Image collection apparatus and biometric recognition device

Abstract

The present application belongs to the technical field of biometric recognition. Provided are an image collection apparatus and a biometric recognition device. The image collection apparatus comprises: a light source, a reflection array and an imaging component, wherein the reflection array is located on a light-emergent side of the light source; the light source is used for emitting light rays towards the reflection array; the reflection array is used for reflecting the light rays towards a palm to be recognized, and illuminating the palm to be recognized, so as to form at least one light spot pattern on the palm to be recognized; and the imaging component is used for receiving light rays reflected by a surface of the palm to be recognized, and outputting an image to be recognized that has the at least one light spot pattern. The image collection apparatus of the present application can avoid attacks from planar non-living palms such as paper prints and pictures, thereby achieving a good liveness detection effect.

Description

Image acquisition device and biometric recognition equipment

[0001] This application claims priority to Chinese patent application No. 202420169363.7 filed on January 23, 2024, with utility model name “Image Acquisition Device and Biometric Identification Device,” the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present application relates to the field of biometric identification technology, and in particular to an image acquisition device and a biometric identification device. Background Art

[0003] As convenient payment penetrates deeper and deeper into daily life, various biometric technologies are increasingly entering the field of identity recognition, and the trend of biometric technology replacing traditional identity authentication is becoming increasingly obvious.

[0004] Palm print and palm vein collection and recognition technology has gradually become a biometric technology that has received continuous attention at this stage, and biometric devices such as palm scanning devices have also emerged.

[0005] Summary of the Invention

[0006] The present application provides an image acquisition device and a biometric recognition device, which enable the biometric recognition device to detect whether the object entering the image acquisition stage is indeed a living user, rather than a paper printout, picture or palm model, and reject it from the recognition link.

[0007] The technical solution is as follows:

[0008] In one aspect, an image acquisition device is provided, comprising: a light source, a reflective array, and an imaging component;

[0009] The reflective array is located on the light-emitting side of the light source, the light source is used to emit light toward the reflective array, and the reflective array is used to reflect the light toward the palm to be identified and illuminate the palm to be identified, so as to form at least one light spot pattern on the palm to be identified;

[0010] The imaging component is used to receive the light reflected from the surface of the palm to be identified and output the image to be identified with the at least one light spot pattern.

[0011] On the other hand, a biometric identification device is provided, which includes the image acquisition device described in the present application.

[0012] The beneficial effects of the technical solution provided by this application include at least:

[0013] The image acquisition device of the present application includes a light source, a reflective array, and an imaging component. The light emitted by the light source first irradiates the surface of the reflective array, and the reflective array reflects the light toward the palm to be identified. On the one hand, it can illuminate the palm to be identified, ensuring that the imaging component can obtain a clear image to be identified. On the other hand, the reflective array forms at least one light spot pattern on the palm to be identified. When the light spot pattern shows different degrees of deformation, it indicates that the palm to be identified is uneven, and the palm to be identified can be judged as a real palm, thereby avoiding attacks from flat non-living palms such as paper printouts and pictures, and achieving better liveness detection effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] FIG1 is a schematic structural diagram of an image acquisition device provided in an embodiment of the present application;

[0015] FIG2 is a schematic diagram of an image to be recognized provided in an embodiment of the present application;

[0016] FIG3 is a schematic structural diagram of a reflective array provided in an embodiment of the present application;

[0017] FIG4 is a schematic structural diagram of an imaging assembly provided in an embodiment of the present application;

[0018] FIG5 is a structural block diagram of a biometric identification device provided in an embodiment of the present application.

[0019] The reference numerals in the figure represent respectively: 100, image acquisition device; 200, image processing unit; 300, palm to be identified; 400, identification unit; 1, light source; 2, reflection array; 20, light spot pattern; 21, reflection array element; 22, driving unit; 3, distance sensor; 4, imaging component; 41, optical lens; 42, circuit board; 43, photosensitive element. DETAILED DESCRIPTION

[0020] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0021] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in Figure 1, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.

[0022] It should be understood that in this application, "electrical connection" can be understood as the physical contact and electrical conduction of components; it can also be understood as the form in which different components in the circuit structure are connected through physical lines such as printed circuit board (PCB) copper foil or wires that can transmit electrical signals. "Communication connection" can refer to electrical signal transmission, including wireless communication connection and wired communication connection. Wireless communication connection does not require a physical medium and does not belong to a connection relationship that limits the product structure. "Connection" and "connected" can both refer to a mechanical connection relationship or a physical connection relationship, that is, A is connected to B or A and B are connected, which means that there is a fastening component (such as screws, bolts, rivets, etc.) between A and B, or A and B are in contact with each other and A and B are difficult to separate.

[0023] Unless otherwise defined, all technical terms used in the embodiments of the present application have the same meanings as commonly understood by those skilled in the art.

[0024] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0025] This embodiment relates to a biometric identification device, such as a palm scanning device, which includes a light source and a camera. The light source is used to illuminate the palm of the user. The camera is used to capture the user's palm, allowing the palm scanning device to recognize the user's palm features and then confirm the user's identity.

[0026] However, this biometric technology has both advantages and disadvantages. If forged, it can cause serious losses. Therefore, adding protection measures for biometric features has become a top priority. Enabling palm scanning devices to verify that the captured object is indeed a living person, rather than a paper printout, image, or palm model, is the most important security measure for biometric devices.

[0027] As shown in FIG1 and FIG2 , this embodiment provides an image acquisition device 100 for a biometric identification device such as a palm-swiping device. The image acquisition device 100 includes: a light source 1 , a reflective array 2 , and an imaging component 4 .

[0028] The reflective array 2 is located on the light-emitting side of the light source 1. For example, if the reflective array 2 is located in the outgoing light path of the light source 1, the light source 1 will emit light toward the reflective array 2. The palm-swiping window of the image acquisition device 100 is located in the reflective light path of the reflective array 2. As a result, the reflective array 2 reflects light toward the palm 300 to be identified, illuminating the palm 300 and forming at least one light spot pattern 20 on the palm 300. The imaging component 4 is located in the reflective light path of the palm-swiping window of the image acquisition device 100. Therefore, the imaging component 4 receives light reflected from the surface of the palm 300 to be identified and outputs an image to be identified with at least one light spot pattern 20.

[0029] Specifically, the image acquisition device 100 of this embodiment includes a light source 1, a reflective array 2, and an imaging assembly 4. Light emitted by the light source 1 first impinges on the surface of the reflective array 2, which then reflects the light toward the palm 300 to be identified, thereby illuminating the palm 300 and forming at least one light spot pattern on the palm 300. The light impinging on the palm 300 is also reflected by the palm 300 to the imaging assembly 4, ensuring that the imaging assembly 4 can capture a clear image of the palm 300.

[0030] If the light spot pattern exhibits varying degrees of deformation, it indicates that the palm 300 to be identified is uneven, and thus can be determined to be a real palm. On the other hand, if the light spot pattern exhibits little deformation, it indicates that the palm to be identified is flat, and thus can be determined to be a flat, non-live palm. Thus, using this image acquisition device for palm swipe recognition can avoid attacks from flat, non-live palms such as paper printouts and images, achieving better liveness detection results.

[0031] In some embodiments, there are multiple spot patterns, arranged relative to each other according to a characteristic positional relationship. Thus, when multiple spot patterns are projected onto a non-planar palm 300 to be identified, not only will the shape of each spot pattern change, but the distances between them will also vary due to differences in the curvature and depth of the palm 300 to be identified. By combining the variations in the individual spot patterns and the variations in distance between them, the shape data of the palm 300 to be identified can be accurately derived. This shape data can then be compared with the original data stored in a database to identify the user.

[0032] In some embodiments, the area of ​​the light spot pattern projected when the distance between the palm 300 to be identified and the image acquisition device 100 is a first distance is greater than the area of ​​the light spot pattern projected when the distance between the palm 300 to be identified and the image acquisition device is a second distance. Where the first distance is less than the second distance, the area of ​​the light spot pattern refers to the area ratio of the light spot pattern on the palm.

[0033] For example, if the palm 300 to be identified is relatively close to the image acquisition device 100, multiple light spot patterns with larger areas can be used for projection. This is because the palm 300 to be identified is non-planar, and its shape causes significant distance differences between various points on the palm 300 to be identified and the image acquisition device 100, which can cause deformation of the light spot. Furthermore, the larger the light spot, the easier it is to distinguish the deformation.

[0034] If the palm 300 to be identified is far away from the image acquisition device 100, the projection can be switched to multiple smaller light spot patterns. This is because when the palm 300 to be identified is far away from the image acquisition device 100, the height differences of the palm 300 itself (i.e., the height differences caused by the unevenness of the palm 300 surface) will cause deformation of the light spot pattern, which is difficult to distinguish. However, when the palm 300 to be identified is at the edge, the changes in the light spot pattern caused by the difference in depth of field between the front and back are easier to distinguish.

[0035] For example, when the palm 300 to be identified is relatively close to the image acquisition device 100, the reflective array element 2 may reflect multiple small-area light spot patterns toward the palm 300 to be identified. If the palm 300 to be identified is a live palm, some of the light spot patterns will not fall on the palm 300 to be identified, resulting in a larger depth of field, while other parts of the light spot patterns will fall on the palm 300 to be identified, resulting in a smaller depth of field. If the palm 300 to be identified is a non-live palm, such as a print or screen display, the depth of field of all the light spot patterns will be equal. Therefore, whether the palm to be identified is live or non-live is determined based on whether the depth of field of all the light spot patterns is equal.

[0036] Therefore, this embodiment can avoid forged palm attacks displayed through printing or screen by combining different light spot patterns and light spot pattern sizes, combined with changes in light spot shape or difference in front and back depth of field (light spot loss), and achieve better liveness detection effect.

[0037] In the past, biometric authentication devices have been compromised by prosthetics, typically by printing images on paper or displaying them on screen. Because prosthetics presented on paper or screen lack depth information, when projected onto a flat surface, the spot pattern remains unchanged and clearly differs from a real hand, making it easily distinguishable.

[0038] In some possible implementations, the light source 1 is an LED light source or a light-emitting diode. Visible light or near-infrared light is illustratively used. Visible light or near-infrared light can emit light of a specific wavelength at a certain angle. In accordance with the image capture requirements of the imaging component 4, different brightness variations can be achieved when driven by different currents and duty cycles.

[0039] In some possible implementations, the image to be identified includes palm print information and palm vein information, or may be one of them. For example, the image to be identified may be palm print information or palm vein information.

[0040] Palmprint information refers to the various lines on the palm surface from the fingertips to the wrist. Many of these features can be used for personal identification, including main lines, wrinkles, fine lines, ridge endings, and bifurcation points. Palmprint morphology is genetically controlled. Even if the skin peels off for some reason, the new lines retain their original structure. Everyone's palmprints are unique; even twins have similar, but never identical, lines. A person's identity can be determined using the line, point, texture, and / or geometric features of a palmprint.

[0041] Palm vein information is a type of vein, referring to the venous system within the palm of the human body. When using palm vein information for identity authentication, the image features of the palm vein are captured, which only exist when the palm is alive.

[0042] In other possible implementations, imaging component 4 includes an RGB camera or an infrared camera. The RGB camera can be used to capture color images with high accuracy. The RGB camera uses three different cables to provide three basic color components, acquiring the three color signals through three independent charge-coupled devices (CCDs).

[0043] In some possible examples, the image acquisition device 100 further includes a protective cover positioned between the reflective array 2, the imaging assembly 4, and the palm 300 to be recognized. For example, the protective cover covers the palm scanning window of the image acquisition device. For example, the base material of the protective cover should be a material with high light transmittance, such as PET (Polyethylene terephthalate), PC (Polycarbonate), or PMMA (polymethyl methacrylate).

[0044] In some embodiments, the brightness of at least one spot pattern is different from the brightness of other areas of the palm 300 to be identified, where the other areas refer to areas on the palm 300 to be identified excluding the spot pattern. The reflective array 2 can be used to reflect light differently in different areas. When the area where the spot pattern is located reflects more light, the spot pattern appears brighter than other areas, thereby forming a highlighted spot pattern.

[0045] In some embodiments, the projection shape of the at least one light spot pattern in a plane is at least one of a rectangle, a square, a triangle, and a circle.

[0046] Through the above arrangement, the projection shape of the light spot pattern in the plane is a regular pattern. Then, when the light spot pattern is irradiated on the uneven surface of the palm 300 to be identified, obvious deformation will occur, which is more conducive to measuring and confirming the deformation amount of the light spot pattern, and then confirming the unevenness of the surface of the palm 300 to be identified.

[0047] As shown in Figure 3, in some embodiments, the reflective array 2 includes at least one reflective array element 21 and a driving unit 22. The at least one reflective array element 21 is connected to the driving unit 22. The driving unit 22 is used to drive the at least one reflective array element 21 to move to adjust the direction of the reflected light.

[0048] Through the above arrangement, the reflective array 2 can use its reflective elements 21 to reflect the light emitted by the light source 1 in different directions. This ensures that the light evenly illuminates the entire palm 300 to be identified, and also forms a bright spot pattern on the surface of the palm 300 to be identified based on the direction of the light superposition.

[0049] Exemplarily, the reflective array 2 uses a DMD (Digital Micromirror Device), which is a MEMS (Micro-Electro-Mechanical System) with electronic input and optical output. The DMD is composed of thousands of tiny movable micromirrors (i.e., reflective array elements 21), each of which corresponds to a pixel. Micromirrors are usually made of aluminum or silicon and have a size between 10 and 20 microns. The DMD is based on semiconductor manufacturing technology and consists of a high-speed digital optical reflective switch array. The imaging pattern and its characteristics are determined by controlling the rotation of the micromirrors around a fixed (yoke) and the time domain response (determining the reflection angle and stagnation time of the light). Through the micromirror array and the fast switching mechanism, digital optical modulation of the incident light and / or reflected light is achieved.

[0050] As shown in Figure 1, in some embodiments, the image acquisition device 100 also includes at least one distance sensor 3, and the at least one distance sensor 3 is located on one side of the imaging component 4. The at least one distance sensor 3 is used to detect the distance between the palm 300 to be identified and the reflective array 2, as well as the distance between the palm 300 to be identified and the imaging component 4.

[0051] In this embodiment, the distance sensor 3 can detect the distance between the palm 300 to be identified and the reflective array 2, or the distance between the palm 300 to be identified and the imaging component 4. This distance information is used to determine whether the palm 300 to be identified is located above the image acquisition device 100. The image acquisition device 100 is activated only when the palm 300 to be identified is confirmed to be located above the image acquisition device 100. Furthermore, the reflective array 2 can determine the exact reflection direction based on this distance information. Furthermore, the imaging component 4 can adjust imaging parameters based on different distance information.

[0052] The distance sensor 3 includes, but is not limited to, an infrared modulated spectrum reflectance intensity sensor and an infrared time-of-flight sensor. For example, there are multiple distance sensors 3 , each of which can be used to detect multiple acquisition areas of the imaging component 4 and reflect light in conjunction with the position-guided reflective array 2 .

[0053] As shown in Figure 1, in some embodiments, at least one distance sensor 3 is electrically connected to the light source 1, and the light source 1 is configured to adjust the light-emitting state according to the distance between the palm 300 to be identified and the reflective array 2, or the distance between the palm 300 to be identified and the imaging component 4.

[0054] In this embodiment, the distance sensor 3 is used to detect the different spatial positions of the palm 300 to be identified above the image acquisition device 100, so as to provide fill light compensation for the light source. For example, when the palm 300 to be identified is relatively close, the light source 1 requires less fill light. When the palm 300 to be identified is relatively far away, the light source 1 requires more fill light.

[0055] As shown in FIG1 , in some embodiments, at least one distance sensor 3 is electrically connected to the reflective array 2. The reflective array 2 is configured to adjust the reflection direction based on the distance between the palm 300 to be identified and the reflective array 2, or the distance between the palm 300 to be identified and the imaging assembly 4. The distance sensor 3 can be used to determine the spatial position of the palm 300 to be identified relative to the reflective array 2, thereby ensuring that the reflective array 2 can reflect light toward the palm 300 to be identified and illuminate the palm 300 to form a light spot pattern.

[0056] As shown in Figure 4, in some embodiments, the imaging component 4 includes an optical lens 41, a circuit board 42 and a photosensitive element 43. The photosensitive element 43 is electrically connected to the circuit board 42, and the optical lens 41 is located on the light input path of the photosensitive element 43.

[0057] In some possible implementations, the photosensitive element 43, also known as an image sensor, may be a complementary metal oxide semiconductor (CMOS) or a charge coupled device (CCD). Alternatively, it may be another type of image sensor other than CMOS or CCD, such as a charge injection device (CID).

[0058] It is understandable that for CMOS, a digital signal processor (DSP) can be integrated into CMOS. CMOS has advantages such as high integration, low power consumption, and low cost, making it suitable for electronic devices with limited installation space, such as biometric devices and mobile phones.

[0059] In some possible implementations, a printed circuit is provided on the surface of the circuit board 42. The circuit board 42 includes a printed circuit board (PCB), a flexible printed circuit board (FPC), a rigid-flex board, and the like.

[0060] On the other hand, in conjunction with FIG5 , this embodiment provides a biometric identification device, which can specifically be a palm scanning device, wherein the biometric identification device includes the image acquisition device 100 of the present application. The biometric identification device of this embodiment uses the image acquisition device 100 of the present application and has all the beneficial technical effects of the present application.

[0061] As shown in FIG5 , in some embodiments, the image acquisition device 100 further includes an image processing unit 200, which is electrically connected to each of the imaging components 4. The image processing unit 200 receives the image to be recognized output by the imaging component 4 and determines the three-dimensional shape of the palm 300 to be recognized based on the deformation of at least one light spot pattern in the image to be recognized. The image processing unit 200 can restore the spatial parameter information of the palm 300 to be recognized, thereby improving the recognition accuracy and efficiency of the biometric recognition device of the present application.

[0062] 5 , in some possible implementations, the biometric recognition device further includes a recognition unit 400, which may store a plurality of candidate palm print images. For example, the recognition unit 400 is a CPU (Central Processing Unit) capable of image processing.

[0063] Through the electrical connection between the recognition unit 400 and the image processing unit 200, the recognition unit 400 can obtain the image to be recognized sent by the image acquisition device 100, and by comparing the image to be recognized with the candidate palmprint image, the recognition unit 400 can determine the target identity corresponding to the image to be recognized.

[0064] It should be noted that the terms "several" and "at least one" in this document refer to one or more, while "multiple" and "at least two" refer to two or more. "And / or" describes the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates an "or" relationship between the associated objects.

[0065] In the description of this specification, reference to the terms "certain embodiments", "one embodiment", "some embodiments", "illustrative embodiment", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application.

[0066] The above description is merely an embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. An image acquisition device, the image acquisition device (100) comprising: A light source (1), a reflective array (2), and an imaging assembly (4); The reflective array (2) is located on the light-emitting side of the light source (1); the light source (1) is used to emit light toward the reflective array (2); the reflective array (2) is used to reflect the light toward the palm (300) to be identified and illuminate the palm (300) to be identified, thereby forming at least one light spot pattern (20) on the palm (300) to be identified; The imaging component (4) is used to receive light reflected from the surface of the palm (300) to be identified, and output an image to be identified with the at least one light spot pattern (20).

2. The image acquisition device according to claim 1, wherein the area of the light spot pattern projected when the distance between the palm to be identified (300) and the image acquisition device is a first distance is greater than the area of the light spot pattern projected when the distance between the palm to be identified (300) and the image acquisition device is a second distance, wherein: The first distance is smaller than the second distance, and the area of the light spot pattern refers to the area ratio of the light spot pattern on the palm.

3. The image acquisition device according to claim 1, wherein the projection shape of the at least one light spot pattern (20) in a plane is at least one of a rectangle, a square, a triangle and a circle.

4. The image acquisition device according to claim 1, wherein the reflective array (2) comprises at least one reflective array element (21) and a driving unit (22); The at least one reflective array element (21) is connected to the driving unit (22), and the driving unit (22) is used to drive the at least one reflective array element (21) to move so as to adjust the direction of reflected light.

5. The image acquisition device according to claim 1, further comprising at least one distance sensor (3), wherein the at least one distance sensor (3) is located on one side of the imaging component (4), and the at least one distance sensor (3) is used to detect the distance between the palm to be identified (300) and the reflective array (2), and the distance between the palm to be identified (300) and the imaging component (4).

6. The image acquisition device according to claim 5, wherein the at least one distance sensor (3) is electrically connected to the light source (1), and the light source (1) is configured to adjust the light emission state according to the distance between the palm to be identified (300) and the reflective array (2) or the distance between the palm to be identified (300) and the imaging component (4).

7. The image acquisition device according to claim 5, wherein the at least one distance sensor (3) is electrically connected to the reflective array (2), and the reflective array (2) is configured to adjust the reflection direction according to the distance between the palm to be identified (300) and the reflective array (2) or the distance between the palm to be identified (300) and the imaging component (4).

8. The image acquisition device according to any one of claims 1 to 7, wherein the imaging component (4) comprises an optical lens (41), a circuit board (42) and a photosensitive element (43), the photosensitive element (43) is electrically connected to the circuit board (42), and the optical lens (41) is located on the light input path of the photosensitive element (43).

9. A biometric identification device, comprising the image acquisition device (100) according to any one of claims 1 to 8.

10. The biometric identification device according to claim 9, wherein the image acquisition device (100) further comprises an image processing unit (200), wherein the image processing unit (200) is electrically connected to the imaging components (4), respectively, and the image processing unit (200) receives the image to be identified output by the imaging component (4), and determines the three-dimensional shape of the palm (300) to be identified based on the deformation of the at least one light spot pattern (20) in the image to be identified.

Images