Palm vein image processing method and related device

Abstract

The invention discloses a palm vein image processing method and a related device, and the method comprises the steps: firstly determining a plurality of finger sutures of a target palm vein image, and then determining a region of interest of the target palm vein image according to the plurality of finger sutures and an inscribed circle of the palm vein image, the finger suture line can represent the adjacent position relation between the two fingers of the palm in the closed state, so that compared with the existing palm vein image recognition technology which only can recognize the palm vein which is completely opened and is in a fixed posture, the palm vein image recognition method has the advantages that the recognition efficiency is improved; according to the method, the region of interest can be accurately positioned through the position relation between the finger seams and the inscribed circle in the palm vein image, so that the accuracy of processing the palm vein image with the palm in the closed state is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of biometric information recognition, and in particular to a palm vein image processing method and related devices. Background Art

[0002] Most of the existing palm vein region of interest (ROI) extraction technologies require users to adopt a fixed posture with their palms fully open before extracting the ROI for registration and recognition. When the user's palm is closed, such ROI extraction methods will lose their effect and the palm vein recognition effect will be poor. Summary of the invention

[0003] The present application provides a palm vein image processing method and related devices, which accurately locate the region of interest through the positional relationship between the inscribed circle and multiple finger seam lines in the palm vein image, realize the palm vein image processing function, and effectively improve the accuracy of processing the palm vein image when the palm is in a closed state.

[0004] In a first aspect, the present application provides a method for processing a palm vein image, comprising: determining multiple finger seam lines of a target palm vein image, a single finger seam line being used to characterize the adjacent positional relationship between two fingers of a palm in a closed state; and determining a region of interest of the target palm vein image based on the multiple finger seam lines and an inscribed circle of the palm vein image.

[0005] In a second aspect, the present application provides a palm vein image processing device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any one of the methods described in the first aspect above.

[0006] In a third aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program or instructions, and when the computer program or instructions are executed by a processor, the steps of the method described in any one of the first aspects above are implemented.

[0007] In a fourth aspect, the present application provides a smart lock, comprising a palm vein image processing device as described in the second aspect.

[0008] In a fifth aspect, the present application provides a vehicle comprising a smart lock as described in the fourth aspect.

[0009] It can be seen that in the embodiment of the present application, a plurality of finger seams of the target palm vein image are first determined, and then the region of interest of the target palm vein image is determined according to the plurality of finger seams and the inscribed circle of the palm vein image. Since the finger seams can characterize the adjacent positional relationship between two fingers of a palm in a closed state, compared with the existing palm vein image recognition technology that can only recognize palm veins in fully open and fixed postures, the present application can accurately locate the region of interest through the positional relationship between the plurality of finger seams and the inscribed circle in the palm vein image, thereby effectively improving the accuracy of processing the palm vein image of a palm in a closed state. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0011] Figure 1 A schematic diagram of a palm vein image processing device provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of a process of processing a palm vein image provided in an embodiment of the present application;

[0013] Figure 3 A schematic diagram of palm contour extraction from a palm vein image provided in an embodiment of the present application;

[0014] Figure 4 A schematic diagram of a method for solving an inscribed circle provided in an embodiment of the present application;

[0015] Figure 5 A schematic diagram of palm rotation center and angle calculation provided in an embodiment of the present application;

[0016] Figure 6 A schematic diagram of the binarization of a local area of ​​a palm provided in an embodiment of the present application;

[0017] Figure 7 A schematic diagram of the classification of finger seams provided in an embodiment of the present application;

[0018] Figure 8 Another schematic diagram of finger suture classification provided in an embodiment of the present application;

[0019] Fig. 9 A schematic diagram of the root points of finger joints provided in an embodiment of the present application;

[0020] Fig.10 A schematic diagram of the ROI interception area provided in an embodiment of the present application;

[0021] Fig.11 A schematic flow chart of another palm vein image processing method provided in an embodiment of the present application;

[0022] Fig.12 A block diagram of the functional units of a palm vein image processing device provided in an embodiment of the present application;

[0023] Fig.13 A schematic diagram of the structure of a palm vein image processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0026] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] In the embodiments of the present application, "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent the following three situations: A exists alone; A and B exist at the same time; B exists alone. Among them, A and B can be singular or plural.

[0028] In the embodiment of the present application, the symbol " / " can indicate that the objects associated with each other are in an "or" relationship. In addition, the symbol " / " can also indicate a division sign, that is, performing a division operation. For example, A / B can indicate A divided by B.

[0029] In the embodiments of the present application, "at least one item" or similar expressions refer to any combination of these items, including any combination of single items or plural items, and refer to one or more, and multiple refers to two or more. For example, at least one item of a, b, or c can represent the following seven situations: a, b, c, a and b, a and c, b and c, a, b, and c. Among them, each of a, b, and c can be an element or a set containing one or more elements.

[0030] In the embodiments of the present application, "equal to" can be used in conjunction with greater than, and is applicable to the technical solution adopted when greater than, and can also be used in conjunction with less than, and is applicable to the technical solution adopted when less than. When equal to is used in conjunction with greater than, it is not used in conjunction with less than; when equal to is used in conjunction with less than, it is not used in conjunction with greater than.

[0031] Palm vein recognition is a biometric recognition technology. Palm veins are the veins in the palm of the hand. Palm vein recognition generally includes four parts: palm vein image acquisition, image preprocessing, palm vein ROI extraction, and palm vein ROI matching. For palm vein recognition technology, the quality of its results directly depends on the accuracy of ROI extraction. Most of the existing palm vein ROI extraction technologies require users to adopt a fixed posture with their palms fully open, and then extract ROI for registration and recognition. When the user's palm is closed, this type of ROI extraction method will lose its effect, and the palm vein recognition effect will be poor.

[0032] The present application provides a method for processing palm vein images in view of the shortcomings of the prior art.

[0033] The execution subject of the palm vein image processing method provided in the present application can be a palm vein image processing device, which can at least realize palm vein image acquisition, image preprocessing, palm vein image feature extraction and palm vein image feature matching in the palm vein recognition process, wherein the image preprocessing mainly includes image scaling, binarization, finding the maximum connected domain and palm contour extraction; palm vein image feature extraction mainly includes obtaining the palm inscribed circle, locating the middle finger tip point, rotating the palm image, adaptive binarization of a specific area, locating the root point of the fingertip and intercepting the ROI. Palm vein image feature matching refers to matching the extracted features with the corresponding palm vein features (i.e., registered palm vein features) extracted and saved in advance.

[0034] The device at least includes a collection end, an image processing end and a database. The collection end can be a palm vein recognition device such as a palm vein scanner, which is mainly composed of an infrared camera and is used to collect palm vein images; the image processing end can be a server or a server cluster, which is used to pre-process the palm vein images collected and sent by the collection end, extract the palm vein ROI, and match the palm vein ROI; the database can be a MySQL database, which is used to store the pre-extracted palm vein ROI.

[0035] like Figure 1 As shown, Figure 1 A schematic diagram of a palm vein image processing device provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the display screen of the processing device 1 prompts the user to raise his hand and place the palm in the palm vein collection point 11 in the air. The palm vein collection point 11 scans the user's palm veins through infrared, and then processes the palm vein image through the processing device 1. The collected palm vein image is compared with the pre-stored palm vein image to authenticate the user's identity, such as clocking in at work, transaction payment and other scenarios.

[0036] Furthermore, the execution entity may also be a system composed of multiple devices, which can at least realize all functions of acquiring palm vein images, preprocessing the acquired palm vein images, extracting palm vein features from the preprocessed palm vein images, and matching the extracted palm vein features with the corresponding palm vein features (i.e., registered palm vein features) extracted and saved in advance.

[0037] See also Figure 2 , Figure 2 A schematic flow chart of a palm vein image processing method provided in an embodiment of the present application includes the following steps:

[0038] Step 201, determining a plurality of finger seam lines of a target palm vein image.

[0039] Among them, a single finger seam line is used to characterize the adjacent position relationship between two fingers of the palm in a closed state.

[0040] The palm vein image includes the fingers, wrist and background area of ​​the user's palm. The palm vein image is acquired by the acquisition end of the palm vein image processing device, or it can be acquired by other devices and then sent to the palm vein image processing device. For example, it can be acquired by an infrared camera through non-contact infrared scanning.

[0041] Step 202: determining a region of interest of the target palm vein image according to the plurality of finger seam lines and the inscribed circle of the palm vein image.

[0042] The region of interest, or ROI, refers to an area to be processed that is outlined in the palm vein image in the form of a box, circle, ellipse, irregular polygon, etc.

[0043] In a possible example, before determining multiple finger seam lines of the target palm vein image, the method also includes: acquiring a palm contour line based on the palm vein image; determining the center of the inscribed circle; determining the tip of the middle finger based on the distance between the center of the inscribed circle and a point on the palm contour line, the tip of the middle finger being the point on the palm contour line corresponding to the maximum value of the distance; rotating the palm vein image with the center of the inscribed circle as the rotation center based on the positional relationship between the center of the inscribed circle and the tip of the middle finger.

[0044] Wherein, obtaining the palm contour line according to the palm vein image includes the following steps: Figure 3 , Figure 3 A schematic diagram of palm contour extraction from a palm vein image provided in an embodiment of the present application is shown in FIG. Figure 3 As shown: First, the acquired palm vein image is scaled, for example, the original image of the palm vein image ( Figure 3 (a) Scaling from 640 pixels * 480 pixels to 160 pixels * 120 pixels ( Figure 3 b); then perform a binarization operation, set the pixel value with a gray value greater than the segmentation threshold to 255, and set the pixel value with a gray value less than the segmentation threshold to 0, and obtain Figure 3 In c, the segmentation threshold can be determined by the Otsu algorithm; then the maximum connected domain is obtained to filter out the brighter background and retain only the palm part. Figure 3 Finally, the outermost contour of the palm is extracted to obtain Figure 3 The palm contour in e, where the outermost contour contains the inner contour, so the outer contour is detected and all contour points are stored. Under this method, two consecutive contour points are either horizontally adjacent, vertically adjacent, or diagonally adjacent.

[0045] Among them, determining the center of the inscribed circle includes: calculating the first center of the palm vein image, the first center of the palm vein image being the center of mass of the palm vein image; performing an inscribed circle solving operation on the first center of the circle, until determining that the second center of the circle obtained is the center of the inscribed circle after a preset number of executions; the inscribed circle solving operation includes the following steps: sampling in a square area centered on the first center of the circle; calculating the shortest distance from a point in the square area to the palm contour line; selecting a point corresponding to the maximum value from all the shortest distances as the second center of the circle; adding 1 to the number of executions; judging whether the number of executions reaches the preset number of times; if so, determining that the second center of the circle is the center of the inscribed circle, and determining the maximum value of the shortest distance as the radius of the inscribed circle; if not, determining the second center of the circle as the first center of the circle, resetting the size of the square area, and performing the next inscribed circle solving operation.

[0046] Among them, the centroid of the palm area is the average value of the horizontal and vertical coordinates of all pixel points in the palm contour line. Specifically, for each point on the palm contour, its horizontal and vertical coordinates are accumulated respectively to obtain two cumulative sums, namely, the sum of the horizontal coordinates sum_x and the sum of the vertical coordinates sum_y; the number of contour points is counted to obtain the total number of contour points count, then the horizontal coordinate of the centroid is centroid_x=sum_x / count, and the vertical coordinate of the centroid is centroid_y=sum_y / count.

[0047] The inscribed circle solving operations include: Figure 4 , Figure 4 A schematic diagram of a method for solving an inscribed circle provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, sampling is performed in a 36*36 square area centered on the centroid A, with one point sampled for every 6 pixels, for a total of 7*7=49 points. Figure 4 For each of the 49 white dots, calculate the shortest distance to the palm contour line, and get 49 shortest distances. Select the point with the largest shortest distance from the 49 shortest distances as the second circle center. Figure 4 The shortest distance corresponding to the second circle center is the radius of the inscribed circle. The number of executions is recorded as 1. For example, if the preset number of times is 3, the coordinates of the second circle center are assigned to the first circle center. The square area size is set to 12*12 with the first circle center (point B) as the center. That is, sampling is performed in the 12*12 square area with the first circle center as the center. One point is sampled for every 2 pixels, and a total of 7*7=49 points are sampled. Figure 4The point in the center area of ​​the palm in ii. For each of these 49 points, calculate the shortest distance from it to the palm contour line, and get 49 shortest distances. From the 49 shortest distances, select the point with the largest shortest distance as the second circle center. Figure 4 The number of executions is recorded as 2, and the next inscribed circle solving operation is performed. The square area size is set to 5*5 with the first circle center (point C) as the center, that is, sampling is performed in the 5*5 square area with the first circle center as the center. Figure 4 Calculate the shortest distances from the 5*5=25 points in the center of the palm to the contour line, and get 25 shortest distances. Select the largest point from the 25 shortest distances as the second center. Figure 4 In iii, point D is used, and the number of executions is recorded as 3. Then the center of the second circle (point D) is the center of the inscribed circle, and the shortest distance from the second circle center to the palm contour is the radius of the inscribed circle. Figure 4 Circle 1 in iii is the largest inscribed circle obtained.

[0048] The tip of the middle finger is the pixel point with the largest distance from the center point D of the largest inscribed circle to the palm contour line. Figure 4 Point E in iii.

[0049] Furthermore, in order to reduce the amount of calculation and the calculation time, a sampling operation may be performed, and the points on the contour line may be taken as one every two or four or other values.

[0050] In a possible example, rotating the palm vein image according to the positional relationship between the center of the inscribed circle and the tip of the middle finger and with the center of the inscribed circle as the rotation center includes: determining a second rotation angle according to the coordinates of the center of the inscribed circle and the coordinates of the tip of the middle finger, the second rotation angle being the angle between the straight line where the two coordinates are located and the positive direction of the y-axis; determining a rotation direction according to the magnitude relationship between the abscissa of the center of the inscribed circle and the abscissa of the tip of the middle finger, the rotation direction including a clockwise direction or a counterclockwise direction; when the abscissa of the center of the inscribed circle is greater than the abscissa of the tip of the middle finger, the rotation direction is the clockwise direction; when the abscissa of the center of the inscribed circle is less than the abscissa of the tip of the middle finger, the rotation direction is the counterclockwise direction; rotating the palm vein image according to the second rotation angle, the rotation direction and with the center of the inscribed circle as the rotation center.

[0051] The rotation of the palm vein image requires three factors: the rotation center, the rotation direction, and the rotation angle. The rotation center is the center of the inscribed circle. The rotation angle can be determined by the slope of the straight line determined by the center of the inscribed circle and the tip of the middle finger, and the magnitude relationship between the horizontal and vertical coordinates of the two points. For example, please refer to Figure 5 , Figure 5The palm rotation center and angle calculation diagram provided in the embodiment of the present application is as follows: Figure 5 As shown, Figure 5 The coordinates of the center of the circle D and the tip of the middle finger E are (50,50) and (100,0) respectively. The slope of the straight line determined by these two points is -1. According to the slope, the palm may have two orientations, namely, the palm pointing to the lower right and the palm pointing to the upper left. According to the coordinate size relationship between the fingertip and the center of the circle, the palm is pointing to the lower right. The palm vein image is rotated 135° counterclockwise to the vertical direction to obtain Figure 5 In ii.

[0052] Furthermore, the palm vein image can be rotated using a rotation matrix. Assuming that the image is to be rotated 0 degrees counterclockwise, the following rotation matrix M can be used:

[0053]

[0054] α=scale·coS(angle)

[0055] β=scale·sin(angle)

[0056] Among them, angle is the rotation angle θ, center is the rotation center, and scale is the scaling ratio.

[0057] For the coordinates (x, y) of each pixel on the palm vein image, the rotation is completed by the following formula:

[0058] dst(x, y) = src(M 11 x+M 12 y+M 13 , M 21 x+M 22 y+M 23 )

[0059] Among them, src is the original image, dst is the output image after rotation, M 11 、M 12 、M 13 、M 21 、M 22 、M 23 is the corresponding element in the rotation matrix M.

[0060] It can be seen that in this example, by calculating the geometric relationship between the center of the maximum inscribed circle of the palm and the tip of the middle finger, palms in different orientations can be rotated to a uniform angle, and there is no need to collect the user's palm vein image at a fixed angle and posture.

[0061] In a possible example, determining the region of interest of the target palm vein image based on the multiple finger seam lines and the inscribed circle of the palm vein image includes: obtaining multiple finger seam root points based on the multiple finger seam lines and the center of the inscribed circle; and determining the region of interest based on the multiple finger seam root points and the radius of the inscribed circle.

[0062] It can be seen that in this example, the root point of the finger joint is found through the finger joint line, and the region of interest is determined based on the finger joint root point and the inscribed circle, which solves the problem of extracting the region of interest when it is difficult to locate the finger joint point when the palm is closed.

[0063] In a possible example, determining multiple finger joint lines of the target palm vein image includes: obtaining multiple finger joint points based on the palm vein image; obtaining the horizontal coordinate of each finger joint point, and performing histogram statistics on the horizontal coordinate to determine the number of finger joint points with the same horizontal coordinate; determining the horizontal coordinate with the number of finger joint points greater than the preset threshold as the first horizontal coordinate; diffusing a preset distance to the left and to the right on the basis of the first horizontal coordinate to determine the finger joint points whose number of finger joint points is not zero among the multiple finger joint points; determining a line segment composed of the finger joint points whose number of finger joint points is not zero and the finger joint points corresponding to the first horizontal coordinate as the first finger joint line.

[0064] The palm vein image is used to obtain multiple finger joint points, including the following steps: Figure 6 , Figure 6 Schematic diagram of the binarization of the local area of ​​the palm provided in the embodiment of the present application, see Figure 6 In i, after rotating the palm to a uniform direction, a rectangular area F can be intercepted just above the center of the inscribed circle for local adaptive binarization. In the intercepted rectangular area F, the area outside the palm contour is removed, and the local mean binarization operation is performed, that is, each pixel point in the rectangular area F is traversed, and a local small square is constructed with it as the center and 60% of the inscribed circle radius as the side length. The average grayscale value of all pixels in the square area is calculated, and the finger joint points whose grayscale value is much lower than the average grayscale value of the local area are retained, such as Figure 6 As shown in ii.

[0065] Furthermore, the width of the rectangle may be the diameter of the inscribed circle, and the height of the rectangle may be 60% of the distance from the tip of the middle finger to the center of the inscribed circle.

[0066] Furthermore, the average grayscale value of each small square area can be calculated by a two-dimensional prefix sum algorithm to reduce the calculation time of the algorithm.

[0067] Furthermore, 80% of the average grayscale value in the square area can be taken as the threshold for binarization. If the grayscale value of the center point of the small square is greater than the threshold, the grayscale value of the center point is set to 255. Conversely, if the grayscale value of the center point of the small square is less than the threshold, the grayscale value of the center point is set to 0.

[0068] After finding the finger gap points, a histogram of the horizontal coordinates of all the finger gap points is made, and the highest horizontal coordinate in the histogram is found, that is, the horizontal coordinate with the most finger gap points, which is recorded as the first horizontal coordinate. Based on the first horizontal coordinate, the histogram is diffused to the left and right respectively, and the horizontal coordinates of the finger gap points in the histogram whose values ​​are not 0 are determined. They are classified as the same finger gap line with the first horizontal coordinate, and each finger gap line is given a label label. When the X coordinate of the finger gap point value 0 in the histogram is encountered during the diffusion process, the diffusion stops.

[0069] Furthermore, the distance between the newly found first coordinate and the first coordinate of each previously classified label is calculated. If the distance to the nearest first coordinate is less than 25% of the radius of the inscribed circle and the histogram value of the current first coordinate is less than 30% of the histogram value of the nearest first coordinate, the first coordinate is classified as the label to which the nearest first coordinate belongs. Repeat the above process until all finger joint points have a label and each label has a first coordinate.

[0070] For example, see Figure 7 , Figure 7 The schematic diagram of finger seam classification provided in the embodiment of the present application is as follows: Figure 7 As shown, the finger seam points in the rectangular frame are classified according to the above method to obtain four finger seam lines, which are marked as label1, label2, label3, and label4 respectively.

[0071] In one possible example, the finger is wearing an accessory, and the diffusing to the left and right on the basis of the first horizontal coordinate to find the finger points whose horizontal coordinates are not 0 among the multiple finger points includes: diffusing to the left and right by a preset maximum distance on the basis of the first horizontal coordinate to find the finger points whose horizontal coordinates are not 0 among the multiple finger points.

[0072] For example, Figure 8 As shown in , when a ring is worn on the ring finger, the maximum distance of diffusion to the left and right based on the first coordinate is limited, so that the two finger seams are forcibly cut off before being connected by the ring, that is, the finger seam points on the ring are divided into two nearby finger seam lines to prevent the algorithm from judging the two finger seam lines together with the ring as one finger seam line. Figure 8As shown, for the finger seam lines label1 and label2, label1 is restricted to diffuse to the right to a maximum distance f based on its first coordinate, and label2 is restricted to diffuse to the left to a maximum distance f based on its first coordinate, forcibly cutting off the ring to connect the two finger seam lines.

[0073] Further, the maximum distance f may be 30% of the inscribed circle radius.

[0074] It can be seen that in this example, the algorithm is partially adjusted for the case where there are accessories on the fingers. The maximum distance of diffusion to the left and right based on the first coordinate is limited, so that two complete finger seam lines can be obtained, and the classification of the finger seam lines when there are no rings will not be affected.

[0075] In a possible example, obtaining multiple finger joint root points based on the multiple finger joint lines and the center of the inscribed circle includes: performing the following steps for each finger joint line: calculating the first horizontal coordinate of the first finger joint line currently being processed, the Manhattan distance between the center of the inscribed circle and each finger joint point in the first finger joint line, the first horizontal coordinate refers to a horizontal coordinate in which the number of finger joint points with the same horizontal coordinate on the first finger joint line is greater than a preset threshold; determining the finger joint point corresponding to the smallest Manhattan distance as the finger joint root point.

[0076] For example, see Fig. 9 , Fig. 9 The schematic diagram of the finger root point provided in the embodiment of the present application is as follows: Fig. 9 As shown, for label1, for each finger joint point on label1, calculate the Manhattan distance between the finger joint point and the first horizontal coordinate of label1 and the center of the inscribed circle. The formula is as follows: Manhattan distance = 1*abs(finger joint point.X-inscribed circle center.X)+0.8*abs(finger joint point.Y-inscribed circle center.Y)+1.5*abs(finger joint point.X-first horizontal coordinate of label1), find the finger joint point with the smallest Manhattan distance under label1, denoted as min_pt, and min_pt is the root point of the finger joint under label1, see Fig. 9 Do the same process as above for the finger joint points on label2, label3, and label4, and get Fig. 9 The remaining G2, G3, and G4 finger root points.

[0077] Among them, finger point.X is the horizontal coordinate of the finger point, finger point.Y is the vertical coordinate of the finger point, inscribed circle center.X is the horizontal coordinate of the center of the inscribed circle, and inscribed circle center.Y is the vertical coordinate of the center of the inscribed circle.

[0078] Among them, 1, 0.8, and 1.5 are the weights of each distance.

[0079] It can be seen that in this example, the weighted Manhattan distance can accurately find the lowest finger root point in the finger seam line, while filtering out the influence of wearing a ring and other conditions on finding the finger root point, thereby improving the accuracy of finding the finger root point.

[0080] In a possible example, after determining that the finger point corresponding to the smallest Manhattan distance is the finger root point, the method further includes: obtaining the finger point corresponding to the largest Manhattan distance in the first finger seam line, calculating the proportion of finger points in a preset area centered on the finger point; detecting that the proportion is greater than the preset proportion; and deleting the finger root point of the first finger seam line.

[0081] Among them, find the finger point with the largest Manhattan distance under each label, recorded as max_pt, and the proportion of black points in the square area with the maximum inscribed circle radius of 60% as the side length, with max_pt as the center, such as Fig. 9 In the middle square area, if the proportion of black dots in the square area is greater than 30%, it is judged as the palm contour line rather than the finger seam line, and the min_pt of the label to which max_pt belongs is filtered out, that is, the min_pt under this label is not the root point of the finger seam.

[0082] It can be seen that in this example, by filtering out the finger root points whose black dot ratio exceeds a specific threshold, it is possible to eliminate the situation where the palm contour line is mistakenly identified as the finger joint line, thereby improving the accuracy of finger root point identification.

[0083] In a possible example, determining the region of interest based on the multiple finger root points and the radius of the inscribed circle includes: determining a first finger root point and a second finger root point from the multiple finger root points, the first finger root point being the finger root point between the index finger and the middle finger, and the second finger root point being the finger root point between the ring finger and the little finger; determining the midpoint of the first finger root point and the second finger root point; and determining the region of interest based on the coordinates of the midpoint and the radius of the inscribed circle.

[0084] Among them, the multiple finger root points include the finger root point between the thumb and the index finger, the finger root point between the index finger and the middle finger, the finger root point between the middle finger and the ring finger, and the finger root point between the ring finger and the little finger.

[0085] Among them, the method for determining the first finger root point and the second finger root point includes the following steps: determining three finger root points that meet preset conditions from the multiple finger root points, and the preset conditions include at least one restriction on the ratio relationship between the perimeter, maximum angle, and side length of the triangle formed by the three finger root points; determining the two finger root points with the farthest distance from each other among the three finger root points as the first finger root point and the second finger root point.

[0086] Specifically, the preset condition is to find three points with the smallest perimeter of the triangle among the four finger root points, and the maximum angle of the triangle is greater than 110 degrees, the longest side of the triangle is longer than 65% of the maximum inscribed circle radius, and the ratio of the second longest side to the shortest side should be in the interval (1,2).

[0087] It can be seen that in this example, by making certain restrictions on the triangle formed by three points, the robustness of the algorithm can be enhanced.

[0088] Among them, see Fig.10 , Fig.10 A schematic diagram of the ROI interception area provided in the embodiment of the present application is shown in FIG. Fig.10 As shown, the midpoint M between the first finger root point G1 and the second finger root point G3 is recorded as middle_pt. The region of interest is determined according to the coordinates of the midpoint M (middle_pt.x, middle_pt.y) and the radius radius of the inscribed circle: a square area is intercepted with (middle_pt.x, middle_pt.y+0.8radius) as the center and 1.2*radius as the side length. This area is the ROI area where features need to be extracted.

[0089] In a possible example, before determining the midpoint of the first finger root point and the second finger root point, the method also includes: determining a first rotation angle of the palm vein image based on the coordinates of the first finger root point and the second finger root point; and rotating the palm vein image according to the first rotation angle.

[0090] Among them, the slope of the first finger root point and the second finger root point can be used to calculate the rotation angle required to rotate the line connecting these two points to the horizontal direction, and then the image is rotated.

[0091] It can be seen that in this example, by rotating the palm vein image in the horizontal direction, the features of the palm vein can be made more obvious and easier to extract.

[0092] See also Fig.11 , Fig.11 A schematic diagram of a process flow of another palm vein image processing method provided in an embodiment of the present application is shown in FIG. Fig.11 As shown, the above method comprises the following steps:

[0093] Step 1101: palm vein image acquisition.

[0094] The palm vein image is acquired by the acquisition end of the palm vein image processing device, or it can be acquired by other devices and then sent to the palm vein image processing device. For example, it can be acquired by an infrared camera through non-contact infrared scanning.

[0095] Step 1102: preprocessing of palm vein image.

[0096] Among them, palm vein image preprocessing mainly includes image scaling, binarization, finding the maximum connected domain and palm contour extraction.

[0097] Step 1103, obtaining the inscribed circle of the palm.

[0098] The palm inscribed circle is solved by the inscribed circle solving operation provided in the above embodiment.

[0099] Step 1104, positioning the tip of the middle finger.

[0100] The tip of the middle finger is the pixel point with the largest distance from the center of the largest inscribed circle to the palm contour line.

[0101] Step 1105: Rotate the palm vein image.

[0102] Step 1106: Adaptively binarize the specific area.

[0103] Step 1107, locate the finger joint and heel point.

[0104] Step 1108, capture the ROI.

[0105] It should be noted that the various steps in this embodiment have been described in detail in the above embodiments and will not be discussed in detail again.

[0106] It can be seen that in the embodiment of the present application, a plurality of finger seams of the target palm vein image are first determined, and then the region of interest of the target palm vein image is determined according to the plurality of finger seams and the inscribed circle of the palm vein image. Since the finger seams can characterize the adjacent positional relationship between two fingers of a palm in a closed state, compared with the existing palm vein image recognition technology that can only recognize palm veins in fully open and fixed postures, the present application can accurately locate the region of interest through the positional relationship between the plurality of finger seams and the inscribed circle in the palm vein image, thereby effectively improving the accuracy of processing the palm vein image of a palm in a closed state.

[0107] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to realize the above functions, the server includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0108] The embodiment of the present application can divide the server into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of a software program module. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical functional division, and there may be other division methods in actual implementation.

[0109] In the case of integrated units, see Fig.12 , Fig.12 This is a functional unit composition block diagram of a palm vein image processing device provided in an embodiment of the present application. The palm vein image processing device 12 includes a processing unit.

[0110] The processing unit may be a module unit for processing data and the like.

[0111] Optionally, the palm vein image processing device 12 further includes a receiving unit, and the receiving unit may be a module unit for acquiring data and the like.

[0112] Optionally, the palm vein image processing device 12 further includes a sending unit, which may be a module unit for sending data.

[0113] Optionally, the palm vein image processing device 12 further includes a storage unit for storing computer program codes or instructions executed by the palm vein image processing device 12. For example, the storage unit may be a memory.

[0114] It should be noted that the processing unit can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processing unit can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0115] Optionally, the palm vein image processing device 12 may be a chip or a chip module.

[0116] In specific implementation, the palm vein image processing device 12 is used to execute the steps executed by the chip / chip module / server etc. in the above method embodiment.

[0117] The following is a detailed description:

[0118] A processing unit is used to determine a plurality of finger seam lines of a target palm vein image, wherein a single finger seam line is used to characterize the adjacent position relationship between two fingers of a palm in a closed state; and determine a region of interest of the target palm vein image according to the plurality of finger seam lines and an inscribed circle of the palm vein image.

[0119] It can be seen that in the embodiment of the present application, a plurality of finger seams of the target palm vein image are first determined, and then the region of interest of the target palm vein image is determined according to the plurality of finger seams and the inscribed circle of the palm vein image. Since the finger seams can characterize the adjacent positional relationship between two fingers of a palm in a closed state, compared with the existing palm vein image recognition technology that can only recognize palm veins in fully open and fixed postures, the present application can accurately locate the region of interest through the positional relationship between the plurality of finger seams and the inscribed circle in the palm vein image, thereby effectively improving the accuracy of processing the palm vein image of a palm in a closed state.

[0120] In one possible example, in terms of determining the region of interest of the target palm vein image based on the multiple finger seam lines and the inscribed circle of the palm vein image, the processing unit is further used to: obtain multiple finger seam root points based on the multiple finger seam lines and the center of the inscribed circle; and determine the region of interest based on the multiple finger seam root points and the radius of the inscribed circle.

[0121] In one possible example, in terms of obtaining multiple finger joint root points based on the multiple finger joint lines and the center of the inscribed circle, the processing unit is further used to: perform the following steps for each finger joint line: calculate the first horizontal coordinate of the first finger joint line currently being processed, the Manhattan distance between the center of the inscribed circle and each finger joint point in the first finger joint line, the first horizontal coordinate refers to a horizontal coordinate on the first finger joint line where the number of finger joint points with the same horizontal coordinate is greater than a preset threshold; determine the finger joint point corresponding to the smallest Manhattan distance as the finger joint root point; the first finger joint line is any finger joint line.

[0122] In a possible example, after the processing unit determines that the finger point corresponding to the smallest Manhattan distance is the finger root point, the processing unit is also used to: obtain the finger point corresponding to the largest Manhattan distance in the first finger seam line, and calculate the proportion of the finger points in a preset area centered on the finger point; if it is detected that the proportion is greater than the preset proportion; then delete the finger root point of the first finger seam line.

[0123] In one possible example, in terms of determining the region of interest based on the multiple finger root points and the radius of the inscribed circle, the processing unit is further used to: determine a first finger root point and a second finger root point from the multiple finger root points, the first finger root point being the finger root point between the index finger and the middle finger, and the second finger root point being the finger root point between the ring finger and the little finger; determine the midpoint of the first finger root point and the second finger root point; and determine the region of interest based on the coordinates of the midpoint and the radius of the inscribed circle.

[0124] In a possible example, before the processing unit determines the midpoint of the first finger root point and the second finger root point, the processing unit is also used to: determine a first rotation angle of the palm vein image based on the coordinates of the first finger root point and the second finger root point; and rotate the palm vein image according to the first rotation angle.

[0125] In one possible example, in terms of determining the first finger root point and the second finger root point from the multiple finger root points, the processing unit is further used to: determine three finger root points that meet preset conditions from the multiple finger root points, and the preset conditions include restrictions on at least one of the ratio relationship between the perimeter, maximum angle, and side length of the triangle formed by the three finger root points; determine the two finger root points that are farthest from each other among the three finger root points as the first finger root point and the second finger root point.

[0126] In one possible example, in terms of determining multiple finger joint lines of the target palm vein image, the processing unit is further used to: obtain multiple finger joint points based on the palm vein image; obtain the horizontal coordinate of each finger joint point, and perform histogram statistics on the horizontal coordinate to determine the number of finger joint points with the same horizontal coordinate; determine the horizontal coordinate whose number of finger joint points is greater than the preset threshold as the first horizontal coordinate; diffuse a preset distance to the left and to the right on the basis of the first horizontal coordinate to determine the finger joint points whose number of finger joint points is not zero among the multiple finger joint points; determine the line segment composed of the finger joint points whose number of finger joint points is not zero and the finger joint points corresponding to the first horizontal coordinate as the first finger joint line.

[0127] In a possible example, before the processing unit determines multiple finger seam lines of the target palm vein image, the processing unit is also used to: obtain a palm contour line based on the palm vein image; determine the center of the inscribed circle; determine the tip of the middle finger based on the distance between the center of the inscribed circle and the point on the palm contour line, the tip of the middle finger being the point on the palm contour line corresponding to the maximum value of the distance; rotate the palm vein image with the center of the inscribed circle as the rotation center based on the positional relationship between the center of the inscribed circle and the tip of the middle finger.

[0128] In a possible example, the processing unit rotates the palm vein image according to the positional relationship between the center of the inscribed circle and the tip of the middle finger, with the center of the inscribed circle as the rotation center, including: determining a second rotation angle according to the coordinates of the center of the inscribed circle and the coordinates of the tip of the middle finger, the second rotation angle being the angle between the straight line where the two coordinates are located and the positive direction of the y-axis; determining a rotation direction according to the magnitude relationship between the abscissa of the center of the inscribed circle and the abscissa of the tip of the middle finger, the rotation direction including a clockwise direction or a counterclockwise direction; when the abscissa of the center of the inscribed circle is greater than the abscissa of the tip of the middle finger, the rotation direction is the clockwise direction; when the abscissa of the center of the inscribed circle is less than the abscissa of the tip of the middle finger, the rotation direction is the counterclockwise direction; rotating the palm vein image according to the second rotation angle, the rotation direction, and with the center of the inscribed circle as the rotation center.

[0129] In a possible example, in determining the center of the inscribed circle, the processing unit is further used to: calculate a first center of the palm vein image, where the first center is the center of mass of the palm vein image; perform an inscribed circle solving operation on the first center until a second center is determined to be the center of the inscribed circle after a preset number of times;

[0130] In terms of the inscribed circle solving operation, the processing unit is also used to: sample within a square area centered on the first circle center; calculate the shortest distance from a point within the square area to the palm contour line; select a point corresponding to a maximum value from all the shortest distances as the second circle center; add 1 to the number of executions; determine whether the number of executions reaches the preset number; if so, determine that the second circle center is the center of the inscribed circle, and determine the maximum value of the shortest distance as the radius of the inscribed circle; if not, determine that the second circle center is the first circle center, reset the size of the square area, and perform the next inscribed circle solving operation.

[0131] See also Fig.13 , Fig.13 A schematic diagram of the structure of a palm vein image processing device provided in an embodiment of the present application is shown in FIG. Fig.13 As shown, the palm vein image processing device 12 may include: a processor 1301, such as a CPU, a network interface 1304, a user interface 1303, a memory 1305, and a communication bus 1302. Among them, the communication bus 1302 is used to realize the connection and communication between these components. The user interface 1303 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1303 may also include a standard wired interface and a wireless interface. The network interface 1304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1305 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1305 may also be a storage device independent of the aforementioned processor 1301.

[0132] Those skilled in the art will understand that Fig.13 The device structure shown in the figure does not constitute a limitation of the device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0133] like Fig.13 As shown, the memory 1305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a computer program for screen status control.

[0134] exist Fig.13In the processing device shown, the network interface 1304 is mainly used to connect to the background server and communicate data with the background server; the user interface 1303 is mainly used to connect to the client (user end) and communicate data with the client; and the processor 1301 can be used to call the computer program for palm vein image processing stored in the memory 1305, and perform the operations in the above-mentioned palm vein image processing method. The method implemented when the computer program for palm vein image processing running on the above-mentioned processor 1301 is executed can refer to the various embodiments of the palm vein image processing method of the present application, and will not be repeated here.

[0135] An embodiment of the present application provides a computer-readable storage medium having a computer program / instruction stored thereon. When the computer program / instruction is executed by a processor, the steps of the method described in any possible embodiment are implemented.

[0136] The present application embodiment provides a smart lock, including: Figure 1 The palm vein image processing device shown is used to implement the steps of the method described in any possible embodiment.

[0137] An embodiment of the present application provides a vehicle, comprising the above-mentioned smart lock, and the smart lock is used to implement the steps of the method described in any possible embodiment.

[0138] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0139] In the several embodiments provided in the present application, it should be understood that the disclosed methods, devices and systems can be implemented in other ways. For example, the device embodiments described above are merely schematic; for example, the division of the unit is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0140] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0141] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0142] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a volatile memory or a non-volatile memory. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synchlink DRAM, SLDRAM) and direct memory bus random access memory (directrambus RAM, DR RAM) and other media that can store program code.

[0143] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present application, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present application.

Claims

1. A palm vein image processing method, characterized in that: include: Determine a plurality of finger seam lines of the target palm vein image, wherein a single finger seam line is used to represent the adjacent position relationship between two fingers of the palm in a closed state; The region of interest of the target palm vein image is determined according to the multiple finger seam lines and the inscribed circle of the palm vein image.

2. The method according to claim 1, characterized in that The determining the region of interest of the target palm vein image according to the multiple finger seam lines and the inscribed circle of the palm vein image comprises: Obtaining a plurality of finger joint root points according to the plurality of finger joint lines and the center of the inscribed circle; The region of interest is determined according to the plurality of finger root points and the radius of the inscribed circle.

3. The method according to claim 2, characterized in that The step of obtaining a plurality of finger joint root points according to the plurality of finger joint lines and the center of the inscribed circle comprises: Follow these steps for each finger seam: Calculate the first horizontal coordinate of the first finger seam line currently being processed, the Manhattan distance between the center of the inscribed circle and each finger seam point in the first finger seam line, wherein the first horizontal coordinate refers to a horizontal coordinate at which the number of finger seam points with the same horizontal coordinate on the first finger seam line is greater than a preset threshold; Determine the finger joint point corresponding to the minimum Manhattan distance as the finger joint root point; the first finger joint line is any finger joint line.

4. The method according to claim 3, characterized in that After determining that the finger joint point corresponding to the minimum Manhattan distance is the finger joint root point, the method further includes: Obtaining a finger seam point corresponding to the largest Manhattan distance in the first finger seam line, and calculating the proportion of finger seam points in a preset area centered on the finger seam point; If it is detected that the ratio is greater than a preset ratio, the root point of the first finger seam line is deleted.

5. The method according to claim 2, characterized in that: The determining of the region of interest according to the plurality of finger gap root points and the radius of the inscribed circle comprises: Determine a first finger joint root point and a second finger joint root point from the plurality of finger joint root points, wherein the first finger joint root point is a finger joint root point between the index finger and the middle finger, and the second finger joint root point is a finger joint root point between the ring finger and the little finger; Determine the midpoint between the first finger gap root point and the second finger gap root point; The region of interest is determined according to the coordinates of the midpoint and the radius of the inscribed circle.

6. The method according to claim 5, characterized in that Before determining the midpoint of the first finger joint root point and the second finger joint root point, the method further includes: Determine a first rotation angle of the palm vein image according to the coordinates of the first finger root point and the second finger root point; The palm vein image is rotated according to the first rotation angle.

7. The method according to claim 5, characterized in that The determining of the first finger joint root point and the second finger joint root point from the plurality of finger joint root points comprises: Determine three finger root points that meet preset conditions from the multiple finger root points, wherein the preset conditions include at least one restriction on the perimeter, maximum angle, and ratio of sides of a triangle formed by the three finger root points; Determine that the two finger joint root points that are farthest from each other among the three finger joint root points are the first finger joint root point and the second finger joint root point.

8. The method according to claim 3, characterized in that The step of determining a plurality of finger seam lines of a target palm vein image includes: Obtaining a plurality of finger joint points according to the palm vein image; Obtaining the horizontal coordinate of each finger joint point, and performing histogram statistics on the horizontal coordinates to determine the number of finger joint points with the same horizontal coordinate; Determine the horizontal coordinate whose number of finger gap points is greater than the preset threshold as the first horizontal coordinate; Diffusion to the left and right by a preset distance based on the first horizontal coordinate to determine the finger gap points whose number among the plurality of finger gap points is not zero; Determine that a line segment formed by the finger joint points whose number is not 0 and the finger joint points corresponding to the first horizontal coordinate is the first finger joint line.

9. The method according to any one of claims 1 to 8, characterized in that: Before determining a plurality of finger seam lines of the target palm vein image, the method further includes: Acquire a palm contour line according to the palm vein image; Determining the center of the inscribed circle; Determine the tip of the middle finger according to the distance between the center of the inscribed circle and the point on the palm contour line, wherein the tip of the middle finger is the point on the palm contour line corresponding to the maximum value of the distance; The palm vein image is rotated with the center of the inscribed circle as the rotation center according to the positional relationship between the center of the inscribed circle and the tip of the middle finger.

10. The method according to claim 9, characterized in that The step of rotating the palm vein image with the center of the inscribed circle as the rotation center according to the positional relationship between the center of the inscribed circle and the tip of the middle finger includes: Determine a second rotation angle according to the coordinates of the center of the inscribed circle and the coordinates of the tip of the middle finger, wherein the second rotation angle is the angle between the straight line where the two coordinates are located and the positive direction of the y-axis; The rotation direction is determined according to the magnitude relationship between the abscissa of the center of the inscribed circle and the abscissa of the tip of the middle finger, and the rotation direction includes a clockwise direction or a counterclockwise direction; when the abscissa of the center of the inscribed circle is greater than the abscissa of the tip of the middle finger, the rotation direction is the clockwise direction; when the abscissa of the center of the inscribed circle is less than the abscissa of the tip of the middle finger, the rotation direction is the counterclockwise direction; The palm vein image is rotated according to the second rotation angle and the rotation direction with the center of the inscribed circle as the rotation center.

11. The method according to claim 9, characterized in that Determining the center of the inscribed circle includes: Calculating a first center of the palm vein image, where the first center is the centroid of the palm vein image; Performing an inscribed circle solving operation on the first circle center until the second circle center obtained after a preset number of times is determined to be the center of the inscribed circle; The inscribed circle solving operation comprises the following steps: Sampling in a square area centered on the first circle center; calculating the shortest distance from a point in the square area to the palm contour line; selecting a point corresponding to the maximum value from all the shortest distances as the second circle center; Increase the number of executions by 1; Determining whether the execution times reaches the preset times; If yes, then determining the second center as the center of the inscribed circle, and determining the maximum value of the shortest distance as the radius of the inscribed circle; If not, the second circle center is determined as the first circle center, the size of the square area is reset, and the next inscribed circle solving operation is performed.

12. A palm vein image processing device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 11.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program or instructions, and when the computer program or instructions are executed by a processor, the steps of the method described in any one of claims 1 to 11 are implemented.

14. A smart lock, characterized in that: The invention comprises the palm vein image processing device as claimed in claim 12.

15. A vehicle, characterized in that: Including the smart lock as described in claim 14.

Images