value of each first target pixel in the fingerprint target image.

[0138] Based on the above embodiments, the fingerprint image processing method provided in this invention further utilizes an interpolation algorithm to determine the second pixel value of the corresponding first target pixel based on the pixel values ​​of the first initial pixels surrounding the mapping point; then, it determines the pixel value of the first target pixel corresponding to the mapping point based on the first pixel value, the second pixel value, and their respective weighting coefficients; wherein the calculation of the first pixel value incorporates a parameter of the image ridge direction, so that the pixel value calculation of each target pixel incorporates the parameter of the image ridge direction. By interpolating the fingerprint image according to the orientation field, the fingerprint information in the fingerprint target image can be enhanced, smoothing the ridges, improving the visual effect, and achieving the effect of improving the quality of the target image, which is more conducive to extracting feature points, thereby improving the accuracy of fingerprint recognition. Furthermore, the introduction of the second pixel value avoids inaccurate calculation results caused by using the orientation fields of singular points in the fingerprint image due to large changes in the orientation field. This improves the image quality of the entire fingerprint region in the entire fingerprint target image.

[0139] Optionally, the fingerprint target image also includes a background region located within the area surrounding the fingerprint region; the method further includes:

[0140] Determine the second mapping point of the second target pixel in the fingerprint target image in the original fingerprint image; the second target pixel is a pixel within the background region;

[0141] Calculate the third distance between a preset number of second initial pixels around the second mapping point and the second mapping point, and calculate the pixel value of the second target pixel based on the pixel value of each second initial pixel and the third distance;

[0142] A background region image of the fingerprint target image is generated based on the pixel value of each second target pixel in the fingerprint target image.

[0143] The determination of the second target pixel in the fingerprint target image can refer to the calculation process of the second pixel value, which will not be repeated here. The third distance includes the horizontal coordinate distance between the second initial pixel and the second mapping point, and the vertical coordinate distance between the second initial pixel and the second mapping point.

[0144] In summary, the technical scheme provided by the embodiment of the present application determines the ridge direction of the first mapping point, and calculates the direction weight of the first initial pixel around the first mapping point relative to the ridge direction; the ridge direction (fingerprint direction field) is taken as a parameter to participate in the calculation, which strengthens the fingerprint information, smoothes the ridge, suppresses the noise, and improves the image visual effect, thereby improving the quality of the fingerprint target image, and more favorably extracting the feature point, and further improving the accuracy of the fingerprint recognition. Table 1 is a fingerprint recognition comparison table of the prior art and the embodiment of the present application. Referring to Table 1, it is verified by actual test of the fingerprint library that, under the comparison condition of a similarity of 0.97, the 362DPI image is interpolated to 500DPI, and the technical scheme provided by the embodiment of the present application can reduce the false recognition rate and the rejection rate of the fingerprint recognition relative to the simple use of the bilinear difference algorithm or the cubic convolution in the prior art. The false recognition rate refers to the probability of the fingerprint recognition error under the condition that the fingerprint image is interpolated to 500DPI and the similarity satisfies 0.97. The rejection rate refers to the probability that the similarity does not satisfy 0.97 after the fingerprint image is interpolated to 500DPI.

[0145] Table 1 is a fingerprint recognition comparison table of the prior art and the embodiment of the present application.

[0146]

[0147] The embodiment of the present application also provides a fingerprint image processing device for executing the fingerprint image processing method in any of the above embodiments. Figure 8 Fig. 1 is a structural block diagram of a fingerprint image processing device provided by the embodiment of the present application, referring to Figure 8 The fingerprint image processing device comprises:

[0148] An original image acquisition module 10 is configured to acquire a fingerprint original image, the fingerprint original image being used to obtain a fingerprint target image, the fingerprint target image and the fingerprint original image being images with different resolutions.

[0149] A mapping point determination module 20 is configured to determine a first mapping point of a first target pixel in a fingerprint target image in a fingerprint original image; the fingerprint target image comprises a fingerprint region, and the first target pixel is a pixel in the fingerprint region.

[0150] A first weight determination module 30 is configured to determine a target tangent of the first mapping point in the fingerprint original image, and determine a first weight of a first initial pixel around the first mapping point according to the target tangent; the first initial pixel is a pixel within a preset range of the first mapping point.

[0151] A first pixel value calculation module 40 is configured to calculate a first pixel value of the first target pixel according to a pixel value of each first initial pixel and the first weight of each first initial pixel.

[0152] The fingerprint target image generation module 50 is configured to generate a fingerprint region image of the fingerprint target image according to the first pixel value of each first target pixel in the fingerprint target image.

[0153] Optionally, the first mapping point is a point on a fingerprint ridge line or a fingerprint valley line of the fingerprint original image; the first weight determination module comprises a target tangent line determination submodule, and the target tangent line determination submodule is configured to, if the first mapping point is a pixel in the fingerprint original image, determine a tangent line of the first mapping point on the fingerprint ridge line or the fingerprint valley line as the target tangent line.

[0154] If the first mapping point is a sub-pixel in the fingerprint original image, a pixel closest to the first mapping point in the fingerprint original image is determined, and a tangent line of the pixel closest to the first mapping point on the fingerprint ridge line or the fingerprint valley line is determined as the target tangent line.

[0155] Optionally, the first weight determination module comprises a first weight calculation submodule, and the first weight calculation submodule is configured to calculate a first distance of each first initial pixel to the target tangent line, and determine a first weight of each first initial pixel according to the first distance of each first initial pixel to the target tangent line, the first distance and the first weight being in a negative correlation relationship.

[0156] Optionally, the first weight calculation submodule is further configured to, in a case where the first distance of the first initial pixel to the target tangent line is less than or equal to a preset distance, calculate the first weight of the first initial pixel according to a preset weight calculation formula and the first distance of the first initial pixel to the target tangent line; and in a case where the first distance of the first initial pixel to the target tangent line is greater than the preset distance, determine a preset weight value as the first weight of the first initial pixel.

[0157] Optionally, the fingerprint image processing apparatus further comprises a second pixel value calculation module configured to calculate a second distance between each first initial pixel and the first mapping point respectively, and calculate a second pixel value of each first target pixel according to the pixel value of each first initial pixel and the second distance.

[0158] The fingerprint target image generation module 50 is further configured to determine a pixel value of each first target pixel according to the first pixel value of each first target pixel, the second pixel value of each first target pixel and a respective weight proportion coefficient, and generate a fingerprint region image according to the pixel value of each first target pixel in the fingerprint target image.

[0159] Optionally, the pixel value of each first target pixel is determined based on the following formula:

[0160] F(x, y) = G1*r1 + G2*r2.

[0161] Wherein, F(x, y) is the pixel value of the first target pixel (x, y); G1 is the first pixel value; G2 is the second pixel value; r1 is the weight proportion coefficient of the first pixel value, and r2 is the weight proportion coefficient of the second pixel value; r1 = 1-r2, and the range of r2 includes [0, 1].

[0162] Optionally, if the first mapping point is a fingerprint line singular point, the weight proportion coefficient of the second pixel value is equal to 1, and the weight proportion coefficient of the first pixel value is equal to 0.

[0163] If the first mapping point is not the fingerprint line singular point, the weight proportion coefficient of the first pixel value and the weight proportion coefficient of the second pixel value are both greater than 0.

[0164] Wherein, the fingerprint line singular point is a point whose angle difference between the tangent direction of a fingerprint line and the tangent direction of a fingerprint line adjacent to the fingerprint line is greater than a preset angle.

[0165] Optionally, the fingerprint target image further includes a background area, and the background area is located in a region around the fingerprint area; the fingerprint image processing device further includes a background area image generation module, which is configured to determine a second mapping point of a second target pixel in the fingerprint target image in the fingerprint original image, the second target pixel is a pixel in the background area, calculate third distances between a preset number of second initial pixels around the second mapping point and the second mapping point respectively, and calculate a pixel value of the second target pixel according to pixel values of the second initial pixels and the third distances; and generate a background area image of the fingerprint target image according to the pixel value of each second target pixel in the fingerprint target image.

[0166] The embodiment of the application further provides a storage medium, the storage medium stores computer instructions, and the computer instructions are used for enabling a processor to implement the fingerprint image processing method in any of the above embodiments when the processor executes the computer instructions. The same technical effects are achieved, and details are not repeated here.

[0167] The embodiment of the application further provides an electronic device, the electronic device includes:

[0168] at least one processor; and

[0169] a memory connected with the at least one processor in communication; wherein,

[0170] The memory stores a computer program which can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the fingerprint image processing method in any of the above embodiments. The same technical effects are achieved, and details are not repeated here.

[0171] Note that the above merely describes preferred embodiments of the present application and the principles of the technology applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, modifications and substitutions can be made without departing from the scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method of processing a fingerprint image, characterized by, The method comprises the following steps: obtaining a fingerprint original image, wherein the fingerprint original image is used to obtain a fingerprint target image, and the fingerprint target image and the fingerprint original image are images with different resolutions; determining a first mapping point of a first target pixel in the fingerprint target image in the fingerprint original image, wherein the fingerprint target image comprises a fingerprint region, and the first target pixel is a pixel in the fingerprint region; the first mapping point of the first target pixel in the fingerprint original image is a pixel or a sub-pixel in the fingerprint original image; determining a target tangent line of the first mapping point in the fingerprint original image, and determining a first weight of a preset number of first initial pixels around the first mapping point according to the target tangent line; the first weight of each first initial pixel around the first mapping point with respect to the target tangent line is a direction weight of each first initial pixel around the first mapping point with respect to a direction of a ridge line; the step of determining the first weight of the preset number of first initial pixels around the first mapping point according to the target tangent line comprises the following steps: wherein, is a first weight, is a first distance of the first initial pixel in the fingerprint raw image relative to the target tangent line; is a coefficient ranging from -1.5 ~ -0.5; calculating a first distance of each first initial pixel to the target tangent line; and determining a first weight of each first initial pixel according to the first distance of each first initial pixel to the target tangent line, wherein the first distance and the first weight are in a negative correlation; wherein the step of determining the first weight of each first initial pixel according to the first distance of each first initial pixel to the target tangent line is based on the following determination: calculating a first pixel value of the first target pixel according to pixel values of each first initial pixel and the first weight of each first initial pixel; the step of calculating the first pixel value of the first target pixel according to the pixel values of each first initial pixel and the first weight of each first initial pixel comprises the following steps: normalizing the first weight; and performing convolution on the first initial pixels around the first mapping point after the first weight is normalized to obtain the first pixel value of the first target pixel; generating a fingerprint region image of the fingerprint target image according to the first pixel value of each first target pixel in the fingerprint target image; before the step of determining the pixel value of the first target pixel according to the first pixel value, the method further comprises the following steps: calculating a second distance between each first initial pixel and the first mapping point, and calculating a second pixel value of the first target pixel according to the pixel value of each first initial pixel and the second distance; the step of generating the fingerprint region image of the fingerprint target image according to the first pixel value of each first target pixel in the fingerprint target image comprises the following steps: determining the pixel value of the first target pixel according to the first pixel value of the first target pixel, the second pixel value of the first target pixel, and a weight proportion coefficient of each; generating the fingerprint region image according to the pixel value of each first target pixel in the fingerprint target image; if the first mapping point is a singular point of a ridge line, the weight proportion coefficient of the second pixel value is equal to 1, and the weight proportion coefficient of the first pixel value is equal to 0. If the first mapping point is not the ridge line singular point, the weight proportion coefficient of the first pixel value and the weight proportion coefficient of the second pixel value are both values greater than 0; Wherein, the angle difference between the fingerprint line tangent direction of the ridge line singular point and the fingerprint line tangent direction of the adjacent fingerprint pixel is greater than a preset angle.

2. The method according to claim 1, wherein The first mapping point is a point on the fingerprint ridge line or the fingerprint valley line of the fingerprint original image; The method further comprises: If the first mapping point is a pixel in the fingerprint original image, the tangent line of the first mapping point on the fingerprint ridge line or the fingerprint valley line is determined as the target tangent line; If the first mapping point is a sub-pixel in the fingerprint original image, the pixel closest to the first mapping point on the fingerprint original image is determined, and the tangent line of the pixel closest to the first mapping point on the fingerprint ridge line or the fingerprint valley line is determined as the target tangent line.

3. The method of claim 1, wherein, The first weight of each first initial pixel is determined according to the first distance of each first initial pixel to the target tangent line, comprising: In the case that the first distance of the first initial pixel to the target tangent line is less than or equal to a preset distance, the first weight of the first initial pixel is calculated according to a preset weight calculation formula and the first distance of the first initial pixel to the target tangent line; In the case that the first distance of the first initial pixel to the target tangent line is greater than a preset distance, a preset weight value is determined as the first weight of the first initial pixel.

4. The method of claim 1, wherein, The pixel value of the first target pixel is determined based on the following formula: ； Wherein, F(x, y) is the pixel value of the first target pixel (x, y); G1 is the first pixel value; G2 is the second pixel value; r1 is the weight proportion coefficient of the first pixel value, and r2 is the weight proportion coefficient of the second pixel value; r1 = 1-r2, and the range of r2 includes [0, 1].

5. The method of claim 1, wherein, The fingerprint target image further comprises a background region, the background region is located in a region around the fingerprint region; the method further comprises: Determining a second mapping point of a second target pixel in the fingerprint target image in the fingerprint original image; the second target pixel is a pixel in the background region; Respectively calculating a third distance between a preset number of second initial pixels around the second mapping point and the second mapping point, and calculating a pixel value of the second target pixel according to a pixel value of each second initial pixel and the third distance; Generating a background region image of the fingerprint target image according to the pixel value of each second target pixel in the fingerprint target image.

6. A fingerprint image processing apparatus characterized by comprising: A device for performing the fingerprint image processing method of any one of claims 1-5, comprising: An original image acquisition module, configured to acquire a fingerprint original image, the fingerprint original image being used to obtain a fingerprint target image, the fingerprint target image and the fingerprint original image being images with different resolutions; An original image acquisition module, configured to acquire a fingerprint original image, the fingerprint original image being used to obtain a fingerprint target image, the fingerprint target image and the fingerprint original image being images with different resolutions; The mapping point determination module is configured to determine a first mapping point of a first target pixel in the fingerprint target image in the fingerprint original image; the fingerprint target image comprises a fingerprint region, and the first target pixel is a pixel in the fingerprint region; The first weight determination module is configured to determine a target tangent line of the first mapping point in the fingerprint original image, and determine first weights of a preset number of first initial pixels around the first mapping point according to the target tangent line; The first pixel value calculation module is configured to calculate a first pixel value of the first target pixel according to pixel values of the first initial pixels and the first weights of the first initial pixels; The fingerprint target image generation module is configured to generate a fingerprint region image of the fingerprint target image according to the first pixel values of the first target pixels in the fingerprint target image.

7. A storage medium, characterized by The storage medium stores computer instructions, and the computer instructions are used to enable the processor to implement the fingerprint image processing method in any one of claims 1-5 when executed.

8. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the fingerprint image processing method in any one of claims 1-5.

Images