Multi-camera palm recognition device
By employing a multi-camera palm recognition solution in the palm recognition device, combining infrared and RGB camera groups with a ranging and supplementary lighting module, the problem of high requirements for user palm placement is solved, achieving efficient recognition under flexible palm postures, and improving user experience and recognition accuracy.
Patent Information
- Application Number
- CN202410802016.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-20
- Publication Date
- 2025-12-23
AI Technical Summary
Existing palm recognition devices have high requirements for the placement of the user's palm, resulting in a poor user experience.
The device employs a multi-camera hand recognition system, which includes a base and camera groups distributed in different positions. Each camera group consists of an infrared camera and an RGB camera with parallel optical axes to adapt to different hand postures. Combined with a ranging module and a supplementary lighting module, it optimizes image acquisition.
It improves the applicability and user experience of palm recognition, ensuring accurate image acquisition under different palm postures and enhancing recognition performance.
Smart Images
Figure CN121191201A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the field of biometric identification technology, and particularly relates to a multi-camera palm identification device. BACKGROUND
[0002] Biometric identification technology verifies identity by detecting unique physiological or behavioral characteristics of the human body, and has advantages such as being difficult to replicate, not needing to be carried, and being convenient to use. With these unique advantages, the technology has been widely used in many fields such as attendance, access control, medical care, consumption, etc. Among them, palm vein and palm print identification has the characteristics of strong anti-counterfeiting and living body detection, and the security and identification accuracy are higher than those of traditional body surface feature identification technology. However, such identification devices have strict requirements for the position and angle of the palm, and the image quality will be affected if the palm is tilted, not in the appropriate central position, too far or too close, etc., thereby reducing the identification accuracy. Therefore, a palm identification device with lower requirements for user palm placement and better user experience is needed. SUMMARY
[0003] The present application aims to at least solve one of the above technical defects, in particular, the problem of high requirements for user palm placement and poor user experience of the palm identification device in the prior art.
[0004] The present application provides a multi-camera palm identification device, comprising: a base; a plurality of camera groups, each of which is arranged at a different position of the base, each camera group comprising an infrared camera and an RGB camera, and the optical axes of the infrared camera and the RGB camera in the same group are parallel and respectively perpendicular to different preset palm planes.
[0005] In one of the embodiments, the optical axes in different camera groups are convergent.
[0006] In one of the embodiments, the plurality of camera groups comprises at least one pair of symmetric groups, and the two camera groups in the same symmetric group are symmetrically arranged on the base.
[0007] In one of the embodiments, the angle between the optical axes of the two camera groups in the same symmetric group satisfies wherein A is the angle, H is the distance between the two camera groups in the same symmetric group, and L is the distance from the convergence center to the line connecting the two camera groups in the same symmetric group.
[0008] In one of the embodiments, the multi-camera palm identification device further comprises a distance measuring module and a control module; the distance measuring module is connected with the control module and is used for detecting the distance between the object to be identified and the multi-camera palm identification device; the control module is connected with each camera group and is used for controlling each camera group to perform image acquisition when the distance is within a set distance range.
[0009] In one of the embodiments, the distance measuring module is arranged at the center of the base.
[0010] In one of the embodiments, the distance measuring module comprises infrared distance measurement and laser distance measurement.
[0011] In one of the embodiments, the multi-camera palm recognition device further comprises a plurality of infrared light supplement modules, each of which is arranged around the plurality of camera groups.
[0012] In one of the embodiments, the multi-camera palm recognition device further comprises a plurality of RGB light supplement modules, each of which is arranged around the plurality of camera groups.
[0013] In one of the embodiments, the wavelength of the infrared camera comprises 850nm or 940nm.
[0014] From the above technical solutions, the embodiments of the present application have the following advantages:
[0015] The scheme proposes a multi-camera palm recognition device, the core structure of which comprises a base and a plurality of camera groups distributed at different positions of the base, each of which is composed of an infrared camera and an RGB camera. The infrared camera is used to collect the palm vein distribution image, and the RGB camera is used to obtain the palm surface texture image, and the information of the two is complementary to each other. The optical axes of the infrared and RGB cameras in the same camera group are parallel, and the optical axes of different camera groups are respectively perpendicular to different preset palm planes, so as to adapt to the scanning of different palm postures. The scheme better solves the limitations of the traditional single-view palm recognition, improves the applicability of palm recognition, the palm postures available for the user are more flexible, improves the user experience, and the dual cameras in the camera group also ensure the recognition effect. BRIEF DESCRIPTION OF DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.
[0017] Figure 1 The structure schematic diagram of the multi-camera palm recognition device in one embodiment of the present application;
[0018] Figure 2 The schematic diagram of the camera group arrangement mode in one embodiment of the present application;
[0019] Figure 3 The structure schematic diagram of the multi-camera palm recognition device in another embodiment of the present application;
[0020] Figure 4 Figure 1 is a structural schematic diagram of a multi-camera palm recognition device according to an embodiment of the present application;
[0021] Figure 5 Figure 2 is a schematic diagram of the included angle of a camera group in a multi-camera palm recognition device according to an embodiment of the present application;
[0022] Figure 6 Figure 3 is a schematic diagram of the included angle of a camera group in a multi-camera palm recognition device according to another embodiment of the present application;
[0023] BRIEF DESCRIPTION OF DRAWINGS: 10-camera group, 110-infrared camera, 120-RGB camera, 20-distance measuring module, 30-infrared light supplement module, 40-RGB light supplement module. DETAILED DESCRIPTION
[0024] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.
[0025] It should be noted that similar reference numerals and letters indicate similar items in the following drawings, and therefore, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings.
[0026] In the description of the embodiments of the present application, it should be noted that if the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product is usually placed, and are only used to facilitate the description of the present application and simplify the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, if the terms "horizontal", "vertical", "overhanging" and the like appear, they do not mean that the component must be absolutely horizontal or overhanging, but can be slightly inclined. For example, "horizontal" only means that its direction is relatively more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly inclined. In the description of the embodiments of the present application, "a plurality of" represents at least 2.
[0027] The present application provides a multi-camera palm recognition device, please refer to Figure 1The device includes a base and multiple camera groups 10. The base serves as the mounting platform for the entire device, and all necessary modules are mounted on it. The device has at least two camera groups 10, positioned at different locations on the base. Each camera group 10 includes an infrared camera 110 and an RGB camera 120. The infrared camera 110 detects palm vein distribution, while the RGB camera 120 detects palm print distribution. The positions of the infrared camera 110 and the RGB camera 120 within the same camera group 10 can be interchanged. This device can simultaneously combine palm vein and palm print information for identity verification. Vein patterns possess high uniqueness and randomness, making them one of the most reliable biometric features, while palm prints can complement palm vein information, enhancing the verification effect.
[0028] In this embodiment, multiple camera groups 10 are used to face each of the user's hand gestures. Specifically, traditional hand recognition devices use only one camera module, requiring the user's palm plane to be perpendicular to the optical axis of that camera module to capture the clearest image. This places strict requirements on the user's hand gesture. This embodiment, however, uses multiple camera groups 10, each corresponding to a specific hand gesture, giving the user more options in terms of hand gesture. Therefore, the optical axes of the infrared camera 110 and the RGB camera 120 within the same group are parallel. By setting the tilt angle between the camera module and the base, the optical axis of the camera module can be made perpendicular to a preset hand plane. The preset hand plane can be the hand plane corresponding to the high-frequency gesture used by the user during scanning. Figure 1 The multi-camera palm recognition device shown has two camera groups 10, one on the left and one on the right, to handle scenarios where users often tilt their hands to the left or right during scanning. This ensures that regardless of whether the palm is tilted to the left or right, a camera module can capture palm prints and veins at a relatively direct angle. The specific number of camera modules and their corresponding tilt angles can be tailored to factors such as device cost and user habits.
[0029] The scheme proposes a multi-camera palm recognition device, the core structure of which includes a base and a plurality of camera groups 10 distributed at different positions of the base, each camera group 10 being composed of an infrared camera 110 and an RGB camera 120. The infrared camera 110 is used to collect palm vein distribution images, and the RGB camera 120 is used to collect palm surface texture images, and the information of the two is complementary to each other. The optical axes of the infrared and RGB cameras 120 in the same camera group 10 are parallel, and the optical axes of different camera groups 10 are respectively perpendicular to different preset palm planes, so that the scanning of different palm postures can be adapted. The scheme better solves the limitations of traditional single-view palm recognition, improves the applicability of palm recognition, and makes the palm postures used by the user more flexible, improves the user experience, and the dual cameras in the camera group 10 also ensure the recognition effect.
[0030] In one embodiment, the optical axes of different camera groups 10 are convergent. This embodiment proposes that the optical axes of the infrared and RGB cameras 120 inside each camera group 10 are arranged in a convergent manner. The convergent arrangement here does not require all the optical axes to converge at the same point in space. Only the optical axes of all camera groups 10 need to pass through the target area, which is the position of the human hand fully facing the multi-camera palm recognition device at a suitable distance. Generally, the size of the target area can be obtained according to the size of the user's palm and by setting a reasonable expansion margin. The target area is moved to a preset distance in the direction perpendicular to the base from the center of the multi-camera palm recognition device, so as to determine the position of the target area in space. As long as the optical axes of all camera groups 10 pass through the target area, the user's palm will be tilted in different directions to a certain extent when scanning. As long as the optical axis can pass through the target area, this camera group 10 will correspond to a posture that the user may use, and through the reasonable setting of multiple camera groups 10, it can be ensured that the user can accurately scan in most angles. As shown in Figure 2 Figure 2 The block in the middle represents the camera group 10, the dashed line represents the optical axis, and the black solid line represents the projection of the target area. Figure 2 The left side is that the optical axes of the camera groups 10 are convergent, Figure 2 The right side has two camera groups 10 whose optical axes cannot pass through the target area, so they are divergent.
[0031] In one embodiment, the plurality of camera groups 10 includes at least one pair of symmetric groups, and the two camera groups 10 in the same symmetric group are symmetrically arranged on the base. It can be understood that in order to better cover the palm posture, the camera groups 10 can be symmetrically arranged. As shown in Figure 1 As shown, two camera groups 10 are included in total, which are symmetrically distributed left and right with the center of the base as the symmetric point, and the optical axes are all deflected to the middle part of the base, showing a converging state. This kind of structure can cope with the situation that the palm posture is often tilted to the left or to the right. As shown in FIG. 2B, Figure 3 As shown, three camera groups 10 are included in total, one of which is arranged at the center of the base, and the other two are symmetrically distributed up and down with the center of the base as the symmetric point, and the optical axes are all deflected to the middle part of the base. This kind of structure can cope with the situation that the palm posture is often tilted upwards or upwards. Figure 4 As shown, four camera groups 10 are included in total, two of which are symmetrically distributed left and right with the center of the base as the symmetric point, and the other two are symmetrically distributed up and down with the center of the base as the symmetric point. And the optical axes of the four camera groups 10 are all deflected to the middle part of the base. This kind of structure can cope with the situation that the palm posture is often tilted upwards, upwards, to the left or to the right.
[0032] In one embodiment, the angle between the optical axes of the two camera groups 10 in the same symmetric group satisfies Wherein, A is the angle, H is the distance between the two camera groups 10 in the same symmetric group, and L is the distance from the convergence center to the line connecting the two camera groups 10 in the same symmetric group.
[0033] It can be understood that the convergence center here is a point at a preset distance from the center of the base. The distance between the hand of a general user and the center of the base is within the interval with the preset distance as the midpoint. This convergence center can represent the position of the user's palm. This embodiment is to ensure that all symmetric groups can converge to the same convergence center. This kind of design has the best scanning effect. For the structure in Figure 1 , please refer to Figure 5 , the preset distance is 20 cm, the distance between the two camera groups 10 is 7 cm, and the angle A is calculated to be 21°. Similarly, for the structures in Figure 3 and Figure 4 , please refer to Figure 6 , the angle A can be calculated to be 44°.
[0034] In one embodiment, the multi-camera palm recognition device further includes a distance measuring module 20 and a control module. The distance measuring module 20 is connected with the control module, and is used to detect the distance between the object to be recognized and the multi-camera palm recognition device. The control module is connected with each camera group 10, and is used to control each camera group 10 to perform image acquisition when the distance is within a set distance range.
[0035] It can be understood that the purpose of introducing the distance measuring module 20 is to determine the distance between the to-be-identified object (such as a palm) and the device, so as to determine whether to start the imaging process. Moreover, long-term opening of the camera group 10 is easy to cause waste of energy and affect the service life of the camera group 10. Therefore, only when the to-be-identified object enters the set distance range, the control module controls each camera group 10 to start working, and each camera group 10 will be in a dormant state at other times. Each camera group 10 can synchronously perform image acquisition and return the acquired images to the control module for further processing.
[0036] In one of the embodiments, the distance measuring module 20 is arranged at the center of the base. Arranging the distance measuring module 20 at the center can more accurately measure the distance from the to-be-identified object to the entire device, avoiding the perspective deviation when arranged at a side. The center position is less likely to be blocked by the surrounding camera groups 10 or other components, which is conducive to ensuring the unobstructed distance measuring line of sight.
[0037] In one of the embodiments, the distance measuring module 20 includes infrared distance measurement and laser distance measurement. Infrared distance measurement and laser distance measurement are currently common optical distance measurement methods, in which the laser distance measurement has higher accuracy but is expensive. The infrared distance measurement and the laser distance measurement generally adopt the ToF principle, that is, the time required for the test light to fly to the object and then reflect back, and the distance is calculated based on the time and the speed of light.
[0038] In one of the embodiments, the multi-camera palm recognition device further includes a plurality of infrared light supplement modules 30, and each infrared light supplement module 30 is arranged around the plurality of camera groups 10.
[0039] It can be understood that under natural light, there may be a problem of poor shooting effect, and therefore, the embodiment is provided with a plurality of infrared light supplement modules 30 for light supplement. The infrared light supplement module 30 can be an infrared LED, which emits infrared light with the same wavelength as the infrared camera 110. The infrared light supplement module 30 is arranged around the plurality of camera groups 10, so that the infrared camera 110 in each camera group 10 has a chance to be supplemented with light. Specifically, the infrared light supplement module 30 can be four, which are arranged at the upper left, upper right, lower left and lower right positions. The appropriate auxiliary light source can compensate for the dark area of the image to obtain a high-quality image that is uniform, bright and low in noise.
[0040] In one of the embodiments, the multi-camera palm recognition device further includes a plurality of RGB light supplement modules 40, and each RGB light supplement module is arranged around the plurality of camera groups 10.
[0041] It can be understood that under natural light, there can be a problem of poor shooting effect, therefore, the embodiment sets a plurality of RGB light compensation modules 40 to compensate light. The RGB light compensation module 40 can be a white light or a three-color light LED. The RGB light compensation module 40 is arranged around the plurality of camera groups 10, so that the RGB camera 120 in each camera group 10 has the opportunity to be compensated for light. Specifically, the infrared light compensation module 30 can be arranged in succession on a rectangular profile, and the camera group 10 is located inside the rectangular profile. The appropriate auxiliary light source can compensate for the dark area of imaging to obtain a high-quality image that is uniform, bright and low noise.
[0042] In one of the embodiments, the wavelength of the infrared camera 110 includes 850nm or 940nm.
[0043] The near-infrared light of 850nm and 940nm wavelengths has good transmission performance on human tissues. This enables them to more clearly penetrate the skin surface and image the blood vessels, veins and other structures inside the human body.
[0044] Finally, it should be noted that in this document, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.
[0045] The various embodiments in the specification are described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the various embodiments can be combined as needed, and the same and similar parts refer to each other.
[0046] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A multi-camera palm recognition device, comprising: The application relates to a multi-camera palm recognition device. The device comprises: a base; 2.The multi-camera palm recognition device of claim 1, wherein, a plurality of camera groups arranged at different positions of the base, each of the camera groups comprising an infrared camera and an RGB camera, and the optical axes of the infrared camera and the RGB camera in the same group being parallel and vertical to different preset palm planes.
3. The multi-camera palm recognition device of claim 2, wherein, The optical axes in different camera groups are convergent.
4. The multi-camera palm recognition device of claim 3, wherein, An angle between the optical axes of two camera groups in the same symmetry group satisfies Wherein, A is the angle, H is the distance between two camera groups in the same symmetry group, and L is the distance from the convergence center to the line between two camera groups in the same symmetry group.
5. The multi-camera palm recognition device of claim 1, wherein, At least one pair of symmetrical groups is included in the plurality of camera groups, and two camera groups in the same symmetrical group are symmetrically arranged on the base. The device further comprises a distance measuring module and a control module. The distance measuring module is connected with the control module and used for detecting the distance between an object to be identified and the multi-camera palm recognition device.
6. The multi-camera palm recognition device of claim 5, wherein, The control module is connected with each camera group and used for controlling each camera group to collect images when the distance is within a set distance range.
7. The multi-camera palm recognition device of claim 5, wherein, The distance measuring module is arranged at the center of the base. 8.The multi-camera palm recognition device of claim 1, wherein, The distance measuring module comprises infrared distance measurement and laser distance measurement. 9.The multi-camera palm recognition device of claim 1, wherein, The device further comprises a plurality of infrared light supplement modules, and each infrared light supplement module is arranged around the plurality of camera groups.
10. The multi-camera palm recognition device of claim 1, wherein, The device further comprises a plurality of RGB light supplement modules, and each RGB light supplement module is arranged around the plurality of camera groups. The wavelength of the infrared camera comprises 850nm or 940nm.