Palmar vein effective area extraction method, system, medium and electronic device

Abstract

The application provides a palm vein effective area extraction method, system, medium and electronic equipment; the method comprises the following steps: acquiring a first palm image; performing image segmentation on the first palm image to obtain a second palm image; determining two target points according to the second palm image; and extracting a palm vein effective area based on the first palm image and the two target points. The application realizes extraction of the palm vein effective area, can remove image pixels in the palm image except the palm vein effective area, which may be disturbed, thereby realizing extraction of subsequent feature information by using the palm vein effective area, and improving recognition speed and recognition accuracy.

Description

Technical Field

[0001] This application belongs to the field of image processing technology, and relates to palm veins, and in particular to a method, system, medium and electronic device for extracting the effective area of ​​palm veins. Background Technology

[0002] Currently, with the rapid development of information technology and network technology, information security has shown unprecedented importance. Biometric technology, with its unique stability, uniqueness and convenience, is being used more and more widely. Palmprint recognition, as a new and effective biometric technology, has attracted widespread attention from researchers at home and abroad due to its characteristics such as simple sampling, rich image information, high user acceptance, difficulty in forgery and low susceptibility to noise interference.

[0003] Current palmprint recognition is based on an entire palm image. Typically, this palm image contains other potentially interfering image pixels in addition to the effective area of ​​the palm veins. This affects the speed and accuracy of palmprint recognition, leading to a decrease in recognition speed and accuracy. Therefore, there is an urgent need for a method to extract the effective area of ​​the palm veins. Summary of the Invention

[0004] The purpose of this application is to provide a method, system, medium, and electronic device for extracting the effective area of ​​palm veins, in order to solve the problems of low recognition speed and low recognition accuracy of existing palm print recognition technologies.

[0005] In a first aspect, this application provides a method for extracting the effective region of palm veins, the method comprising the following steps: acquiring a first palm image; performing image segmentation on the first palm image to acquire a second palm image; determining two target points based on the second palm image; and extracting the effective region of palm veins based on the first palm image and the two target points.

[0006] In this application, the effective region of the palm vein is extracted based on image segmentation technology. This can remove potentially interfering image pixels from the palm image other than the effective region of the palm vein, thereby enabling the extraction of subsequent feature information using the effective region of the palm vein, thus improving recognition speed and accuracy.

[0007] In one implementation of the first aspect, acquiring the first palm image includes the following steps: acquiring an original palm image; performing grayscale processing on the original palm image to acquire a grayscale palm image; estimating multiple hand joints in the grayscale palm image; the multiple hand joints include at least: a wrist point and a finger root point from the wrist to the middle finger skeleton; and acquiring the first palm image based on the grayscale palm image and the multiple hand joints.

[0008] In this implementation, the hand joints in the grayscale image of the palm are estimated, which makes it easier to obtain the first palm image from the grayscale image of the palm based on the hand joints.

[0009] In one implementation of the first aspect, obtaining the first palm image based on the palm grayscale image and multiple hand joint points includes the following steps: determining whether the palm orientation in the palm grayscale image is positive based on the wrist point and the finger root point from the wrist to the middle finger skeleton; if the line connecting the wrist point and the finger root point from the wrist to the middle finger skeleton is on a vertical line, then the palm orientation is positive; if the palm orientation is not positive, rotating the palm grayscale image to make the palm orientation positive, and obtaining a positive palm image; when the palm orientation is positive, the palm grayscale image is the positive palm image; obtaining the first palm image from the positive palm image based on the multiple hand joint points.

[0010] Considering that the palm may be facing in various directions in different palm images, this implementation performs forward rotation on the palm grayscale image to facilitate subsequent unified processing and, to a certain extent, improve the extraction accuracy of the effective area of ​​palm veins.

[0011] In one implementation of the first aspect, determining the two target points based on the second palm image includes the following steps: determining a first lowest point of a first finger gap and a second lowest point of a second finger gap based on the second palm image; wherein the first finger gap is the gap between the index finger and the middle finger; the second finger gap is the gap between the ring finger and the little finger; starting from the first lowest point, extending multiple points along the edges of the index finger and the middle finger respectively to form a first curve; starting from the second lowest point, extending multiple points along the edges of the ring finger and the little finger respectively to form a second curve; determining the tangents of the first curve and the second curve, and the first intersection point of the tangent with the first curve and the second intersection point of the tangent with the second curve; the first intersection point and the second intersection point are the two target points.

[0012] In one implementation of the first aspect, the extraction of the effective region of the palm vein based on the first palm image and the two target points includes the following steps: determining whether the connecting line of the two target points is on a horizontal line; when the connecting line of the two target points is not on a horizontal line, rotating the first palm image so that the connecting line of the two target points is on a horizontal line, obtaining a third palm image, and evaluating the palm width in the third palm image; when the connecting line of the two target points is on a horizontal line, evaluating the palm width in the first palm image; and extracting the effective region of the palm vein from the first palm image or the third palm image based on the palm width and the two target points on the horizontal line.

[0013] In one implementation of the first aspect, evaluating the palm width in the third palm image includes the following steps: obtaining the edge contour of the palm in the third palm image; scanning the edge contour based on two target points on a horizontal line to obtain multiple edge distances; the edge distance is the distance between two opposite edge points in the edge contour; and evaluating the palm width based on the multiple edge distances.

[0014] In one implementation of the first aspect, the step of extracting the effective region of the palm vein from the first palm image or the third palm image based on the palm width and two target points on a horizontal line includes the following steps: determining a cutting width; the cutting width being the product of the palm width and a preset cutting ratio; determining a target cutting range in the first palm image or the third palm image based on the cutting width and the two target points on a horizontal line, so as to extract the effective region of the palm vein from the first palm image or the third palm image based on the target cutting range; the target cutting range corresponding to the effective region of the palm vein.

[0015] Secondly, this application provides a palm vein effective region extraction system, the palm vein effective region extraction system comprising: an image acquisition module for acquiring a first palm image; an image segmentation module for segmenting the first palm image to acquire a second palm image; a point determination module for determining two target points based on the second palm image; and an effective region extraction module for extracting the effective region of the palm vein based on the first palm image and the two target points.

[0016] Thirdly, this application provides an electronic device, the electronic device comprising: a memory for storing a computer program; and a processor for executing the computer program to cause the electronic device to perform the above-described palm vein effective area extraction method.

[0017] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by an electronic device, implements the above-described method for extracting the effective area of ​​palm veins.

[0018] As described above, the method, system, medium, and electronic device for extracting the effective area of ​​palm veins described in this application have the following advantages:

[0019] Beneficial effects:

[0020] Compared with the prior art, this application provides a method for extracting the effective area of ​​palm veins, which realizes the rapid extraction of the effective area of ​​palm veins in palm images, and avoids interference from image pixels other than the effective area of ​​palm veins in the palm image on subsequent palmprint recognition, thereby improving the speed and accuracy of palmprint recognition. Attached Figure Description

[0021] Figure 1A The diagram shows the 21 evaluation points described in the embodiments of this application.

[0022] Figures 1B to 1J The image shown is a schematic diagram of the palm-related images involved in the palm vein effective area extraction method described in the embodiments of this application.

[0023] Figure 2 The flowchart shown is a method for extracting the effective area of ​​palm veins according to an embodiment of this application.

[0024] Figure 3 The flowchart shown is a process for obtaining a first palm image as described in an embodiment of this application.

[0025] Figure 4 The flowchart shown is a process for obtaining a first palm image based on a grayscale image of the palm and multiple hand joints, as described in an embodiment of this application.

[0026] Figure 5 The flowchart shown is a process for determining two target points based on a second palm image, as described in an embodiment of this application.

[0027] Figure 6 The flowchart shown is a process for extracting the effective area of ​​palm veins based on a first palm image and two target points, as described in an embodiment of this application.

[0028] Figure 7 The flowchart shown is a process for evaluating the width of a hand in a third hand image, as described in an embodiment of this application.

[0029] Figure 8 The flowchart shown is a process for extracting the effective area of ​​the palm vein from a first palm image or a third palm image based on the palm width and two target points on a horizontal line, as described in an embodiment of this application.

[0030] Figure 9 The diagram shown is a structural schematic of the palm vein effective area extraction system described in this application embodiment. Detailed Implementation

[0031] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0032] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0033] See Figures 1A to 1J ,and Figures 2 to 9 The following embodiments of this application provide a method, system, medium, and electronic device for extracting the effective area of ​​palm veins. Compared with the prior art, this application provides a method for extracting the effective area of ​​palm veins, which realizes rapid extraction of the effective area of ​​palm veins in palm images, and avoids interference from potentially disturbed image pixels other than the effective area of ​​palm veins in the palm image on subsequent palmprint recognition, thereby improving the speed and accuracy of palmprint recognition.

[0034] In one embodiment, the palm vein effective area extraction method provided in this application is applied to an electronic device.

[0035] like Figures 1A to 1J As shown, in this embodiment, the working principle of the palm vein effective area extraction method is as follows:

[0036] 1) Rotate your palm

[0037] In the input image of a hand, the hand may be facing in various directions. For the purpose of uniform processing in the future, the hand will be rotated to face the correct direction.

[0038] The hand image is a hand image captured by the camera that meets the image quality requirements.

[0039] like Figure 1A and Figure 1B As shown, information on 21 evaluation points of the palm was obtained via Mediapipe.

[0040] Mediapipe is a framework for building machine learning pipelines to process time-series data such as video and audio. This cross-platform framework is available for desktop / server, Android, iOS, and embedded devices such as Raspberry Pi and Jetson Nano.

[0041] Will Figure 1A The 0 and 9 evaluation points are used as the reference for rotation, so that the two points are on the vertical line after rotation (at this time, the palm is considered to be facing positive).

[0042] like Figure 1A As shown, the 21 evaluation points are as follows:

[0043] Point 0 is the wrist point;

[0044] {1,2,3,4} are key points on the skeletal structure from the wrist to the thumb;

[0045] {5,6,7,8} are key points on the skeletal structure from the wrist to the index finger;

[0046] {9,10,11,12} are key points on the skeletal structure from the wrist to the middle finger;

[0047] {13,14,15,16} are key points on the skeletal structure from the wrist to the ring finger;

[0048] {17,18,19,20} are key points on the skeleton from the wrist to the little finger;

[0049] Among them, {4,8,12,16,20} are the fingertip points, and {5,9,13,17} are the finger root points.

[0050] Specifically, first, an image of a hand (with the hand not facing forward) is input; then, the hand image is processed into grayscale to obtain a grayscale image; next, 21 evaluation points are estimated from the grayscale image using Mediapipe, and these 21 evaluation points are labeled in the grayscale image (e.g., ...). Figure 1B (as shown); Finally, rotate the grayscale image based on the 0 and 9 evaluation points so that the palm in the grayscale image is facing positive (as shown). Figure 1C (As shown).

[0051] 2) Cut an image to the size of a palm.

[0052] Based on the coordinates of the aforementioned 21 points, the outermost point is selected to form a rectangular frame, which is then multiplied by a coefficient to slightly enlarge the frame. Then, the original image (as described above) is extracted using this rectangular frame. Figure 1C The corresponding palm in the corresponding image.

[0053] Considering that the rectangle determined based on the outermost of the 21 points does not completely cover the entire palm area, the rectangle is multiplied by a coefficient to slightly enlarge it, so that the resulting rectangle can completely cover the entire palm area.

[0054] This coefficient is a certain value obtained through training. Its specific value is not a limiting condition for this application, as long as it is greater than 1. In practical applications, it can be set according to the specific application scenario.

[0055] This eliminates interference information in the image that is far from the palm; then, to facilitate subsequent processing, the image is padded to make it a 512x512 (512 refers to pixels) square image (e.g., Figure 1D (As shown).

[0056] Here, the image can also be filled as a 1024×1024 square image, i.e., 512x512 is not a limitation of this application; in practical applications, the type of square image to be filled can be selected according to the specific application scenario.

[0057] Larger pixels result in better extraction of the effective area of ​​the palm vein, but the extraction rate of the effective area of ​​the palm vein will be slower.

[0058] 3) Image segmentation

[0059] Image segmentation aims to separate the palm from the background to obtain the approximate shape of the palm. The resulting mask image is used for subsequent identification of finger gap cut points and palm width assessment.

[0060] In this embodiment, the image segmentation method is used, and the segmentation result is as follows: Figure 1E As shown.

[0061] Otsu's method is an algorithm for determining the threshold for image binarization segmentation. It was proposed by Japanese scholar Otsu in 1979. Based on the principle of Otsu's method, this method is also known as the maximum inter-class variance method because the inter-class variance between the foreground and background images is maximized after image binarization segmentation using the threshold obtained by Otsu's method.

[0062] 4) Calculate the tangent and the point of tangency between the two fingers.

[0063] This function is designed to define two fixed points using two finger gaps; firstly, it involves cropping an image from the above... Figure 1ETwo finger gap regions are extracted from the corresponding image; the first finger gap region is the gap between the index and middle fingers; the second finger gap region is the gap between the ring and little fingers (these two finger gap regions are selected because they are relatively large when the fingers are open, facilitating subsequent processing). Then, the lowest point is found in the first finger gap region, and from this lowest point, 100 points are extended forward along the edge of the index finger and backward along the edge of the middle finger, forming a 200-point curve. The lowest point is found in the second finger gap region, and from this lowest point, 100 points are extended forward along the edge of the ring finger and backward along the edge of the little finger, forming another 200-point curve. Finally, the tangents to the two curves obtained from the two finger gaps are found, and the points of tangency are determined. These points of tangency are the reference points (i.e., fixed points), such as... Figure 1F As shown, this is the first finger gap area.

[0064] The number of points extending forward and backward from the lowest point is not a limiting condition for this application. In practical applications, it can be set according to the specific application scenario.

[0065] 5) Rotate your palm along the tangent / point of tangency.

[0066] like Figure 1G As shown, rotate according to the coordinates of the reference point. Figure 1D The corresponding image ensures that the two reference points are on the same horizontal line (i.e., the tangent is on the horizontal line, which facilitates the determination of the palm print cutting area later).

[0067] 6) Calculate the width of the palm

[0068] This function is used to calculate the width of the palm, which is then used to determine the cutting size of the palm veins.

[0069] First, based on Figure 1G The corresponding image is used to obtain the edge contour of the palm using the Canny algorithm, such as... Figure 1H As shown; then, starting from the horizontal line where the two reference points are located, perform a horizontal scan downwards and record the distance between two opposite edge points of the palm edge contour in sequence. Finally, evaluate the width of the palm based on this distance.

[0070] The Canny algorithm, developed by John F. Canny in 1986, is a multi-level edge detection algorithm. More importantly, Canny established the computational theory of edge detection, explaining how this technique works. Typically, the goal of edge detection is to significantly reduce the image's data size while preserving its original attributes. Various algorithms exist for edge detection; although the Canny algorithm is old, it can be considered a standard algorithm for edge detection and is still widely used in research.

[0071] In one embodiment, during a horizontal scan, the scan is stopped when the obtained distance changes abruptly.

[0072] In this embodiment, estimating the palm width based on distance includes taking the median value of the distance as the palm width.

[0073] In one embodiment, a distance greater than a preset distance threshold is defined as a sudden change in distance.

[0074] The preset distance threshold is pre-set, and its specific value is not a limitation of the present invention. In practical applications, it can be set according to the specific application scenario.

[0075] In one embodiment, during a horizontal scan, the scan is stopped when an evaluation point is reached.

[0076] In this embodiment, estimating the palm width based on distance includes taking the minimum value among the distances as the palm width.

[0077] 7) Cutting the palm

[0078] like Figure 1I As shown, this function first needs to calculate the cutting frame. The reference point of the cutting frame is determined by the reference point of the finger seam, and the size of the cutting frame is determined by multiplying the width of the palm by the cutting ratio.

[0079] The cutting ratio is preset, and its specific setting is not a limitation of the present invention. In practical applications, it can be set according to the specific application scenario.

[0080] In one embodiment, the cutting ratio is less than 1.

[0081] In one embodiment, the cutting ratio is 0.8-0.9.

[0082] Then, as Figure 1J As shown, the effective area of ​​the palm vein can be obtained by applying the cutting frame.

[0083] In this embodiment, the effective area size of the palm vein is 140×140.

[0084] In this application, by extracting the effective area of ​​the palm vein and removing potentially interfering image pixels outside the effective area, the effective area is used for subsequent feature information extraction, thereby improving the recognition speed and accuracy of the subsequent palm print.

[0085] The technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0086] like Figure 2 As shown, this embodiment provides a method for extracting the effective area of ​​palm veins, which includes the following steps:

[0087] Step S1: Obtain the first palm image.

[0088] like Figure 3 As shown, in one embodiment, acquiring the first palm image includes the following steps:

[0089] Step S11: Obtain the original image of the palm.

[0090] Specifically, the original image of the hand is obtained from the palm image captured by the camera.

[0091] The original image of the hand meets the image quality requirements.

[0092] In one embodiment, hand images that do not meet the image quality requirements are removed from the hand images captured by the camera, and the original hand image is selected from the remaining hand images that meet the image quality requirements.

[0093] In one embodiment, the image quality requirement is a pre-set rule.

[0094] Specifically, a hand image that meets the rule is defined as meeting the image quality requirements; conversely, a hand image that does not meet the rule is defined as not meeting the image quality requirements.

[0095] In one embodiment, the image quality requirements include, but are not limited to, a sharpness greater than a first preset value and / or a hand integrity greater than a second preset value.

[0096] The first and second preset values ​​are both pre-set values, and their specific values ​​are not considered as limiting conditions of this application.

[0097] Step S12: Perform grayscale processing on the original palm image to obtain a grayscale image of the palm.

[0098] Step S13: Estimate multiple hand joints in the grayscale image of the hand.

[0099] It should be noted that the multiple hand joint points include, but are not limited to: wrist points (corresponding to "0 evaluation points" in the above embodiments) and finger root points on the wrist to the middle finger skeleton (corresponding to "9 evaluation points" in the above embodiments).

[0100] Step S14: Obtain the first palm image based on the grayscale image of the palm and the multiple hand joints.

[0101] like Figure 4 As shown, in one embodiment, obtaining the first palm image based on the palm grayscale image and multiple hand joints includes the following steps:

[0102] Step S141: Determine whether the palm orientation in the grayscale image of the palm is positive based on the wrist point and the finger root point from the wrist to the middle finger skeleton.

[0103] In this embodiment, if the line connecting the wrist point and the finger root point from the wrist to the middle finger skeleton is on a vertical line (i.e., the wrist point and the finger root point from the wrist to the middle finger skeleton have the same horizontal coordinate), then the palm orientation is positive.

[0104] When the palm is not facing forward (i.e., the horizontal coordinates of the wrist point and the finger root point on the middle finger skeleton are different), step S142 is executed.

[0105] Step S142: Rotate the grayscale image of the palm so that the palm is facing forward, and obtain a forward-facing image of the palm.

[0106] It should be noted that when the palm is facing forward, the grayscale image of the palm is the image of the palm facing forward.

[0107] Step S143: Obtain the first palm image from the frontal palm image based on the multiple hand joints.

[0108] Step S2: Perform image segmentation on the first palm image to obtain the second palm image.

[0109] In one embodiment, the Otsu method is used to segment the first palm image to obtain the second palm image.

[0110] Step S3: Determine two target points based on the second palm image.

[0111] like Figure 5 As shown, in one embodiment, determining the two target points based on the second palm image includes the following steps:

[0112] Step S31: Based on the second palm image, determine the first lowest point of the first finger gap and the second lowest point of the second finger gap.

[0113] The first finger gap is the gap between the index and middle fingers; the second finger gap is the gap between the ring and little fingers.

[0114] Step S32: Starting from the first lowest point, extend multiple points along the edge of the index finger and the edge of the middle finger to form a first curve.

[0115] Step S33: Starting from the second lowest point, extend multiple points along the edge of the ring finger and the edge of the little finger to form a second curve.

[0116] Step S34: Determine the tangents of the first curve and the second curve, and the first intersection point of the tangent with the first curve and the second intersection point of the tangent with the second curve.

[0117] It should be noted that the first intersection point and the second intersection point are two target fixed points (corresponding to the "reference points" in the above embodiments).

[0118] Specifically, using the polygon tangent algorithm, the tangents to the first curve and the second curve are found, and the intersections of these tangents with the first curve and the second curve are the two target points.

[0119] Step S4: Extract the effective area of ​​the palm vein based on the first palm image and the two target points.

[0120] like Figure 6 As shown, in one embodiment, the extraction of the effective region of the palm vein based on the first palm image and the two target points includes the following steps:

[0121] Step S41: Determine whether the connecting line between the two target points is on a horizontal line.

[0122] When the line connecting the two target points is not on a horizontal line (i.e., the ordinates of the two target points are different), proceed to step S42.

[0123] Step S42: Rotate the first palm image so that the line connecting the two target points is on a horizontal line, obtain the third palm image, and evaluate the palm width in the third palm image.

[0124] like Figure 7 As shown, in one embodiment, evaluating the palm width in the third palm image includes the following steps:

[0125] Step S421: Obtain the edge contour of the palm in the third palm image.

[0126] In one embodiment, the Canny algorithm is used to obtain the edge contour of the palm in the third palm image.

[0127] Step S422: Scan the edge contour based on the two target points on the horizontal line to obtain multiple edge distances.

[0128] It should be noted that the edge distance is the distance between two opposite edge points in the edge profile.

[0129] Step S423: Evaluate the palm width based on the multiple edge distances.

[0130] In one embodiment, the smallest edge distance is selected from a plurality of edge distances as the palm width.

[0131] In one embodiment, the median value from a plurality of edge distances is selected as the palm width.

[0132] When the line connecting the two target points is on a horizontal line (i.e., the ordinates of the two target points are the same), step S43 is executed.

[0133] Step S43: Evaluate the palm width in the first palm image.

[0134] It should be noted that the evaluation of the palm width in the first palm image in step S43 is based on the same principle as the evaluation of the palm width in the third palm image in step S42 above, so its working principle will not be described in detail here.

[0135] Step S44: Extract the effective area of ​​the palm vein from the first palm image or the third palm image based on the palm width and the two target points on the horizontal line.

[0136] like Figure 8 As shown, in one embodiment, the step of extracting the effective area of ​​the palm vein from the first palm image or the third palm image based on the palm width and two target points on the horizontal line includes the following steps:

[0137] Step S441: Determine the cutting width.

[0138] In one embodiment, the cutting width is the product of the palm width and a preset cutting ratio (corresponding to the "cutting ratio" in the above embodiment).

[0139] Step S442: Determine the target cutting range in the first palm image or the third palm image based on the cutting width and the two target points on the horizontal line, so as to extract the effective area of ​​the palm vein from the first palm image or the third palm image based on the target cutting range.

[0140] In this embodiment, the target cutting range (corresponding to the "cutting frame" in the above embodiment) corresponds to the effective area of ​​the palm vein.

[0141] In this embodiment, the working principle of the palm vein effective area extraction method is the same as described above. Figures 1A to 1J The working principle of the palm vein effective area extraction method provided in the corresponding embodiment is the same, so it will not be described in detail here.

[0142] The scope of protection of the palm vein effective area extraction method described in this application is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.

[0143] This application also provides a palm vein effective area extraction system, which can implement the palm vein effective area extraction method described in this application. However, the implementation device of the palm vein effective area extraction method described in this application includes, but is not limited to, the structure of the palm vein effective area extraction system listed in this embodiment. All structural modifications and substitutions of the prior art made based on the principles of this application are included within the protection scope of this application.

[0144] like Figure 9 As shown, this embodiment provides a palm vein effective area extraction system, which includes:

[0145] Image acquisition module 91 is used to acquire the first palm image.

[0146] The image segmentation module 92 is used to segment the first palm image to obtain the second palm image.

[0147] The point determination module 93 is used to determine two target points based on the second palm image.

[0148] The effective region extraction module 94 is used to extract the effective region of the palm vein based on the first palm image and the two target points.

[0149] It should be noted that the structure and principle of the image acquisition module 91, the image segmentation module 92, the fixed point determination module 93 and the effective region extraction module 94 correspond one-to-one with the steps (steps S1 to S4) in the above palm vein effective region extraction method, so they will not be described again here.

[0150] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, apparatuses, modules, or units, and may be electrical, mechanical, or other forms.

[0151] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0152] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0153] This embodiment also provides an electronic device, which includes: a memory for storing a computer program; and a processor for executing the computer program to enable the electronic device to perform the above-described palm vein effective area extraction method.

[0154] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by an electronic device, implements the above-described method for extracting the effective area of ​​palm veins.

[0155] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. This available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state drive (SSD)).

[0156] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0157] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for extracting the effective area of ​​palm veins, characterized in that, The method for extracting the effective area of ​​palm veins includes the following steps: Obtain the first palm image; The process of obtaining the first palm image includes the following steps: obtaining an original palm image; performing grayscale processing on the original palm image to obtain a grayscale palm image; estimating multiple hand joints in the grayscale palm image; the multiple hand joints include at least: wrist points and finger root points from the wrist to the middle finger skeleton; and obtaining the first palm image based on the grayscale palm image and the multiple hand joints. The process of obtaining the first palm image based on the palm grayscale image and multiple hand joint points includes the following steps: determining whether the palm orientation in the palm grayscale image is positive based on the wrist point and the finger root point from the wrist to the middle finger skeleton; if the line connecting the wrist point and the finger root point from the wrist to the middle finger skeleton is on a vertical line, then the palm orientation is positive; if the palm orientation is not positive, rotating the palm grayscale image to make the palm orientation positive, and obtaining a positive palm image; when the palm orientation is positive, the palm grayscale image is the positive palm image; obtaining the first palm image from the positive palm image based on multiple hand joint points; Perform image segmentation on the first palm image to obtain the second palm image; Two target points are determined based on the second palm image. This determination includes: determining the first lowest point of the first finger gap and the second lowest point of the second finger gap based on the second palm image; wherein the first finger gap is the gap between the index and middle fingers; the second finger gap is the gap between the ring and little fingers; starting from the first lowest point, multiple points are extended along the edges of the index and middle fingers to form a first curve; starting from the second lowest point, multiple points are extended along the edges of the ring and little fingers to form a second curve; the tangents of the first and second curves are determined, as well as the first intersection point of the tangent with the first curve and the second intersection point of the tangent with the second curve; the first intersection point and the second intersection point are the two target points; using a polygon tangent algorithm, the tangents of the first and second curves are found, and the intersection points of these tangents with the first and second curves are the two target points. Extracting the effective region of the palm vein based on the first palm image and the two target points; the extraction of the effective region of the palm vein based on the first palm image and the two target points includes: determining whether the connecting line of the two target points is on a horizontal line; when the connecting line of the two target points is not on a horizontal line, rotating the first palm image so that the connecting line of the two target points is on a horizontal line, obtaining a third palm image, and evaluating the palm width in the third palm image; when the connecting line of the two target points is on a horizontal line, evaluating the palm width in the first palm image; and extracting the effective region of the palm vein from the first palm image or the third palm image according to the palm width and the two target points on the horizontal line.

2. The method for extracting the effective area of ​​palm veins according to claim 1, characterized in that, The evaluation of the palm width in the third palm image includes the following steps: Obtain the edge contour of the palm in the third palm image; The edge contour is scanned based on two target points on a horizontal line to obtain multiple edge distances; the edge distance is the distance between two opposite edge points in the edge contour. The palm width is evaluated based on multiple edge distances.

3. The method for extracting the effective area of ​​palm veins according to claim 1, characterized in that, The step of extracting the effective area of ​​the palm vein from the first palm image or the third palm image based on the palm width and two target points on the horizontal line includes the following steps: Determine the cutting width; the cutting width is the product of the palm width and the preset cutting ratio; The target cutting range in the first palm image or the third palm image is determined based on the cutting width and the two target points on the horizontal line, so as to extract the effective area of ​​the palm vein from the first palm image or the third palm image based on the target cutting range; the target cutting range corresponds to the effective area of ​​the palm vein.

4. A system for extracting the effective area of ​​palm veins, characterized in that, For performing the palm vein effective region extraction method as described in any one of claims 1 to 3, the palm vein effective region extraction system comprises: The image acquisition module is used to acquire the first palm image; The image segmentation module is used to segment the first palm image to obtain the second palm image; The point determination module is used to determine two target points based on the second palm image; The effective region extraction module is used to extract the effective region of the palm vein based on the first palm image and the two target points.

5. An electronic device, characterized in that, The electronic device includes: The memory is used to store computer programs; A processor for executing the computer program to cause the electronic device to perform the palm vein effective area extraction method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by an electronic device, the program implements the palm vein effective area extraction method according to any one of claims 1 to 3.

Images