Palm print acquisition method and apparatus, device, and storage medium
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- JIANGSU BRMICO ELECTRONICS
- Filing Date
- 2025-09-05
- Publication Date
- 2026-06-04
Smart Images
Figure CN2025119393_04062026_PF_FP_ABST
Abstract
Description
Palmprint acquisition methods, devices, equipment and storage media Technical Field
[0001] This application relates to the field of palmprint payment, and particularly to a palmprint acquisition method, apparatus, device, and storage medium. Background Technology
[0002] Fingerprint and palm print scanning is limited by advancements in camera technology, typically employing contact-based capacitive sensors to scan images, followed by digitization. Non-contact image scanning often loses more detail, especially when applied to palm prints. Low-resolution cameras cannot capture clear palm print images, while high-resolution cameras are too expensive.
[0003] In related technologies, the method for cameras to capture palm prints involves the user moving their hand to adjust the distance and angle between themselves and the camera. A clear image is captured when the palm is positioned at a suitable angle. This application scenario arises because while most cameras now have built-in focus adjustment functions, they only preset a fixed focal length for a specific application scenario. For example, they preset the image capture when the palm is 15cm-20cm away from the camera, and then adhere to this fixed focal length parameter. When the palm is more than 20cm away or less than 15cm, insufficient clarity occurs. Of course, unclear images can be compensated for using interpolation and filtering algorithms. However, algorithms inevitably introduce the probability of image distortion or deformity. Therefore, solving the problem of palm print clarity requires focusing on the physical device itself.
[0004] Furthermore, most current palmprint capture cameras operate in a fixed direction and do not actively seek a suitable angle. When the palm is tilted to one side and not directly facing the camera, the captured palmprint image will be suboptimal. While algorithms can correct this palm tilt, there is a risk of distortion. Therefore, addressing the palm tilt issue through device design is a viable solution.
[0005] Therefore, in view of the above-mentioned technical problems, the present invention provides a palmprint acquisition method, device, equipment and storage medium. Summary of the Invention
[0006] This application provides a palmprint acquisition method, apparatus, device, and storage medium, particularly a non-contact palmprint acquisition method and apparatus, which solves the problems of image distortion, deformity, and offset during palmprint payment image acquisition.
[0007] On one hand, this application provides a palm print collection device, the device including a longitudinal conveyor belt (10), a transverse conveyor belt (20) and a support frame (70); a palm print collection component (60) is fixedly installed at the center of the transverse conveyor belt (20); the belt body of the transverse conveyor belt (20) is fitted in a first sliding groove (30), the first sliding groove (30) is fixedly installed on the longitudinal conveyor belt (10); the belt body of the longitudinal conveyor belt (10) is fitted in a second sliding groove (40), the second sliding groove (40) is fixedly installed on the support frame (70);
[0008] The transverse conveyor belt (20) is controlled to slide laterally by a first stepper motor (50), and the longitudinal conveyor belt (10) is controlled to slide longitudinally by a second stepper motor;
[0009] When the palm print image acquired by the palm print acquisition component (60) is offset, the longitudinal conveyor belt (10) and / or the transverse conveyor belt (20) are controlled to move in the corresponding directions to adjust the shooting position.
[0010] Specifically, the longitudinal conveyor belt (10) and the transverse conveyor belt (20) are respectively arc-shaped structures and are respectively fitted into the first arc-shaped sliding groove (30) and the second arc-shaped sliding groove (40).
[0011] Specifically, the legs of the first sliding groove (30) are fixedly installed on the longitudinal conveyor belt (10), and an inner cavity is provided between the groove and the legs. A first gear (69) that is connected to the first stepper motor (50) is installed in the inner cavity.
[0012] The bottom of the transverse conveyor belt (20) is threaded, and the first gear (69) meshes with the thread of the transverse conveyor belt (20) to drive the transverse conveyor belt (20) to move laterally.
[0013] Specifically, the legs of the second sliding groove (40) are fixedly installed on the support frame (70), and an inner cavity is provided between the groove and the legs. A second gear (41) that is connected to the second stepper motor is installed in the inner cavity.
[0014] The bottom of the longitudinal conveyor belt (10) is threaded, and the second gear (41) meshes with the thread of the longitudinal conveyor belt (10) to drive the longitudinal conveyor belt (10) to move longitudinally.
[0015] Specifically, the palm print acquisition component (60) includes a cylindrical shell, a prism (67) is installed at the axial position at the bottom of the shell, and a camera (68) is installed on the side wall of the shell. Light is incident along the axis of the shell, and after passing through the prism (67), it is reflected to the camera (68) to acquire a palm print image.
[0016] An aperture assembly (65) is fixedly installed on the outside of the prism (67), and an aperture gear (62) with adjustable aperture size is sleeved on the outside of the aperture assembly (65); a convex lens (61) is installed above the aperture assembly (65), and the convex lens (61) is embedded in the aperture assembly (65) and the entrance of the housing;
[0017] When the palm print image captured by the camera (68) does not meet the recognition requirements, the aperture gear (62) is controlled to rotate forward or backward according to the size of the palm print image, thereby adjusting the aperture focal length and depth of field.
[0018] Specifically, the radial dimensions of the aperture assembly (65) and the prism (67) are smaller than the inner diameter of the cylindrical shell; LED beads (64) are provided on the outer edge of the entrance of the shell;
[0019] A stepper motor (63) is also installed on the inner side of the bottom of the housing. A gear is installed on the output shaft of the stepper motor (63) and meshes with the aperture gear (62) on the outer edge of the aperture assembly (65).
[0020] Specifically, a sensor (66) is installed on the inner wall of the housing at the same height as the aperture gear (62) to collect the aperture tooth pattern in real time.
[0021] Specifically, the cross-section of the prism (67) is a right triangle with two right-angled sides of 45 degrees. The incident light is reflected horizontally by the oblique surface and then transmitted to the camera (68).
[0022] On the other hand, this application provides a palmprint acquisition method, the method being used in a palmprint acquisition device, the method comprising:
[0023] According to the image acquisition instructions, the palm print image is acquired and extracted, the pixel information of the palm print image is identified, and the number of key points of the palm and the pixel coordinate data of the key points of the palm are determined; the key points of the palm include the fingertips, the finger joints, and the wrist joints.
[0024] The completeness of the palm image and the palm angle orientation are calculated based on the number of key points and pixel coordinates of the palm.
[0025] When the palmprint image captured by the camera does not meet the recognition requirements, the adjustment parameters of each gear in the palmprint acquisition device are calculated based on the offset position of the palm angle, and the aperture acquisition position is adjusted to obtain the palmprint image at the target angle.
[0026] Specifically, calculating the completeness of the palm image and the palm orientation based on the number of key points and pixel coordinates of the palm includes:
[0027] Define the key points A(Xa,Ya) at the base of the thumb, B(Xb,Yb) at the tip of the thumb, C(Xc,Yc) at the tip of the index finger, D(Xd,Yd) at the tip of the middle finger, E(Xe,Ye) at the tip of the ring finger, and F(Xf,Yf) at the joint end of the little finger.
[0028] After extracting the palmprint image, all key points and corresponding coordinate information are identified based on pixel information;
[0029] When the palm image contains six key points, it indicates that the palm image is complete. Calculate the coordinates of the intersection point Qe formed by the line connecting key points A and D and the line connecting key points B and E, and the coordinates of the intersection point Qc formed by the line connecting key points A and C and the line connecting key points B and D.
[0030] Determine the palm orientation and palm deflection angle based on the coordinates of intersection point Qe and intersection point Qc.
[0031] When the palm orientation and palm angle do not meet the recognition requirements, the horizontal axis offset parameter and / or vertical axis offset parameter are determined based on the palm orientation and palm angle, and the posture adjustment information is generated based on the offset parameter. The stepper motor is then controlled to adjust the horizontal conveyor belt and / or vertical conveyor belt before re-image acquisition.
[0032] Specifically, the horizontal axis offset parameters are determined based on the palm orientation and palm angle, including:
[0033] When the intersection point Qc is identified to fall within the pixel area of the index finger and the intersection point Qe is identified to fall within the pixel area of the middle finger, the palm is determined to be offset to the left relative to the aperture; the horizontal conveyor belt is controlled to move the palmprint acquisition component to the left, thereby adjusting the camera angle to the right;
[0034] When it is identified that the intersection point Qc coordinates fall within the pixel area of the ring finger and the intersection point Qe coordinates fall within the pixel area of the middle finger, it is determined that the palm is offset to the right relative to the aperture; the horizontal conveyor belt is controlled to move the palmprint acquisition component to the right, and then the camera angle is adjusted to the left.
[0035] The vertical axis offset parameters are determined based on the palm orientation and palm deflection angle, including:
[0036] Set the center point coordinates of the line connecting keypoints A and B as Qz, represented as Qz((Xa+Xb) / 2,(Ya+Yb) / 2); set the first distance Sdf between keypoints D and F as follows:
[0037] Set the second distance Sqf between keypoints Qz and F, as follows:
[0038] The ratio P between the palm length and the middle finger length is determined by the ratio of the first distance to the second distance, expressed as follows: P = Sqf / Sdf
[0039] When P>1.2, it indicates that the length of the palm is greater than the length of the middle finger, and the palm is slightly higher than the aperture; control the longitudinal conveyor belt to move the palmprint acquisition component upward, and then control the camera angle to adjust downward;
[0040] When P<1, it indicates that the length of the palm is less than the length of the middle finger, and the palm is lower than the aperture; the longitudinal conveyor belt is controlled to move the palmprint acquisition component downward, and then the camera angle is controlled to adjust upward.
[0041] In another aspect, this application provides a palmprint acquisition method, the method being used in a palmprint acquisition device, the method comprising:
[0042] According to the image acquisition instructions, the palm print image is acquired and extracted, the pixel information of the palm print image is identified, and the number of key points of the palm and the pixel coordinate data of the key points of the palm are determined; the key points of the palm are the fingertips and the wrist bottom end near the base of the thumb.
[0043] The completeness of the palm image and the position of the palm are calculated based on the number of key points and pixel coordinates of the palm.
[0044] When the palm print image captured by the camera does not meet the recognition requirements, the adjustment parameters of the aperture gear in the non-contact palm print acquisition device are calculated based on the palm position, and the aperture focal length and depth of field are adjusted to obtain a complete palm print image.
[0045] Specifically, after receiving the image acquisition command, the main control chip activates the sensor and LED beads in the non-contact palm print acquisition device. The sensor captures and identifies the first aperture tooth pattern on the outer side of the aperture assembly, and the LED beads provide supplementary lighting to the palm area.
[0046] Specifically, calculating the completeness of the hand image and the hand position based on the number of key points and pixel coordinates of the hand includes:
[0047] Define the key points A(Xa,Ya) at the base of the thumb, B(Xb,Yb) at the tip of the thumb, C(Xc,Yc) at the tip of the index finger, D(Xd,Yd) at the tip of the middle finger, E(Xe,Ye) at the tip of the ring finger, and F(Xf,Yf) at the tip of the little finger.
[0048] After extracting the palmprint image, all key points and corresponding coordinate information are identified based on pixel information;
[0049] When the palm image contains six keypoints, indicating that the palm image is complete, calculate the distance S between endpoints A and D.AD ; indicates the following:
[0050] When S AD When the value is within the first preset range, it indicates that the size of the palm is close to the image size, and the image is captured and generated.
[0051] When S DD When the value is within the first preset range but outside the second preset range, the palm image is too small, according to S. AD The value determines the adjustment parameters, and controls the stepper motor to rotate the aperture gear in the forward direction, thus bringing the depth of field closer;
[0052] When key points are missing in the palm image, the offset parameters are determined based on the finger positions corresponding to the number of key points, and the pose adjustment information is generated based on the offset parameters. The stepper motor is then controlled to adjust the aperture gear before re-capturing the image.
[0053] Specifically, when key points are missing in the palm image, determining the offset parameter based on the finger position corresponding to the key point includes:
[0054] When all six key points are not detected, the hand is indicated to be too close to the set threshold and the hand size is too large to fit the image. Based on the number of missing key points, pose adjustment information is generated to reduce the aperture and increase the depth of field.
[0055] When the detection result is missing key point F or key point B, the palm is instructed to shift to both sides, and pose adjustment information is generated to reduce the aperture and increase the depth of field based on the number of missing key points.
[0056] When the detection result is missing key point A, or missing both key points A and B, or only contains key points A and B, the palm is indicated to shift up and down. Gesture correction information is generated based on the palm position so that the image can be re-captured.
[0057] In another aspect, this application provides a computer device including a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, wherein the at least one instruction, the at least one program, the code set or instruction set is loaded and executed by the processor to implement the palmprint acquisition method described in any of the above aspects.
[0058] In another aspect, this application provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the palmprint acquisition method described in any of the above aspects.
[0059] The beneficial effects of the technical solution provided in this application include at least the following: the algorithm and device of this application can first identify the palm shape in the acquired image, and determine the palm orientation and palm angle based on the completeness of the palm and the identification of key points. For cases where the palm is offset to the left or right, the aperture can be moved to the palm position by moving the transverse conveyor belt of the device left or right, thus achieving angle correction. For cases where the palm is offset up or down, the aperture can be moved to the palm position by moving the longitudinal conveyor belt of the device up or down. Due to the arc-shaped conveyor belt design, this allows for posture correction over a wide range, ensuring that a complete and angularly accurate palm print image is captured.
[0060] Especially in scenarios where the palm is significantly off-center and key points are not fully recognized, the stepper motor in the palmprint acquisition component can be used independently for focus control. If the palm size is determined to be larger than the image size, it means the palm is too close to the camera. In this case, the camera aperture is reduced, increasing the depth of field until the palm size matches the image size. Conversely, if the palm size is smaller than the image size, the camera aperture is increased as needed, decreasing the depth of field until the palm size matches the image size. This solution maximizes the adaptive adjustment and acquisition of palm images through focus control, thereby improving the recognition success rate. Attached Figure Description
[0061] Figure 1 is a front view of the palmprint acquisition device provided in an embodiment of this application;
[0062] Figure 2 is a cross-sectional view of the side of the palm print collection device;
[0063] Figure 3 shows a partial enlarged view of the palmprint acquisition component;
[0064] Figure 4 shows the front view of the palmprint acquisition device;
[0065] Figure 5 shows a top view of the palmprint acquisition device;
[0066] Figure 6 shows a schematic diagram of the palmprint acquisition component moving towards the palm on the horizontal and vertical axes.
[0067] Figure 7 is a flowchart of the palmprint acquisition method provided in an embodiment of this application;
[0068] Figure 8 is a flowchart of the non-contact palmprint acquisition method provided in an embodiment of this application;
[0069] Figure 9 shows a schematic diagram of selecting key points on the palm.
[0070] Figure 10 shows a schematic diagram of a scenario where the palm is tilted to the left and the palm is turned upwards;
[0071] Figure 11 shows an algorithm flowchart of the palmprint acquisition method provided in the embodiments of this application;
[0072] Figure 12 shows schematic diagrams of different hand placement scenarios;
[0073] Figure 13 shows the flowchart of the posture adjustment strategy for different hand placement scenarios.
[0074] Reference numerals: 10-Longitudinal conveyor belt; 20-Transverse conveyor belt; 30-First sliding groove; 40-Second sliding groove; 50-First stepper motor; 60-Palmprint acquisition component; 61-Convex lens; 62-Aperture gear; 63-Stepper motor; 64-LED lamp bead; 65-Aperture component; 66-Sensor; 67-Prism; 68-Camera; 69-Limiting hole; 70-Support frame. Detailed Implementation
[0075] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.
[0076] In this article, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.
[0077] Figure 1 is a front view of the palmprint acquisition device provided in this embodiment, and Figure 2 is a sectional view of the side of the palmprint acquisition device. The device as a whole is a multi-angle attitude adjuster erected by a support frame 70, including a longitudinal conveyor belt 10, a transverse conveyor belt 20, and a support frame 70; a palmprint acquisition component 60 is fixedly installed at the center of the transverse conveyor belt 20. The entire or partial body of the transverse conveyor belt 20 is fitted into a first sliding groove 30. The first sliding groove 30 is fixedly installed on the longitudinal conveyor belt 10. The entire or partial body of the longitudinal conveyor belt 10 is fitted into a second sliding groove 40, which is fixedly installed on the support frame 70. The transverse conveyor belt 20 is controlled to slide laterally by a first stepper motor 50, and the longitudinal conveyor belt 10 is controlled to slide longitudinally by a second stepper motor. The function of this device is to control the longitudinal conveyor belt 10 and / or the transverse conveyor belt 20 to move in the corresponding direction to adjust the shooting position when the palmprint image acquired by the palmprint acquisition component 60 deviates.
[0078] In this embodiment, the longitudinal conveyor belt 10 and the transverse conveyor belt 20 are designed as arc-shaped structures, respectively fitted into the arc-shaped first sliding groove 30 and the second sliding groove 40. The belts distributed transversely and longitudinally are perpendicular to each other. The two arc-shaped structures are specifically set according to actual conditions, and the two arcs are generally the same. The arc-shaped curved structure forms an enclosed curved surface similar to a "small sun heater".
[0079] Referring to Figure 3, a partially enlarged view of the palmprint acquisition assembly is shown. The support leg of the first sliding groove 30 is fixedly mounted on the longitudinal conveyor belt 10. An inner cavity is provided between the groove and the support leg, and a first gear 69, which is driven and connected to the first stepper motor 50, is installed in the inner cavity. The bottom of the transverse conveyor belt 20 is threaded, and the first gear 69 meshes with the thread of the transverse conveyor belt 20, driving the transverse conveyor belt 20 to move laterally.
[0080] The legs of the second sliding groove 40 are fixedly mounted on the support frame 70. An inner cavity is provided between the groove and the legs, and a second gear 41, which is connected to the second stepper motor, is installed in the inner cavity. Correspondingly, the bottom of the longitudinal conveyor belt 10 is threaded, and the second gear 41 meshes with the thread of the longitudinal conveyor belt 10 to drive the longitudinal conveyor belt 10 to move longitudinally.
[0081] In some embodiments, because the palmprint acquisition component 60 moves on a curved surface, it needs to have highly controllable focusing capabilities when the shooting angle and distance change. Therefore, the palmprint acquisition component 60 provided in this application is also specifically designed. The palmprint acquisition component 60 is generally a cylindrical device housing. Figure 4 is a front view of the palmprint acquisition device provided in the embodiment of this application. A prism 67 is installed at the axial position at the bottom of the housing. A camera 68 for acquiring palmprint images is installed on the inner side wall of the housing. During shooting, the palmprint light is incident inward along the axis of the housing, reflected by the prism 67, and then reflected to the camera 68 to capture the palmprint image.
[0082] Figure 5 is a top view of the palm print acquisition device provided in this embodiment. An aperture assembly 65 is fixedly disposed above the prism 67. An aperture gear 62 with adjustable aperture size is sleeved on the outside of the aperture assembly 65, that is, rotating the aperture gear 62 can change the aperture parameters. A convex lens 61 is disposed above the aperture assembly 65, and the convex lens 61 is embedded in the entrance of the aperture assembly 65 and the housing.
[0083] A sensor 66 is installed on the inner wall of the housing at the same height as the aperture gear 62 to collect the aperture tooth pattern in real time. A stepper motor 63 is installed on the inner side of the bottom of the housing, and a gear is installed on the output shaft of the stepper motor 63. The gear meshes with the aperture gear 62 on the outer edge of the aperture assembly 65. When the palm print image captured by the camera 68 is incomplete, the aperture gear 62 can be controlled to rotate forward or backward by the motor component, thereby adjusting the aperture focal length and depth of field. For example, rotating the side of the aperture one revolution will adjust the aperture from the maximum to the minimum.
[0084] In one feasible implementation, the convex lens 61 has a focal length of 40mm, is made of quartz glass, and consists of two symmetrical convex lenses 61. The upper half of the convex lens 61 faces outward and is mounted on the outer housing, while the lower half faces inward and is positioned at the aperture opening. A gap of 1.8mm is left between the planes of the two convex lenses 61. The aperture thickness varies depending on the adjusted overlap, ranging from a minimum of 1.3mm to a maximum of 1.5mm.
[0085] In this application, the cross-section of the prism 67 is a right-angled triangle with two right-angled sides at 45 degrees. The upper right-angled side is the light entrance, receiving external light rays from the convex lens 61. The hypotenuse of the prism 67 is the light reflection point, and the hypotenuse has a reflective coating that also absorbs floodlight, thereby enhancing image contrast. The incident light rays are reflected horizontally by the hypotenuse and then transmitted to the camera 68, which is the CMOS image sensor 66. In one feasible embodiment, the CMOS image sensor 66 has a focal length of 40mm, 200W pixels, and an image size of 640*480.
[0086] In addition, limit holes 69 are symmetrically provided at the bottom of the outer shell, and LED beads 64 are provided at the outer edge of the top entrance of the shell for image acquisition and supplementary lighting.
[0087] In this embodiment, the lengths of the horizontal and vertical transmission belts are limited. Figure 6 shows the maximum angle of 76° for hand movement of the palmprint acquisition component along the horizontal and vertical axes. This angle was obtained through actual measurement based on usage scenarios. Generally, extreme scenarios where the palm is flat and only the side of the palm faces the camera are unlikely. Due to the influence of the hand's skeletal structure, in most cases, the angle of deviation to the camera is between 0° and 34° when the user's palm is facing down, and between 0° and 22° when the palm is facing up. The angle of deviation to the camera is between 0° and 30° when the palm faces left or right. Therefore, the transmission belts along the horizontal and vertical axes can maintain the camera's movement between -38° and +38° for shooting, which meets the needs of most application scenarios.
[0088] Figure 7 is a flowchart of the palmprint acquisition method provided in an embodiment of this application, applied to the palmprint acquisition device described above. The method includes the following steps:
[0089] S1. Collect and extract palmprint images according to the image acquisition instructions, identify the pixel information of the palmprint images, and determine the number of key points on the palm and the pixel coordinate data of the key points on the palm.
[0090] Based on the above device, the PC sends the image acquisition command to the image acquisition device via the USB interface. After receiving the image acquisition command, the main control chip on the device turns on the CMOS image sensor and LED beads to start acquiring palm prints. At this time, the palm should be placed in front of or above the convex lens to capture a frame of the image.
[0091] Next, the histogram of this frame is obtained through image processing algorithms, the palm threshold is calculated, and the image is binarized based on the obtained threshold to distinguish the palm from the background and extract the palmprint image.
[0092] When a palm print image contains images of a hand, it can be identified through pixel analysis.
[0093] In this embodiment, the finger tip, knuckle tip, and wrist tip can be set as key points, and the position coordinates of these key points can be determined for subsequent position determination.
[0094] S2. Calculate the completeness of the palm image and the palm angle orientation based on the number of key points and pixel coordinates of the palm.
[0095] The completeness of the palm image is determined by the distance between the palm and the convex lens. When the distance is appropriate, a complete palm image can be captured. When the distance is too far, a complete palm image cannot be captured, resulting in the loss of key points. The position of the palm can be determined based on these lost key points. The palm's orientation is primarily considered in scenarios where the image includes all key points. In other words, assuming the palm image is complete, the angle between the palm and the aperture (with the light inlet as the recognition center point) is determined to ascertain the palm's orientation. Only when the orientation is appropriate can a clear palmprint image and accurate recognition be ensured.
[0096] S3. When the palm print image captured by the camera does not meet the recognition requirements, the adjustment parameters of each gear in the palm print acquisition device are calculated based on the offset position of the palm angle, and the aperture acquisition position is adjusted to obtain the palm print image at the target angle.
[0097] For incomplete palm print images, appropriate adjustment parameters can be calculated based on the palm's position. Similarly, for complete palm print parameters, if image sharpness is insufficient due to distance, the aperture adjustment parameters are also calculated based on the palm's position. For example, if the palm print is slightly to the left, the aperture is directly adjusted to re-acquire the image and include the palm; if the palm print is severely to the left, a voice prompt will remind the user to move to the right. When the palm is too far away, resulting in a small image, the aperture is reduced to decrease the depth of field, allowing for the capture of the optimal palm print image.
[0098] Even if a complete palm print image is obtained, if the palm angle is off, posture adjustment is still required. For example, if the hand is off to the left or right, the movement of the horizontal conveyor belt can be controlled, which indirectly drives the palm print acquisition component to move as a whole, so that the palm is aligned with the aperture entrance.
[0099] This application focuses on discussing angle and posture correction adjustments for scenes where complete palm print images are captured.
[0100] In some embodiments, calculating the completeness of the palm image and the palm orientation based on the number of key points and pixel coordinates includes:
[0101] a. Define the key points A(Xa,Ya) at the base of the thumb and wrist, B(Xb,Yb) at the tip of the thumb, C(Xc,Yc) at the tip of the index finger, D(Xd,Yd) at the tip of the middle finger, E(Xe,Ye) at the tip of the ring finger, and F(Xf,Yf) at the joint end of the little finger; Figure 9 on the left shows a schematic diagram of selecting key points on the palm.
[0102] b. After extracting the palm print image, identify all key points and their corresponding coordinates based on pixel information;
[0103] c. When the palm image contains six key points, it indicates that the palm image is complete. Calculate the coordinates of the intersection point Qe formed by the line connecting key points A and D and the line connecting key points B and E, and the coordinates of the intersection point Qc formed by the line connecting key points A and C and the line connecting key points B and D.
[0104] As shown on the right side of Figure 9, ideally, when the palm faces the camera, the middle finger of a human hand is approximately positioned on the vertical axis of the palm. This means that connecting keypoints A, B, and D will form an approximate isosceles triangle, with AB as the base and AD and BD as the two isosceles sides. The index and ring fingers are the two fingers closest to the middle finger. Connecting keypoints A and C gives line AC, and connecting keypoints B and E gives line BE. We can see that lines AC and BD intersect at a point in the background area between the index and middle fingers, not the palm; we call this point Qc. Similarly, lines BE and AD intersect at another point in the background area between the ring and middle fingers, not the palm; we call this point Qe.
[0105] d. Determine the palm orientation and palm deflection angle based on the coordinates of intersection point Qe and intersection point Qc;
[0106] e. When the palm orientation and palm angle do not meet the recognition requirements, determine the horizontal axis offset parameter and / or vertical axis offset parameter based on the palm orientation and palm angle, generate posture adjustment information based on the offset parameter, control the stepper motor to adjust the horizontal conveyor belt and / or vertical conveyor belt, and then re-acquire the image.
[0107] Figure 10 illustrates scenarios with the palm tilted to the left and the palm turned upwards. The left image shows the scenario with the palm tilted to the left. As can be seen, point Qc leaves the background area between the index and middle fingers (not the palm's background) and lands on the index finger. Point Qe leaves the background area between the ring and middle fingers (not the palm's background) and lands on the middle finger. Therefore, we only need to determine the landing points of the two pixels Qc and Qe to determine the palm's orientation and approximate tilt angle.
[0108] The formula for finding the coordinates of the intersection points Qc and Qe, taking point Qc as an example, with the coordinates of key points A(Xa,Ya), B(Xb,Yb), and C(Xc,Yc), can be used to find the equation of line AC using the two-point form: (Yb-Ya)*x-(Xb-Xa)*y+(Xb*Ya–Yb*Xa)=0
[0109] Similarly, the equation of line BD is: (Yd-Yb)*x-(Xd-Xb)*y+(Xd*Yb–Yd*Xb)=0
[0110] Therefore, we can construct a system of two linear equations in two variables to find the coordinates of the intersection point.
[0111] It should be noted that the x and y values obtained at this point are usually not integers, but the pixel coordinates are integers. Therefore, subsequent steps can simply round x and y.
[0112] In step d, different judgment and correction methods are used for offsets in different directions and angles. Specifically, the horizontal axis offset parameters are determined based on the palm orientation and palm deflection angle, including:
[0113] 1. When the intersection point Qc is found to fall within the pixel area of the index finger and the intersection point Qe is found to fall within the pixel area of the middle finger, the palm is determined to be offset to the left relative to the aperture.
[0114] In this situation, the adjustment parameters can be determined based on the previously set relationship between the first stepper motor and the gear. For example, control the first stepper motor to rotate forward 0.25 revolutions, the transverse conveyor belt to move the palm print acquisition component to the left, then the camera to adjust to the right, and then re-acquire the image.
[0115] 2. When the intersection point Qc is found to fall within the pixel area of the ring finger and the intersection point Qe is found to fall within the pixel area of the middle finger, it is determined that the palm is offset to the right relative to the aperture.
[0116] In this situation, the first stepper motor can be reversed by 0.25 revolutions, the transverse conveyor belt can be used to move the palm print acquisition component to the right, the camera angle can be adjusted to the left, and then the image can be re-acquired.
[0117] For scenarios that require pitch angle adjustment, that is, determining the longitudinal axis offset parameter based on the palm orientation and palm deviation angle, including:
[0118] First, it is necessary to clarify a premise of this application. The ratio between the length of a person's palm and the length of the middle finger is approximately between 1:1 and 1.2:1. As shown in the right side of Figure 2, it is a picture where the palm is relatively above the camera. The length of the middle finger is significantly less than the length of the palm, and the ratio does not meet the range between 1:1 and 1.2:1. Similarly, when the palm is relatively below the camera, the length of the middle finger will be significantly greater than the length of the palm. Thus, this step becomes obtaining the ratio of the palm length to the middle finger length.
[0119] 1. Set the center point coordinates of the line connecting key points A and B as Qz, and the coordinate is expressed as Qz((Xa + Xb) / 2, (Ya + Yb) / 2); set the first distance Sdf between key points D and F, which is expressed as follows:
[0120] Set the second distance Sqf between key points Qz and F, which is expressed as follows:
[0121] 2. Determine the ratio P of the palm length to the middle finger length according to the ratio of the first distance to the second distance, which is expressed as follows: P = Sqf / Sdf
[0122] 3. When P > 1.2, it indicates that the palm length is greater than the middle finger length, and the palm is relatively above the aperture; control the longitudinal conveyor belt to drive the palm print acquisition component to move upward, and then control the camera angle to adjust downward;
[0123] 4. When P < 1, it indicates that the palm length is less than the middle finger length, and the palm is relatively below the aperture; control the longitudinal conveyor belt to drive the palm print acquisition component to move downward, and then control the camera angle to adjust upward.
[0124] If the measurement result satisfies 1 < P < 1.2, it means that the angle of the current picture acquisition and detection is appropriate. It should be noted that there are also special groups of people whose ratio between the palm length and the middle finger length is not between 1:1 and 1.2:1. However, the people in this situation are actually still close to this ratio. At this time, 1 < P < 1.2 is still used as the standard camera angle judgment value. In this case, the deviation angle of the captured picture is very slight and does not affect the image quality.
[0125] Figure 11 shows the algorithm flowchart of the palmprint acquisition method provided in the embodiments of this application. The image acquisition module is the acquisition and detection process of the aperture component and the camera module. After acquiring an image frame, the palm shape is determined by the algorithm module of the main control chip, and then the key point information is extracted. Then, based on the position of the Qc and Qe coordinate points, it is determined whether the first stepper motor (stepper motor A) needs to be activated for lateral posture adjustment, and whether the second stepper motor (stepper motor B) needs to be activated for longitudinal posture adjustment.
[0126] In addition, this application also describes the premise of detecting the number of key points in step S2, the purpose of which is to ensure that the integrity of the palm meets the requirements, especially in the scenario where the palm is too close to capture the whole picture. In this case, it is necessary to use the palmprint acquisition component itself to focus and complete the panoramic shooting. After ensuring that the whole picture of the palm is captured, the palm posture angle is calculated.
[0127] This application also discloses a flowchart of a non-contact palmprint acquisition method, applied to the aforementioned palmprint acquisition device. Figure 8 is a flowchart of the non-contact palmprint acquisition method provided in this application embodiment, which includes the following steps:
[0128] S1. Collect and extract palmprint images according to the image acquisition instructions, identify the pixel information of the palmprint images, and determine the number of key points on the palm and the pixel coordinate data of the key points on the palm.
[0129] Based on the above device, the PC sends the image acquisition command to the image acquisition device via the USB interface. After receiving the image acquisition command, the main control chip on the device turns on the CMOS image sensor and LED beads to start acquiring palm prints. At this time, the palm should be placed in front of or above the convex lens to capture a frame of the image.
[0130] Next, the histogram of this frame is obtained through image processing algorithms, the palm threshold is calculated, and the image is binarized based on the obtained threshold to distinguish the palm from the background and extract the palmprint image.
[0131] When a palm print image contains images of a hand, it can be identified through pixel analysis.
[0132] In this embodiment, the fingertip and wrist tip can be set as key points, and the position coordinates of these key points can be determined for subsequent position determination.
[0133] S2. Calculate the completeness of the palm image and the palm position based on the number of key points and pixel coordinates of the palm.
[0134] The completeness of the palm is determined by the distance between the palm and the convex lens. When the distance is appropriate, a complete palm image can be captured. When the distance is too far, a complete palm image cannot be captured, which will result in the loss of key points. The position of the palm can be determined based on the lost key points.
[0135] S3. When the palm print image captured by the camera does not meet the recognition requirements, the adjustment parameters of the aperture gear in the non-contact palm print acquisition device are calculated based on the palm position, and the aperture focal length and depth of field are adjusted to obtain a complete palm print image.
[0136] For incomplete palm print images, appropriate adjustment parameters can be calculated based on the palm's position. Similarly, for complete palm print parameters, if image sharpness is insufficient due to distance, the aperture adjustment parameters are also calculated based on the palm's position. For example, if the palm print is slightly to the left, the aperture is directly adjusted to re-acquire the image and include the palm; if the palm print is severely to the left, a voice prompt will remind the user to move to the right. When the palm is too far away, resulting in a small image, the aperture is reduced to decrease the depth of field, allowing for the capture of the optimal palm print image.
[0137] In some implementations, calculating the completeness of a hand image based on the number of key points and pixel coordinates may include the following steps:
[0138] 1. Define the key points A(Xa,Ya) at the base of the thumb, B(Xb,Yb) at the tip of the thumb, C(Xc,Yc) at the tip of the index finger, D(Xd,Yd) at the tip of the middle finger, E(Xe,Ye) at the tip of the ring finger, and F(Xf,Yf) at the tip of the little finger.
[0139] 2. After extracting the palm print image, identify all key points and their corresponding coordinates based on pixel information;
[0140] 3. When the palm image contains six key points, it indicates that the palm image is complete. Calculate the distance S between endpoints A and D. AD ; indicates the following:
[0141] 4. When S AD When the value is within the first preset range, it indicates that the size of the palm is close to the image size, and the image is captured and generated.
[0142] 5. When S AD When the value is within the first preset range but outside the second preset range, the palm image is too small, according to S. AD The value determines the adjustment parameters, and controls the stepper motor to rotate the aperture gear in the forward direction, thus bringing the depth of field closer;
[0143] 6. When key points are missing in the palm image, the offset parameters are determined based on the finger positions corresponding to the key points, and the posture adjustment information is generated based on the offset parameters. The stepper motor is then controlled to correct the deviation before the image is re-acquired and recognized.
[0144] Specifically, for cases lacking key points, the focus is on how to locate the hand position and how to make a judgment. Under normal logic, when all six key points are not detected, it indicates that the hand's proximity exceeds a set threshold and the hand size exceeds the image size. In this case, the user can be prompted to move the hand back. This application can generate pose adjustment information to reduce the aperture and increase the depth of field based on the number of missing key points. For cases exceeding the adjustment range, the user is prompted to move the hand back. When the detection result lacks key point F or key point B, it indicates that the hand shifts to the sides. The user can be reminded to move to the corresponding side. This application generates pose adjustment information to reduce the aperture and increase the depth of field based on the number of missing key points. Similarly, when the detection result lacks key point A, or lacks both key points A and B, or only contains key points A and B, it indicates that the hand is severely shifted vertically. This situation exceeds the aperture pose adjustment range, and the user is prompted with the corresponding adjustment gesture.
[0145] To facilitate scene description, this application further optimizes the algorithm and makes corresponding pose adjustment strategies based on different key points. Figure 12 shows a schematic diagram of different hand placement scenarios.
[0146] Key points A, B, C, D, E, and F can be categorized into the following scenarios:
[0147] Scenario 1: The results did not detect these six key points. This means that the size of the captured hand exceeds the image size of 640*480;
[0148] Scenario 2: The result does not detect key point F or the algorithm does not detect key point B. This means that the palm is not in the center of the image, and the palm is slightly to the left or right.
[0149] Scenario 3: The result did not detect key points F and E, or the algorithm did not detect key points B and C. This means that the palm is not in the center of the image, and the palm is moderately deviated to the left or right.
[0150] Scenario 4: The result did not detect key points A, B, and C, or the algorithm did not detect key points D, E, and F. This means that the palm is not in the center of the image, and the palm is severely deviated to the left or right.
[0151] Scenario 5: The result only detected keypoints A and B. This means that the palm is not in the center of the image, but rather slightly above it.
[0152] Scenario 6: Keypoint A was not detected. This means the palm is not in the center of the image; it is slightly lower.
[0153] Scenario Seven: Key points A and B are not detected, or only key point A is detected. This indicates that the palm is not in the middle of the image, and the palm is severely shifted downward or upward.
[0154] Scenario Eight: All key points are detected.
[0155] For the above eight scenarios, Figure 13 shows the posture adjustment strategy flowcharts for different palm placement scenarios.
[0156] For Scenarios One, Two, Three, and Six, which are classified as one category and belong to the situation where a certain part of the palm exceeds the image size. After the algorithm in the main control chip determines that it belongs to these scenarios, the main control chip will first read the scale value in the sensor, and then control the stepping motor to reverse half a turn, reduce the aperture, pull the depth of field farther, and then re - capture the image.
[0157] For Scenarios Four and Seven, since the palm posture is severely deviated, re - capturing the image is required. The user can adjust according to the prompt, or information such as payment failure can be reported.
[0158] For Scenario Five, the algorithm processing is as follows:
[0159] Because the pixel coordinates of the key point to a point at the bottom vertically are (0, Ya), the distance from key point A to the bottom pixel of the image is Ya.
[0160] If Ya > 240, it means that the palm image is severely shifted upward. The user can be prompted to adjust the palm downward, and then directly return to the step of re - capturing the image.
[0161] If 120 < Ya < 240, it means that the palm image is moderately shifted upward. The main control chip will first read the scale value in the sensor, and then control the stepping motor to reverse one turn, reduce the aperture, pull the depth of field farther, and then return to the step of re - capturing the image.
[0162] If Ya < 120, it means that the palm image is slightly shifted upward. The main control chip will first read the scale value in the sensor, and then control the stepping motor to reverse half a turn, reduce the aperture, pull the depth of field farther, and then return to the step of re - capturing the image.
[0163] For Scenario Eight, the algorithm processing is as follows:
[0164] Calculate the distance S between key point A and key point D AD ;
[0165] If 420 < S AD < 480, it means that the size of the palm image is close to the image size. The main control chip returns the current frame image to the host computer or PC via USB and prompts that the image capture is successful.
[0166] If 360 < S ADIf the value is less than 420, it indicates that the palm image is slightly too small. The main control chip will first read the scale value from the sensor, then control the stepper motor to rotate forward half a revolution, increase the aperture, and then return to the step of re-acquiring the image after narrowing the depth of field.
[0167] If 240 AD If the image size is less than 360, it indicates that the palm image is moderately small. The main control chip will first read the scale value from the sensor, then control the stepper motor to rotate one revolution forward, increase the aperture, and then return to the step of re-acquiring the image after narrowing the depth of field.
[0168] If 0 AD If the value is less than 240, it indicates that the palm image is moderately small. The main control chip will first read the scale value from the sensor, then control the stepper motor to rotate two clockwise, increase the aperture, and then return to the step of re-acquiring the image after narrowing the depth of field.
[0169] Specifically, after each scene assessment by the algorithm, if aperture adjustment is required, the main control chip will read the current scale reading through the sensor. If the current scale reading is already at the forward rotation limit, and the algorithm requires further forward rotation, it will directly return an image acquisition failure message. If the current scale reading is already at the reverse rotation limit, and the algorithm requires further reverse rotation, it will also directly return an image acquisition failure message.
[0170] In summary, the algorithm and device of this application can first identify the palm shape in the acquired image, and determine the palm orientation and palm angle based on the completeness of the palm and the recognition of key points. For cases where the palm is offset laterally, the aperture can be moved to the palm position by moving the device's lateral conveyor belt left and right, achieving angle correction. For cases where the palm is offset vertically, the aperture is moved to the palm position by moving the device's longitudinal conveyor belt up and down. Due to the curved conveyor belt design, this allows for posture correction over a wide range, ensuring the capture of complete and angularly accurate palmprint images.
[0171] Especially in scenarios where the palm is significantly off-center and key points are not fully recognized, the stepper motor in the palmprint acquisition component can be used independently for focus control. If the palm size is determined to be larger than the image size, it means the palm is too close to the camera. In this case, the camera aperture is reduced, increasing the depth of field until the palm size matches the image size. Conversely, if the palm size is smaller than the image size, the camera aperture is increased as needed, decreasing the depth of field until the palm size matches the image size. This solution maximizes the adaptive adjustment and acquisition of palm images through focus control, thereby improving the recognition success rate.
[0172] The palmprint acquisition device provided in this application embodiment can be applied to the palmprint acquisition method provided in the above embodiment. For relevant details, please refer to the above method embodiment. The implementation principle and technical effect are similar, and will not be repeated here.
[0173] It should be noted that the palmprint acquisition device provided in this embodiment is only illustrated by the above-described division of functional modules / units. In practical applications, the above functions can be assigned to different functional modules / units as needed, that is, the internal structure of the palmprint acquisition device can be divided into different functional modules / units to complete all or part of the functions described above. Furthermore, the implementation method of the palmprint acquisition method provided in the above-described method embodiments and the implementation method of the palmprint acquisition device provided in this embodiment belong to the same concept. The specific implementation process of the palmprint acquisition device provided in this embodiment is detailed in the above-described method embodiments and will not be repeated here.
[0174] This application also discloses a computer-readable storage medium. Specifically, the computer-readable storage medium is used to store a computer program, which, when executed by a processor, implements the methods described in the above-described method embodiments. Those skilled in the art will understand that implementing all or part of the processes in the methods described in the above-described embodiments of this application can be accomplished by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.
[0175] This specific embodiment is merely an explanation of the present invention and is not intended to limit the invention. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they are within the scope of the claims of the present invention.
Claims
1. A palmprint acquisition device, characterized in that, The device includes a longitudinal conveyor belt (10), a transverse conveyor belt (20), and a support frame (70); a palm print acquisition component (60) is fixedly installed at the center of the transverse conveyor belt (20); the belt body of the transverse conveyor belt (20) is fitted in a first sliding groove (30), and the first sliding groove (30) is fixedly installed on the longitudinal conveyor belt (10); the belt body of the longitudinal conveyor belt (10) is fitted in a second sliding groove (40), and the second sliding groove (40) is fixedly installed on the support frame (70); The transverse conveyor belt (20) is controlled to slide laterally by a first stepper motor (50), and the longitudinal conveyor belt (10) is controlled to slide longitudinally by a second stepper motor; When the palm print image acquired by the palm print acquisition component (60) is offset, the longitudinal conveyor belt (10) and / or the transverse conveyor belt (20) are controlled to move in the corresponding directions to adjust the shooting position.
2. The palmprint acquisition device according to claim 1, characterized in that, The longitudinal conveyor belt (10) and the transverse conveyor belt (20) are respectively arc-shaped structures and are respectively fitted into the first arc-shaped sliding groove (30) and the second arc-shaped sliding groove (40).
3. The palmprint acquisition device according to claim 2, characterized in that, The legs of the first sliding groove (30) are fixedly installed on the longitudinal conveyor belt (10). An inner cavity is provided between the groove and the legs. A first gear (69) that is connected to the first stepper motor (50) is installed in the inner cavity. The bottom of the transverse conveyor belt (20) is threaded, and the first gear (69) meshes with the thread of the transverse conveyor belt (20) to drive the transverse conveyor belt (20) to move laterally.
4. The palmprint acquisition device according to claim 2, characterized in that, The legs of the second sliding groove (40) are fixedly installed on the support frame (70). An inner cavity is provided between the groove and the legs. A second gear (41) that is connected to the second stepper motor is installed in the inner cavity. The bottom of the longitudinal conveyor belt (10) is threaded, and the second gear (41) meshes with the thread of the longitudinal conveyor belt (10) to drive the longitudinal conveyor belt (10) to move longitudinally.
5. The palmprint acquisition device according to any one of claims 1-4, characterized in that, The palmprint acquisition component (60) includes a cylindrical housing, a prism (67) is installed at the axial position at the bottom of the housing, and a camera (68) is installed on the side wall of the housing. Light is incident along the axis of the housing, and after passing through the prism (67), it is reflected to the camera (68) to acquire a palmprint image. An aperture assembly (65) is fixedly installed on the outside of the prism (67), and an aperture gear (62) with adjustable aperture size is sleeved on the outside of the aperture assembly (65); a convex lens (61) is installed above the aperture assembly (65), and the convex lens (61) is embedded in the aperture assembly (65) and the entrance of the housing; When the palm print image captured by the camera (68) does not meet the recognition requirements, the aperture gear (62) is controlled to rotate forward or backward according to the size of the palm print image, thereby adjusting the aperture focal length and depth of field.
6. The palmprint acquisition device according to claim 5, characterized in that, The radial dimensions of the aperture assembly (65) and the prism (67) are smaller than the inner diameter of the cylindrical shell; an LED bead (64) is provided on the outer edge of the entrance of the shell; A stepper motor (63) is also installed on the inner side of the bottom of the housing. A gear is installed on the output shaft of the stepper motor (63) and meshes with the aperture gear (62) on the outer edge of the aperture assembly (65).
7. The palmprint acquisition device according to claim 6, characterized in that, A sensor (66) is installed on the inner wall of the housing at the same height as the aperture gear (62) to collect the aperture tooth pattern in real time.
8. The palmprint acquisition device according to claim 5, characterized in that, The cross-section of the prism (67) is a right triangle with two right-angled sides of 45 degrees. The incident light is reflected horizontally by the oblique surface and then transmitted to the camera (68).
9. A palmprint acquisition method, characterized in that, The method is used in a palmprint acquisition device, and the method includes: According to the image acquisition instructions, the palm print image is acquired and extracted, the pixel information of the palm print image is identified, and the number of key points of the palm and the pixel coordinate data of the key points of the palm are determined; the key points of the palm include the fingertips, the finger joints, and the wrist joints. The completeness of the palm image and the palm angle orientation are calculated based on the number of key points and pixel coordinates of the palm. When the palmprint image captured by the camera does not meet the recognition requirements, the adjustment parameters of each gear in the palmprint acquisition device are calculated based on the offset position of the palm angle, and the aperture acquisition position is adjusted to obtain the palmprint image at the target angle.
10. The method according to claim 9, characterized in that, The calculation of the completeness of the palm image and the palm orientation based on the number of key points and pixel coordinates of the palm includes: Define the key points A(Xa,Ya) at the base of the thumb, B(Xb,Yb) at the tip of the thumb, C(Xc,Yc) at the tip of the index finger, D(Xd,Yd) at the tip of the middle finger, E(Xe,Ye) at the tip of the ring finger, and F(Xf,Yf) at the joint end of the little finger. After extracting the palmprint image, all key points and corresponding coordinate information are identified based on pixel information; When the palm image contains six key points, it indicates that the palm image is complete. Calculate the coordinates of the intersection point Qe formed by the line connecting key points A and D and the line connecting key points B and E, and the coordinates of the intersection point Qc formed by the line connecting key points A and C and the line connecting key points B and D. Determine the palm orientation and palm deflection angle based on the coordinates of intersection point Qe and intersection point Qc. When the palm orientation and palm angle do not meet the recognition requirements, the horizontal axis offset parameter and / or vertical axis offset parameter are determined based on the palm orientation and palm angle, and the posture adjustment information is generated based on the offset parameter. The stepper motor is then controlled to adjust the horizontal conveyor belt and / or vertical conveyor belt before re-image acquisition.
11. The method according to claim 10, characterized in that, The horizontal axis offset parameters are determined based on the palm orientation and palm angle, including: When the intersection point Qc is identified to fall within the pixel area of the index finger and the intersection point Qe is identified to fall within the pixel area of the middle finger, the palm is determined to be offset to the left relative to the aperture; the horizontal conveyor belt is controlled to move the palmprint acquisition component to the left, thereby adjusting the camera angle to the right; When it is identified that the intersection point Qc coordinates fall within the pixel area of the ring finger and the intersection point Qe coordinates fall within the pixel area of the middle finger, it is determined that the palm is offset to the right relative to the aperture; the horizontal conveyor belt is controlled to move the palmprint acquisition component to the right, and then the camera angle is adjusted to the left. The vertical axis offset parameters are determined based on the palm orientation and palm deflection angle, including: Set the center point coordinates of the line connecting keypoints A and B as Qz, represented as Qz((Xa+Xb) / 2,(Ya+Yb) / 2); set the first distance Sdf between keypoints D and F as follows: Set the second distance Sqf between keypoints Qz and F, as follows: The ratio P between the palm length and the middle finger length is determined by the ratio of the first distance to the second distance, as shown below: P = Sqf / Sdf When P>1.2, it indicates that the length of the palm is greater than the length of the middle finger, and the palm is slightly higher than the aperture; control the longitudinal conveyor belt to move the palmprint acquisition component upward, and then control the camera angle to adjust downward; When P<1, it indicates that the length of the palm is less than the length of the middle finger, and the palm is lower than the aperture; the longitudinal conveyor belt is controlled to move the palmprint acquisition component downward, and then the camera angle is controlled to adjust upward.
12. A palmprint acquisition method, characterized in that, The method is used in a palmprint acquisition device, and the method includes: According to the image acquisition instructions, the palm print image is acquired and extracted, the pixel information of the palm print image is identified, and the number of key points of the palm and the pixel coordinate data of the key points of the palm are determined; the key points of the palm are the fingertips and the wrist bottom end near the base of the thumb. The completeness of the palm image and the position of the palm are calculated based on the number of key points and pixel coordinates of the palm. When the palm print image captured by the camera does not meet the recognition requirements, the adjustment parameters of the aperture gear in the non-contact palm print acquisition device are calculated based on the palm position, and the aperture focal length and depth of field are adjusted to obtain a complete palm print image.
13. The method according to claim 12, characterized in that, After receiving the image acquisition command, the main control chip activates the sensor and LED beads in the non-contact palm print acquisition device. The sensor captures and identifies the first aperture tooth pattern on the outer side of the aperture assembly, and the LED beads provide supplementary lighting to the palm area.
14. The method according to claim 12, characterized in that, The calculation of the completeness of the palm image and the palm position based on the number of key points and pixel coordinates of the palm includes: Define the key points A(Xa,Ya) at the base of the thumb, B(Xb,Yb) at the tip of the thumb, C(Xc,Yc) at the tip of the index finger, D(Xd,Yd) at the tip of the middle finger, E(Xe,Ye) at the tip of the ring finger, and F(Xf,Yf) at the tip of the little finger. After extracting the palmprint image, all key points and corresponding coordinate information are identified based on pixel information; When the palm image contains six keypoints, indicating that the palm image is complete, calculate the distance S between endpoints A and D. AD ; indicates the following: When S AD When the value is within the first preset range, it indicates that the size of the palm is close to the image size, and the image is captured and generated. When S AD When the value is within the first preset range but outside the second preset range, the palm image is too small, according to S. AD The value determines the adjustment parameters, and controls the stepper motor to rotate the aperture gear in the forward direction, thus bringing the depth of field closer; When key points are missing in the palm image, the offset parameters are determined based on the finger positions corresponding to the number of key points, and the pose adjustment information is generated based on the offset parameters. The stepper motor is then controlled to adjust the aperture gear before re-capturing the image.
15. The method according to claim 14, characterized in that, When key points are missing in the palm image, the offset parameters are determined based on the finger positions corresponding to the key points, including: When all six key points are not detected, the hand is indicated to be too close to the set threshold and the hand size is too large to fit the image. Based on the number of missing key points, pose adjustment information is generated to reduce the aperture and increase the depth of field. When the detection result is missing key point F or key point B, the palm is instructed to shift to both sides, and pose adjustment information is generated to reduce the aperture and increase the depth of field based on the number of missing key points. When the detection result is missing key point A, or missing both key points A and B, or only contains key points A and B, the palm is indicated to shift up and down. Gesture correction information is generated based on the palm position so that the image can be re-captured.
16. A computer device, characterized in that, The computer device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the palmprint acquisition method as described in any one of claims 9 to 15.
17. A computer-readable storage medium, characterized in that, The readable storage medium stores at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the palmprint acquisition method as described in any one of claims 9 to 15.