Palm image recognition method, device, equipment, storage medium and program product

Abstract

The present application discloses a palm image recognition method, device, equipment, storage medium and program product, which belongs to the field of computer technology. The method includes: obtaining a color image and an infrared image of the same palm image; aligning the color image and the infrared image to obtain the alignment relationship between the color image and the infrared image; performing region recognition processing on the infrared image to determine the first palm region on the infrared image; based on the alignment relationship between the color image and the infrared image, determining the second palm region corresponding to the first palm region on the color image; performing palm comparison recognition processing on the first palm region of the infrared image and the second palm region of the color image to determine the target object identification corresponding to the palm image. Through the above method, the color image can be assisted to quickly determine the palm region, so that the palm image recognition method can adapt to complex environments and improve the accuracy of palm recognition.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a palm image recognition method, device, equipment, storage medium and program product. Background Art

[0002] With the development of computer technology, palm recognition technology is being used more and more widely. It can be applied in a variety of scenarios, such as payment scenarios or clocking in at work. Through palm recognition, the user's identity can be verified.

[0003] In the related art, when a user swipes his palm, a computer device collects a palm image, and the computer device transmits the palm image to a palm recognition server through a network. The palm recognition server recognizes the palm image, thereby completing identity recognition.

[0004] In complex lighting environments such as "strong backlight", "strong side light" and "darkness", the palm images collected by computer equipment are of poor quality, making it difficult to determine the palm area to be identified, resulting in low accuracy of palm recognition. Summary of the invention

[0005] The present application provides a palm image recognition method, device, equipment, storage medium and program product, and the technical solution is as follows:

[0006] According to one aspect of the present application, a palm image recognition method is provided, the method comprising:

[0007] Acquire a color image and an infrared image of the same palm image, wherein the color image refers to an image obtained by imaging the palm with a color camera based on natural light, and the infrared image refers to an image obtained by imaging the palm with an infrared camera based on infrared light;

[0008] Performing alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image;

[0009] Performing region recognition processing on the infrared image to determine a first palm region on the infrared image;

[0010] determining, on the color image, a second palm region corresponding to the first palm region based on an alignment relationship between the color image and the infrared image;

[0011] Palm comparison and recognition processing is performed on the first palm area of ​​the infrared image and the second palm area of ​​the color image to determine the target object identifier corresponding to the palm image.

[0012] According to one aspect of the present application, a palm image recognition device is provided, the device comprising:

[0013] An acquisition module, used to acquire a color image and an infrared image of the same palm image, wherein the color image refers to an image obtained by imaging the palm with a color camera based on natural light, and the infrared image refers to an image obtained by imaging the palm with an infrared camera based on infrared light;

[0014] An alignment module, used for performing alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image;

[0015] A recognition module, used for performing region recognition processing on the infrared image to determine a first palm region on the infrared image;

[0016] The alignment module is further used to determine a second palm area corresponding to the first palm area on the color image based on the alignment relationship between the color image and the infrared image;

[0017] The recognition module is further used to perform palm comparison and recognition processing on the first palm area of ​​the infrared image and the second palm area of ​​the color image to determine the target object identifier corresponding to the palm image.

[0018] In a possible implementation, the alignment module is further used to perform spatial alignment processing and / or temporal alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image.

[0019] In a possible implementation, the alignment module is also used to obtain the coordinate parameters of the palm in the pixel coordinate system of the infrared image; based on the camera intrinsic parameters of the infrared camera, the coordinate parameters of the palm in the infrared image are represented by the infrared camera coordinate system, and the camera intrinsic parameters are used to describe the parameters of the conversion relationship between the coordinate parameters of the palm in the world coordinate system and the coordinate parameters of the palm in the pixel coordinate system; based on the camera extrinsic parameters, the coordinate parameters of the palm in the infrared image are represented by the color camera coordinate system, and the camera extrinsic parameters are used to describe the parameters of the conversion relationship between the color camera coordinate system and the infrared camera coordinate system; based on the camera intrinsic parameters of the color camera, the pixel coordinate system of the color image is used to represent the coordinate parameters of the palm in the infrared image, so as to obtain the spatial alignment relationship between the color image and the infrared image.

[0020] In a possible implementation, the recognition module is further used to map the first palm area on the infrared image to the color image based on the spatial alignment relationship between the color image and the infrared image, and obtain the second palm area on the color image.

[0021] In a possible implementation, the alignment module is also used to obtain timestamps marked on the color image and the infrared image, where the timestamp refers to temporal data marked on the color image and the infrared image when the color camera and the infrared camera are exposed; based on the timestamp, a time alignment relationship between the color image and the infrared image is obtained.

[0022] In a possible implementation, the recognition module is further used to map the first palm area on the infrared image to the color image based on a time alignment relationship between the color image and the infrared image, and obtain the second palm area on the color image.

[0023] In a possible implementation, the recognition module is further used to adjust the exposure parameter of the second palm area in the color image of the i-th frame to obtain the second palm area in the color image of the i+1-th frame when the quality parameter of the second palm area in the color image of the i-th frame is less than a preset threshold; perform palm comparison and recognition processing on the first palm area in the infrared image of the i+1-th frame and the second palm area in the color image of the i+1-th frame, and fuse the palm comparison and recognition results of the first palm area and the second palm area according to a weight value to determine the target object identifier corresponding to the palm image, where i is a positive integer.

[0024] In a possible implementation, the recognition module is further configured to detect finger gaps in the infrared image, and determine the first palm region on the infrared image based on the finger gaps.

[0025] In a possible implementation, the recognition module is further configured to perform palm comparison and recognition processing on the first palm area of ​​the infrared image through an infrared image processor to determine a first object identifier corresponding to the palm image; and perform palm comparison and recognition processing on the second palm area of ​​the color image through a color image processor to determine a second object identifier corresponding to the palm image;

[0026] Based on the weight values ​​of the infrared image processor and the color image processor, the first object identifier and the second object identifier are fused to obtain a target object identifier corresponding to the palm image.

[0027] In one possible implementation, the recognition module is also used to determine the weight values ​​of the infrared image processor and the color image processor based on the quality parameters of the second palm area of ​​the color image; based on the weight values ​​of the infrared image processor and the color image processor, the first object identifier and the second object identifier are fused to obtain the target object identifier corresponding to the palm image.

[0028] The wavelength of the infrared light is 940 nm.

[0029] In a possible implementation, the recognition module is further used to obtain the recognition distance of the palm to be recognized through a short-range sensor, and the recognition distance refers to the distance between the palm to be recognized and the color camera and the infrared camera; based on the recognition distance, determine the exposure parameters of the color camera and the infrared camera; according to the exposure parameters, obtain the color image and the infrared image of the palm to be recognized; perform palm comparison and recognition processing on the color image and the infrared image, and obtain the target object identification corresponding to the palm to be recognized within a recognition time period, and the recognition time period refers to the time corresponding to the entire process of measuring the recognition distance through the short-range sensor and performing palm comparison and recognition processing; when the recognition time period is greater than the time threshold, execute the palm image recognition method to obtain the target object identification corresponding to the palm image.

[0030] According to another aspect of the present application, a computer device is provided, which includes: a processor and a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the palm image recognition method as described above.

[0031] According to another aspect of the present application, a computer storage medium is provided, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor to implement the palm image recognition method as described above.

[0032] According to another aspect of the present application, a computer program product is provided, which includes a computer program stored in a computer-readable storage medium; the computer program is read and executed from the computer-readable storage medium by a processor of a computer device, so that the computer device executes the palm image recognition method described above.

[0033] The beneficial effects of the technical solution provided by this application include at least:

[0034] By acquiring a color image and an infrared image of the same palm image; aligning the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image; performing region recognition processing on the infrared image to determine a first palm region on the infrared image; based on the alignment relationship between the color image and the infrared image, determining a second palm region corresponding to the first palm region on the color image; performing palm comparison recognition processing on the first palm region of the infrared image and the second palm region of the color image to determine the target object identification corresponding to the palm image. The present application determines the palm region on the infrared image by aligning the infrared image with the color image, determines the corresponding palm region on the color image based on the alignment relationship between the infrared image and the color image, and performs palm comparison recognition on the palm regions corresponding to the infrared image and the color image, respectively, so as to determine the target object identification. Based on the above method, the color image can be assisted to quickly determine the palm region, so that the palm image recognition method can adapt to complex environments and improve the accuracy of palm recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0036] Figure 1 is a schematic diagram of a palm image recognition method provided by an exemplary embodiment of the present application;

[0037] Figure 2 is a schematic diagram of the architecture of a computer system provided by an exemplary embodiment of the present application;

[0038] Figure 3 is a flow chart of a palm image recognition method provided by an exemplary embodiment of the present application;

[0039] Figure 4 is a flow chart of a palm image recognition method provided by an exemplary embodiment of the present application;

[0040] Figure 5 is a schematic diagram of time alignment of a color image and an infrared image provided by an exemplary embodiment of the present application;

[0041] Figure 6 is a schematic diagram of finger gap points in the palm provided by an exemplary embodiment of the present application;

[0042] Figure 7 is a schematic diagram of image processing in a camera module provided by an exemplary embodiment of the present application;

[0043] Figure 8 is a flow chart of a palm image recognition method provided by an exemplary embodiment of the present application;

[0044] Fig. 9 is a schematic diagram of cross-device payment based on a palm image recognition method provided by an exemplary embodiment of the present application;

[0045] Fig.10 is a flow chart of a palm image recognition method provided by an exemplary embodiment of the present application;

[0046] Fig.11 is a flow chart of spatial alignment of color image and infrared image provided by an exemplary embodiment of the present application;

[0047] Fig.12 is a flow chart of acquiring a color image and an infrared image provided by an exemplary embodiment of the present application;

[0048] Fig.13 is a schematic diagram of a cross-device identity authentication based on a palm image recognition method provided by an exemplary embodiment of the present application;

[0049] Fig.14 is a block diagram of a palm image recognition device provided by an exemplary embodiment of the present application;

[0050] Fig.15 It is a structural diagram of a computer device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0052] First, several terms involved in the embodiments of the present application are briefly introduced:

[0053] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.

[0054] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0055] Cloud technology refers to a hosting technology that unifies hardware, software, network and other resources within a wide area network or local area network to achieve data computing, storage, processing and sharing.

[0056] Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model. It can form a resource pool, which can be used on demand and is flexible and convenient. Cloud computing technology will become an important support. The backend services of the technical network system require a large amount of computing and storage resources, such as video websites, picture websites and more portal websites. With the rapid development and application of the Internet industry, in the future, each item may have its own identification mark, which needs to be transmitted to the backend system for logical processing. Data of different levels will be processed separately. All kinds of industry data need strong system backing support, which can only be achieved through cloud computing.

[0057] Cloud computing is a computing model that distributes computing tasks across a resource pool consisting of a large number of computers, enabling various application systems to obtain computing power, storage space, and information services as needed. The network that provides resources is called a "cloud". From the user's perspective, the resources in the "cloud" are infinitely scalable and can be accessed at any time, used on demand, expanded at any time, and paid for as needed.

[0058] As a provider of basic cloud computing capabilities, a cloud computing resource pool (referred to as a cloud platform, generally referred to as an IaaS (Infrastructure as a Service) platform) will be established, and various types of virtual resources will be deployed in the resource pool for external customers to choose to use. The cloud computing resource pool mainly includes: computing devices (virtualized machines, including operating systems), storage devices, and network devices.

[0059] According to the logical function division, the PaaS (Platform as a Service) layer can be deployed on the IaaS (Infrastructure as a Service) layer, and the SaaS (Software as a Service) layer can be deployed on the PaaS layer. SaaS can also be deployed directly on IaaS. PaaS is a platform for software operation, such as databases, Web (World Wide Web) containers, etc. SaaS is a variety of business software, such as web portals, SMS mass senders, etc. Generally speaking, SaaS and PaaS are upper layers relative to IaaS.

[0060] Computer vision technology (CV) is a science that studies how to make machines "see". To put it more specifically, it refers to machine vision such as using cameras and computers to replace human eyes to identify and measure targets, and further perform graphic processing so that the computer processing becomes an image that is more suitable for human eye observation or transmission to instrument detection. As a scientific discipline, computer vision studies related theories and technologies, and attempts to establish an artificial intelligence system that can obtain information from images or multi-dimensional data. Computer vision technology usually includes image processing, image recognition, image semantic understanding, image retrieval, video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous positioning and map construction, and also includes common biometric recognition technology.

[0061] The present application embodiment provides a schematic diagram of a palm image recognition method, such as Figure 1 As shown, the method can be executed by a computer device, and the computer device can be a terminal or a server.

[0062] Exemplarily, the computer device obtains the color image 103 and the infrared image 104 of the same palm, and performs spatial alignment processing and / or temporal alignment processing on the color image 103 and the infrared image 104 to obtain an alignment relationship between the color image 103 and the infrared image 104 .

[0063] The color image 103 refers to an image obtained by a color camera imaging the palm based on natural light, and the infrared image 104 refers to an image obtained by an infrared camera imaging the palm based on infrared light.

[0064] Exemplarily, the computer device obtains the coordinate parameters of the palm in the pixel coordinate system of the infrared image 104; the computer device uses the infrared camera coordinate system to represent the coordinate parameters of the palm in the infrared image 104 based on the camera intrinsic parameters of the infrared camera; the computer device uses the color camera coordinate system to represent the coordinate parameters of the palm in the infrared image 104 based on the camera extrinsic parameters; the computer device uses the pixel coordinate system of the color image 103 to represent the coordinate parameters of the palm in the infrared image 104 based on the camera intrinsic parameters of the color camera, and obtains the spatial alignment relationship between the color image 103 and the infrared image 104.

[0065] The camera intrinsic parameters are used to describe the conversion relationship between the coordinate parameters of the palm in the world coordinate system and the coordinate parameters of the palm in the pixel coordinate system.

[0066] Camera extrinsics are parameters used to describe the conversion relationship between the color camera coordinate system and the infrared camera coordinate system.

[0067] Exemplarily, the computer device obtains the time stamps marked on the color image 103 and the infrared image 104 , and obtains the time alignment relationship between the color image 103 and the infrared image 104 based on the time stamps.

[0068] The timestamp refers to the time data marked on the color image 103 and the infrared image 104 when the color camera 101 and the infrared camera 102 are exposed;

[0069] For example, the computer device obtains the color image 103 taken by the color camera 101 and the infrared image 104 of the same palm taken by the infrared camera 102. The computer device performs spatial alignment processing and / or temporal alignment processing on the color image 103 and the infrared image 104 of the same palm to achieve alignment of the color image 103 and the infrared image 104.

[0070] The computer device detects finger gap points in the infrared image 104 , and determines a first palm region on the infrared image 104 based on the finger gap points.

[0071] The computer device determines a second palm region corresponding to the first palm region on the color image 103 based on the alignment relationship between the color image 103 and the infrared image 104 .

[0072] Optionally, the computer device maps the first palm area on the infrared image 104 to the color image 103 based on the spatial alignment relationship between the color image 103 and the infrared image 104 , and obtains the second palm area on the color image 103 .

[0073] Optionally, the computer device maps the first palm region on the infrared image 104 to the color image 103 based on the time alignment relationship between the color image 103 and the infrared image 104 , and obtains the second palm region on the color image 103 .

[0074] Optionally, the computer device maps the first palm area on the infrared image 104 to the color image 103 based on the spatial alignment relationship and the temporal alignment relationship between the color image 103 and the infrared image 104 , and obtains the second palm area on the color image 103 .

[0075] Optionally, when the quality parameter of the second palm region of the i-th frame color image is less than a preset threshold, adjusting the exposure brightness value of the second palm region to obtain the second palm region of the i+1-th frame color image;

[0076] The computer device performs palm comparison and recognition processing 105 on the first palm area of ​​the i+1th frame infrared image and the second palm area of ​​the i+1th frame color image, respectively, and fuses the palm comparison and recognition result of the first palm area and the palm comparison and recognition result of the second palm area according to the weight value, so as to determine the target object identification corresponding to the palm image, where i is a positive integer.

[0077] Optionally, the wavelength of the infrared light is 940 nm.

[0078] In summary, the method provided in this embodiment obtains a color image and an infrared image of the same palm image; performs region recognition processing on the infrared image to determine a first palm region on the infrared image; determines a second palm region on the color image based on a spatial alignment processing and / or a temporal alignment relationship between the color image and the infrared image; performs palm comparison and recognition processing on the first palm region of the infrared image and the second palm region of the color image to determine the target object identification corresponding to the palm image. The present application determines the palm region on the infrared image by aligning the infrared image with the color image, determines the palm region on the color image based on the alignment relationship between the infrared image and the color image, and performs palm comparison and recognition on the palm regions corresponding to the infrared image and the color image, respectively, to determine the target object identification. Based on the above method, the color image can be assisted to quickly determine the palm region, so that the palm image recognition method is adapted to complex environments, while improving the accuracy of palm recognition.

[0079] Figure 2 The schematic diagram of the architecture of a computer system provided by an embodiment of the present application is shown. The computer system may include: a terminal 100 and a server 200.

[0080] The terminal 100 may be an electronic device such as a mobile phone, a tablet computer, a vehicle-mounted terminal (vehicle computer), a wearable device, a personal computer (PC), an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, an aircraft, an unmanned vending terminal, etc. The terminal 100 may be installed with a client that runs a target application, and the target application may be an application that refers to palm image recognition, or may be other applications that provide a palm image recognition function, which is not limited in this application. In addition, this application does not limit the form of the target application, including but not limited to an application (Application, App) installed in the terminal 100, a mini-program, etc., and may also be in the form of a web page.

[0081] The server 200 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services, cloud database, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and cloud servers for basic cloud computing services such as big data and artificial intelligence platforms. The server 200 may be a backend server of the above-mentioned target application, used to provide backend services for the client of the target application.

[0082] Among them, cloud technology refers to a hosting technology that unifies hardware, software, network and other resources in a wide area network or local area network to realize data computing, storage, processing and sharing. Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model. It can form a resource pool, which is used on demand and flexible and convenient. Cloud computing technology will become an important support. The background services of the technical network system require a large amount of computing and storage resources, such as video websites, picture websites and more portal websites. With the high development and application of the Internet industry, in the future, each item may have its own identification mark, and all need to be transmitted to the background system for logical processing. Data of different levels will be processed separately. All kinds of industry data require strong system backing support, which can only be achieved through cloud computing.

[0083] In some embodiments, the above-mentioned server can also be implemented as a node in a blockchain system. Blockchain is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0084] The terminal 100 and the server 200 may communicate with each other via a network, such as a wired or wireless network.

[0085] In the palm image recognition method provided in the embodiment of the present application, the execution subject of each step may be a computer device, which refers to an electronic device with data calculation, processing and storage capabilities. Figure 2 Taking the implementation environment of the scheme shown as an example, the palm image recognition method can be executed by the terminal 100 (such as the client of the target application installed and running in the terminal 100 executes the palm image recognition method), or the palm image recognition method can be executed by the server 200, or the terminal 100 and the server 200 can interact and cooperate to execute it, and this application does not limit this.

[0086] Figure 3 is a flowchart of a palm image recognition method provided by an exemplary embodiment of the present application. The method can be executed by a computer device, which can be Figure 2 The terminal 100 or the server 200 in the embodiment. The method comprises:

[0087] Step 302: Acquire a color image and an infrared image of the same palm image.

[0088] The color image refers to the image obtained by imaging the palm with a color camera based on natural light.

[0089] Infrared images refer to images obtained by an infrared camera imaging the palm based on infrared light.

[0090] The palm image is a palm image of the target object whose identity is to be determined, and the palm image includes a palm, which is the palm of the target object whose identity is to be verified. The palm image may also include other information, such as the fingers of the target object, the scene in which the palm of the target object is photographed, etc. The palm image may be obtained by the computer device photographing the palm of the target object whose identity is to be verified, or may be sent by other devices.

[0091] For example, the computer device is a store payment device, which captures the palm of the target object through a camera to obtain the palm image; or, the computer device is a palm image recognition server, which sends the palm image to the palm image recognition server after capturing the palm image of the target object.

[0092] Step 304: performing alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image.

[0093] Exemplarily, the computer device performs alignment processing on the color image and the infrared image of the same palm image to obtain an alignment relationship between the color image and the infrared image.

[0094] The alignment process includes spatial alignment process and temporal alignment process.

[0095] Spatial alignment processing refers to the method of converting color images and infrared images into the same coordinate system.

[0096] Time alignment processing refers to selecting color images and infrared images corresponding to the same timestamp according to the timestamp.

[0097] Step 306: Perform region recognition processing on the infrared image to determine the first palm region on the infrared image.

[0098] The first palm region refers to a palm region in the infrared image.

[0099] Exemplarily, the computer device determines the first palm region from the infrared image by performing region recognition on the infrared image.

[0100] Step 308: Based on the alignment relationship between the color image and the infrared image, determine a second palm region corresponding to the first palm region on the color image.

[0101] Exemplarily, the computer device determines the second palm region corresponding to the first palm region on the color image based on the alignment relationship between the color image and the infrared image.

[0102] For example, the computer device determines the second palm region corresponding to the first palm region on the color image based on the spatial alignment relationship between the color image and the infrared image.

[0103] Alternatively, the computer device determines a second palm region corresponding to the first palm region on the color image based on a time alignment relationship between the color image and the infrared image.

[0104] Alternatively, the computer device determines the second palm region corresponding to the first palm region on the color image based on the spatial alignment relationship and the temporal alignment relationship between the color image and the infrared image.

[0105] Step 310: performing palm comparison and recognition processing on the first palm region of the infrared image and the second palm region of the color image to determine the target object identifier corresponding to the palm image.

[0106] Exemplarily, the palm comparison and identification processing refers to comparing and identifying the features of the palm area with preset palm features in the database.

[0107] The preset palm feature is a palm feature of the stored object identifier. Each preset palm feature has a corresponding object identifier, indicating that the preset palm feature belongs to the object identifier and is a palm feature of the object's palm. The object identifier can be any object identifier, such as an object identifier registered in a payment application, or an object identifier registered in an enterprise.

[0108] In an embodiment of the present application, a computer device includes a database, which includes a plurality of preset palm features and an object identifier corresponding to each preset palm feature. In the database, the preset palm features and the object identifiers may correspond one-to-one, or one object identifier may correspond to at least two preset palm features.

[0109] For example, multiple objects are registered in a payment application. By binding the preset palm features of each object with the corresponding object identifier, the palm features of multiple objects and the corresponding object identifiers are stored in a database. When the objects subsequently use the payment application, the target object identifier is determined by comparing and identifying the first palm area of ​​the infrared image, the second palm area of ​​the color image, and the preset palm features in the database, thereby achieving identity authentication of the object.

[0110] Exemplarily, the computer device performs palm comparison and recognition processing on the first palm area of ​​the infrared image and the second palm area of ​​the color image respectively to obtain the target object identification corresponding to the palm image.

[0111] In summary, the method provided in this embodiment obtains a color image and an infrared image of the same palm image; performs alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image; performs region recognition processing on the infrared image to determine a first palm region on the infrared image; based on the alignment relationship between the color image and the infrared image, determines a second palm region corresponding to the first palm region on the color image; performs palm comparison and recognition processing on the first palm region of the infrared image and the second palm region of the color image to determine the target object identification corresponding to the palm image. The present application determines the palm region on the infrared image, determines the corresponding palm region on the color image based on the alignment relationship between the infrared image and the color image, and performs palm comparison and recognition on the palm regions corresponding to the infrared image and the color image, respectively, so as to determine the target object identification. Based on the above method, the color image can be assisted to quickly determine the palm region, so that the palm image recognition method can adapt to complex environments and improve the accuracy of palm recognition.

[0112] Figure 4 is a flowchart of a palm image recognition method provided by an exemplary embodiment of the present application. The method can be executed by a computer device, which can be Figure 2 The terminal 100 or the server 200 in the embodiment. The method comprises:

[0113] Step 402: Acquire a color image and an infrared image of the same palm image.

[0114] The color image refers to the image obtained by imaging the palm with a color camera based on natural light.

[0115] Infrared images refer to images obtained by an infrared camera imaging the palm based on infrared light.

[0116] The palm image is a palm image of the target object whose identity is to be determined, and the palm image includes a palm, which is the palm of the target object whose identity is to be verified. The palm image may also include other information, such as the fingers of the target object, the scene in which the palm of the target object is photographed, etc. The palm image may be obtained by the computer device photographing the palm of the target object whose identity is to be verified, or may be sent by other devices.

[0117] Exemplarily, the computer device photographs the palm of the subject to obtain a palm image. The palm image includes the palm, which may be the left palm of the subject or the right palm of the subject. For example, the computer device is an Internet of Things device, which photographs the left palm of the subject through a camera to obtain a palm image, and the Internet of Things device may be a merchant payment terminal. For another example, when the subject is shopping in a store and conducting a transaction, the subject extends his palm to the camera of the store payment terminal, and the store payment terminal photographs the palm of the subject through the camera to obtain a palm image.

[0118] In a possible implementation, a computer device establishes a communication connection with another device, and receives a palm image sent by the other device through the communication connection. For example, the computer device is a payment application server, and the other device may be a payment terminal. The payment terminal photographs the palm of the subject, obtains the palm image, and then sends the palm image to the payment application server through the communication connection between the payment terminal and the payment application server, so that the payment application server can determine the target object identifier of the palm image.

[0119] Step 404: perform spatial alignment processing and / or temporal alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image.

[0120] Spatial alignment processing refers to the method of converting color images and infrared images into the same coordinate system.

[0121] Time alignment processing refers to selecting color images and infrared images corresponding to the same timestamp according to the timestamp.

[0122] Exemplarily, the computer device performs spatial alignment processing and / or temporal alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image.

[0123] The alignment relationship includes spatial alignment relationship and temporal alignment relationship.

[0124] Exemplarily, the computer device obtains the coordinate parameters of the palm in the pixel coordinate system of the infrared image; based on the camera intrinsic parameters of the infrared camera, the coordinate parameters of the palm in the infrared image are represented by the infrared camera coordinate system; based on the camera extrinsic parameters, the computer device uses the color camera coordinate system to represent the coordinate parameters of the palm in the infrared image; based on the camera intrinsic parameters of the color camera, the computer device uses the pixel coordinate system of the color image to represent the coordinate parameters of the palm in the infrared image, thereby obtaining the spatial alignment relationship between the color image and the infrared image.

[0125] The camera intrinsic parameters are used to describe the conversion relationship between the coordinate parameters of the palm in the world coordinate system and the coordinate parameters of the palm in the pixel coordinate system.

[0126] The camera extrinsic parameters are used to describe the parameters of the conversion relationship between the color camera coordinate system and the infrared camera coordinate system.

[0127] Exemplarily, the computer device obtains the time stamps marked on the color image and the infrared image, and obtains the time alignment relationship between the color image and the infrared image based on the time stamps.

[0128] The timestamp refers to the temporal data marked on the color image and the infrared image when the color camera and the infrared camera are exposed.

[0129] For example, Figure 5 The schematic diagram of the time alignment of the color image and the infrared image shown in the figure, the method involves a color camera fill light 501, a color camera 502, an infrared camera 503 and an infrared camera fill light 504. The color camera fill light 501 illuminates the color camera 502 in a "constantly on" mode, and the color camera 502 sends a frame synchronization signal (Frame Sync) to the infrared camera during shooting, so that the color camera 502 and the infrared camera 503 are exposed at the same time. At the same time, the infrared camera 503 sends a strobe "Strobe" signal to the infrared camera fill light 504, controlling the infrared camera fill light 504 to perform fill light while the infrared camera 503 is exposed.

[0130] After the color camera 502 and the infrared camera 503 complete shooting, time stamps are marked on the color image and the infrared image, and the computer device obtains the time-aligned color image and the infrared image based on the time stamps.

[0131] Step 406: Perform region recognition processing on the infrared image to determine the first palm region on the infrared image.

[0132] The first palm region refers to a palm region in the infrared image.

[0133] Exemplarily, the computer device determines the first palm region from the infrared image by performing region recognition on the infrared image.

[0134] Exemplarily, the computer device detects finger gap points in the infrared image, and the computer device determines the first palm area on the infrared image based on the finger gap points.

[0135] For example, Figure 6 The schematic diagram of the finger seam points in the palm shown, the finger seam point is the first finger seam point 601 between the index finger and the middle finger, or the finger seam point is the second finger seam point 602 between the middle finger and the ring finger, or the finger seam point is the third finger seam point 603 between the ring finger and the little finger.

[0136] Since the palm area in the palm image may exist in any area of ​​the palm image, in order to determine the position of the palm area in the palm image, finger gap point detection is performed on the palm image to obtain at least one finger gap point of the palm image, so that the first palm area can be determined subsequently based on the at least one finger gap point.

[0137] For example, Figure 7 The image processing schematic diagram in the camera module shown in the figure shows that, when the color camera acquires a color image 701 and the infrared camera acquires an infrared image 703, the color image 701 is processed in the color image processor 702 in the camera module of the color camera; the infrared image 703 is processed in the infrared image processor 704 in the camera module of the infrared camera, and the first palm area 705 is determined based on at least one finger gap point in the infrared image 703.

[0138] Step 408: Based on the alignment relationship between the color image and the infrared image, determine a second palm region corresponding to the first palm region on the color image.

[0139] Exemplarily, the computer device determines the second palm region corresponding to the first palm region on the color image based on the alignment relationship between the color image and the infrared image.

[0140] For example, based on the spatial alignment relationship between the color image and the infrared image, the computer device maps the first palm area on the infrared image to the color image, and obtains the second palm area on the color image.

[0141] Or, the computer device maps the first palm area on the infrared image to the color image based on the time alignment relationship between the color image and the infrared image, and obtains the second palm area on the color image.

[0142] Alternatively, the computer device maps the first palm area on the infrared image to the color image based on the spatial alignment relationship and the temporal alignment relationship between the color image and the infrared image, and determines a second palm area corresponding to the first palm area on the color image.

[0143] Step 410: performing palm comparison and recognition processing on the first palm region of the infrared image and the second palm region of the color image to determine the target object identifier corresponding to the palm image.

[0144] Exemplarily, the palm comparison and identification processing refers to comparing and identifying the features of the palm area with preset palm features in the database.

[0145] The preset palm feature is a palm feature of the stored object identifier. Each preset palm feature has a corresponding object identifier, indicating that the preset palm feature belongs to the object identifier and is a palm feature of the object's palm. The object identifier can be any object identifier, such as an object identifier registered in a payment application, or an object identifier registered in an enterprise.

[0146] Exemplarily, the computer device performs palm comparison and recognition processing on the first palm area of ​​the infrared image and the second palm area of ​​the color image respectively to obtain the target object identification corresponding to the palm image.

[0147] In a possible implementation, when a quality parameter of a second palm region of an i-th frame color image is less than a preset threshold, an exposure parameter of the second palm region is adjusted to obtain the second palm region of an i+1-th frame color image; a computer device performs palm comparison and recognition processing on the first palm region of an i+1-th frame infrared image and the second palm region of an i+1-th frame color image, and fuses the palm comparison and recognition result of the first palm region and the palm comparison and recognition result of the second palm region according to a weight value to determine a target object identifier corresponding to the palm image, where i is a positive integer.

[0148] For example, a computer device obtains a first color image and a first infrared image of the same palm image, and performs palm comparison and recognition on a second palm region of the first color image and a first palm region of the first infrared image. When a quality parameter of the second palm region of the color image is less than a preset threshold, the computer device adjusts an exposure parameter of the color camera for the second palm region to obtain a second color image and a second infrared image. The computer device performs palm comparison and recognition on the second palm region of the second color image and the first palm region of the second infrared image. By analogy, when a quality parameter of the second palm region of the color image is greater than or equal to a preset threshold, the computer device fuses the palm comparison and recognition result of the first palm region and the palm comparison and recognition result of the second palm region according to a weight value, thereby more accurately determining the target object identification corresponding to the palm image.

[0149] In one possible implementation, the computer device performs palm comparison and recognition processing on the first palm area of ​​the infrared image through an infrared image processor to determine a first object identifier corresponding to the palm image; the computer device performs palm comparison and recognition processing on the second palm area of ​​the color image through a color image processor to determine a second object identifier corresponding to the palm image; the computer device fuses the first object identifier and the second object identifier based on weight values ​​of the infrared image processor and the color image processor to obtain a target object identifier corresponding to the palm image.

[0150] Optionally, the computer device determines the weight values ​​of the infrared image processor and the color image processor based on the quality parameters of the second palm area of ​​the color image; the computer device fuses the first object identifier and the second object identifier based on the weight values ​​of the infrared image processor and the color image processor to obtain the target object identifier corresponding to the palm image.

[0151] For example, the computer device determines the weight values ​​of the infrared image processor and the color image processor according to the quality parameter of the second palm region of the color image. The higher the quality parameter of the second palm region of the color image, the higher the weight value of the color image processor.

[0152] Optionally, the wavelength of the infrared light is 940 nm.

[0153] In a possible implementation, a computer device obtains an identification distance of a palm to be identified through a short-range sensor, and determines exposure parameters of a color camera and an infrared camera based on the identification distance; the computer device obtains a color image and an infrared image of the palm to be identified according to the exposure parameters; the computer device performs palm comparison and identification processing on the color image and the infrared image, and obtains a target object identifier corresponding to the palm to be identified within a recognition time period; when the recognition time period is greater than a time threshold, the computer device executes a palm image recognition method (the specific steps of the palm image recognition method can be found in the description in the aforementioned embodiment and will not be repeated here), and obtains a target object identifier corresponding to the palm image.

[0154] The recognition distance refers to the distance between the palm to be recognized and the color camera or infrared camera.

[0155] The recognition time period refers to the time corresponding to the entire process of measuring the recognition distance through the proximity sensor and performing palm comparison recognition processing.

[0156] For example, Figure 8 The flowchart of the palm image recognition method shown. Step 801: When recognizing the palm image, first adopt "fixed exposure parameters:" to recognize the palm image, that is, the computer device obtains the recognition distance between the palm to be recognized and the color camera and the infrared camera through the short-range sensor; Step 802: The computer device determines the exposure parameters based on the recognition distance by comparing the recognition distance table, that is, determines the exposure parameters of the color camera and the infrared camera; The computer device performs palm comparison recognition processing on the color image and the infrared image; Step 803: If the target object identification corresponding to the palm to be recognized is not obtained within 1s, the computer device executes the palm image recognition method (the specific steps of the palm image recognition method can be referred to the description in the aforementioned embodiment, which will not be repeated here), and obtains the target object identification corresponding to the palm image.

[0157] It should be noted that the palm, as a type of biometric feature, is biologically unique and distinguishable. Compared with facial recognition, which is currently widely used in the fields of identity verification, payment, access control, and ride-hailing, the palm will not be affected by makeup, masks, sunglasses, etc., and can improve the accuracy of object identity verification. In some scenarios, such as epidemic prevention and control scenarios, it is necessary to wear a mask to cover the mouth and nose. In this case, using palm images for identity verification can be a better choice.

[0158] Cross-device registration and recognition is a capability that is very important for the object experience. For two types of associated devices, the object can be registered in one type of device, and the object's object identifier is bound to the object's palm features. After that, the object can be authenticated on the other type of device. Since mobile phones and IoT devices differ greatly in image style and image quality, through cross-device registration and recognition, objects can be used directly on IoT devices after being registered on the mobile phone, without the need for the object to be registered on two types of devices. For example, after the object is registered through the mobile phone, it can be authenticated directly on the store's device without the need for the object to be registered on the store's device, thus avoiding information leakage of the object.

[0159] In summary, the method provided in this embodiment obtains a color image and an infrared image of the same palm image; aligns the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image; performs region recognition processing on the infrared image to determine a first palm region on the infrared image; based on the alignment relationship between the color image and the infrared image, determines a second palm region corresponding to the first palm region on the color image; when a quality parameter of the second palm region of the i-th frame color image is less than a preset threshold, adjusts the exposure parameter of the second palm region to obtain the second palm region of the i+1-th frame color image; a computer device performs palm comparison and recognition processing on the first palm region of the i+1-th frame infrared image and the second palm region of the i+1-th frame color image, and fuses the palm comparison and recognition result of the first palm region and the palm comparison and recognition result of the second palm region according to a weight value to determine the target object identifier corresponding to the palm image. The present application determines the palm area on the infrared image, determines the corresponding palm area on the color image based on the alignment relationship between the infrared image and the color image, and performs palm comparison and recognition on the palm areas corresponding to the infrared image and the color image respectively, thereby determining the target object identification. Based on the above method, the color image can be assisted to quickly determine the palm area, and a higher quality second palm area can be obtained by adjusting the exposure parameters, so that the palm image recognition method can adapt to complex environments and improve the accuracy of palm recognition.

[0160] Fig. 9901 is a schematic diagram of a cross-device payment based on a palm image recognition method provided by an exemplary embodiment of the present application. The method involves an object terminal 901, a merchant terminal 903 and a payment application server 902.

[0161] Among them, the object terminal 901 is installed with a payment application, the object terminal 901 logs in to the payment application based on the object identifier, and establishes a communication connection with the payment application server 902, through which the object terminal 901 and the payment application server 902 can interact; the merchant terminals 903 are all installed with payment applications, the merchant terminals 903 log in to the payment application based on the merchant identifier, and establish a communication connection with the payment application server 902, through which the merchant terminals 903 and the payment application server 902 can interact.

[0162] The cross-device payment process includes:

[0163] 1. The subject holds the subject terminal 901 at home, and uses the subject terminal 901 to shoot the subject's own palm to obtain the subject's palm image, logs in to the payment application based on the subject identifier, and sends a palm image registration request to the payment application server 902. The palm image registration request carries the subject identifier and palm image.

[0164] 2. The payment application server 902 receives the palm image registration request sent by the object terminal 901, processes the palm image, obtains the palm features of the palm image, stores the palm features in correspondence with the object identifier, and sends a palm image binding success notification to the object terminal 901.

[0165] Among them, after the payment application server 902 stores the palm feature and the object identifier in correspondence, the palm feature is used as a preset palm feature, and the corresponding object identifier can be determined later by the stored preset palm feature.

[0166] 3. The object terminal 901 receives the palm image binding success notification, displays the palm image binding success notification, and prompts that the object palm image is bound to the object identifier.

[0167] The object completes the palm image registration through the interaction between its own object terminal 901 and the payment application server 902, and can subsequently realize automatic payment through the palm image.

[0168] 4. When the subject purchases goods in the store, the merchant terminal 903 captures the subject's palm to obtain a palm image, and sends a payment request to the payment application server 902 based on the payment application logged in with the merchant ID. The payment request carries the merchant ID, the consumption amount and the palm image.

[0169] 5. After receiving the payment request, the payment application server 902 performs palm comparison and recognition processing on the palm image, determines the object identifier of the palm image, determines the account number of the object identifier in the payment application, completes the transfer through the account number, and sends a payment completion notification to the merchant terminal 903 after the transfer is completed.

[0170] Among them, after the object uses the object terminal 901 to register the palm image, the object can directly pay through the palm at the merchant terminal 903 without the user registering the palm image on the merchant terminal 903, thereby achieving the effect of cross-device palm image recognition and improving convenience.

[0171] 6. The merchant terminal 903 receives the payment completion notification, displays the payment completion notification, and prompts the object that the payment is completed, so that the object and the merchant complete the transaction of the item, and the object can take the item away.

[0172] In addition, the above embodiment uses the object terminal 901 and the merchant terminal 903 to realize the cross-device payment process. The above merchant terminal 903 can also be replaced with a payment device on the bus. According to the above steps, a cross-device bus payment solution can be realized.

[0173] Fig.10 is a flowchart of a palm image recognition method provided by an exemplary embodiment of the present application. The method can be executed by a computer device, which can be Figure 2 The terminal 100 or the server 200 in the embodiment. The method comprises:

[0174] Step 1001: Start.

[0175] Step 1002: Align the color image and the infrared image to achieve pixel-level alignment.

[0176] The computer device obtains a color image and an infrared image of the same palm image. The color image refers to an image obtained by a color camera imaging the palm based on natural light, and the infrared image refers to an image obtained by an infrared camera imaging the palm based on infrared light.

[0177] The computer device performs spatial alignment processing and / or temporal alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image, thereby achieving pixel-level alignment of the color image and the infrared image.

[0178] Step 1003: Perform palm recognition on the infrared image to determine a first palm area.

[0179] The computer device detects finger gap points in the infrared image, and determines a first palm area on the infrared image based on the finger gap points.

[0180] Step 1004: Based on the alignment relationship between the color image and the infrared image, the first palm region on the infrared image is mapped to the color image, and the second palm region is obtained on the color image.

[0181] The computer device maps the first palm area on the infrared image to the color image based on the spatial alignment relationship between the color image and the infrared image, and obtains the second palm area on the color image.

[0182] Or, the computer device maps the first palm area on the infrared image to the color image based on the time alignment relationship between the color image and the infrared image, and obtains the second palm area on the color image.

[0183] Alternatively, the computer device maps the first palm area on the infrared image to the color image based on the spatial alignment relationship and the temporal alignment relationship between the color image and the infrared image, and determines a second palm area corresponding to the first palm area on the color image.

[0184] Step 1005: performing palm comparison and recognition processing on the first palm region of the infrared image and the second palm region of the color image to determine the target object identifier corresponding to the palm image.

[0185] The computer device performs palm comparison and recognition processing on the first palm area of ​​the infrared image through an infrared image processor to determine a first object identifier corresponding to the palm image; the computer device performs palm comparison and recognition processing on the second palm area of ​​the color image through a color image processor to determine a second object identifier corresponding to the palm image; the computer device fuses the first object identifier and the second object identifier based on weight values ​​of the infrared image processor and the color image processor to obtain a target object identifier corresponding to the palm image.

[0186] Step 1006: End.

[0187] Fig.11 is a flowchart of spatial alignment of color images and infrared images provided by an exemplary embodiment of the present application. The method can be executed by a computer device, which can be Figure 2 The terminal 100 or the server 200 in the embodiment. The method comprises:

[0188] Step 1101: Start.

[0189] Step 1102: Obtain the plane pixel depth of the infrared image.

[0190] The computer device obtains the coordinate parameters of the palm in the pixel coordinate system of the infrared image.

[0191] Step 1103: using the camera intrinsic parameters of the infrared camera, convert the coordinate parameters of the palm in the infrared image into the camera coordinate system.

[0192] The computer device uses the infrared camera coordinate system to represent the coordinate parameters of the palm in the infrared image based on the camera intrinsic parameters of the infrared camera.

[0193] The camera intrinsic parameters are used to describe the conversion relationship between the coordinate parameters of the palm in the world coordinate system and the coordinate parameters of the palm in the pixel coordinate system.

[0194] Step 1104: Based on the camera extrinsic parameters, convert the infrared camera coordinate system to the color camera coordinate system.

[0195] The computer device uses a color camera coordinate system to represent the coordinate parameters of the palm in the infrared image based on the camera external parameters.

[0196] Camera extrinsics are parameters used to describe the conversion relationship between the color camera coordinate system and the infrared camera coordinate system.

[0197] Step 1105: Based on the camera intrinsic parameters of the color camera, the infrared image in the pixel coordinate system of the color image is converted to the pixel plane.

[0198] The computer device uses the pixel coordinate system of the color image to represent the coordinate parameters of the palm in the infrared image based on the camera intrinsic parameters of the color camera, and obtains the spatial alignment relationship between the color image and the infrared image.

[0199] Step 1106: End.

[0200] Fig.12 is a flowchart of obtaining a color image and an infrared image provided by an exemplary embodiment of the present application. The method can be executed by a computer device, which can be Figure 2 The terminal 100 or the server 200 in the embodiment. The method comprises:

[0201] Step 1201: Start.

[0202] Step 1202: Send the second palm region of the color image to the color picture processor.

[0203] The second palm region of the color image is sent to a color image processor, and the color image processor processes the second palm region in the color image.

[0204] Step 1203: The color image processor calculates the brightness value corresponding to the second palm area.

[0205] Step 1204: When the brightness value corresponding to the second palm area is greater than or less than the expected brightness range, adjust the exposure parameters.

[0206] When the brightness value corresponding to the second palm area is greater than or less than the expected brightness range, the computer device adjusts the exposure parameters of the color camera.

[0207] Step 1205: When the brightness value corresponding to the second palm area meets the expected brightness range, determine the exposure parameter.

[0208] When the brightness value corresponding to the second palm area meets the expected brightness range, the computer device determines the exposure parameter of the color camera.

[0209] The color camera acquires a color image based on determined exposure parameters.

[0210] Step 1206: Send the first palm region of the infrared image to the infrared picture processor.

[0211] The first palm region of the infrared image is sent to an infrared image processor, and the infrared image processor processes the first palm region in the infrared image.

[0212] Step 1207: The infrared image processor calculates the brightness value corresponding to the first palm area.

[0213] Step 1208: When the brightness value corresponding to the first palm area is greater than or less than the expected brightness range, adjust the exposure parameters.

[0214] When the brightness value corresponding to the first palm area is greater than or less than the expected brightness range, the computer device adjusts the exposure parameters of the infrared camera.

[0215] The infrared camera acquires an infrared image based on the determined exposure parameters.

[0216] Step 1209: When the brightness value corresponding to the first palm area meets the expected brightness range, determine the exposure parameter.

[0217] Step 1210: End.

[0218] Fig.13 1301 is a schematic diagram of a cross-device identity authentication method based on a palm image provided by an exemplary embodiment of the present application. The method involves an object terminal 1301, a door control device 1303 and a door control server 1302.

[0219] Among them, the object terminal 1301 establishes a communication connection with the access control application server 1302, through which the object terminal 1301 and the access control server 1302 can interact; the access control device 1303 establishes a communication connection with the access control server 1302, through which the access control device 1303 and the access control server 1302 can interact.

[0220] The cross-device authentication process includes:

[0221] 1. The subject holds the subject terminal 1301 at home, and uses the subject terminal 1301 to photograph the subject's palm to obtain the subject's palm image, and sends a palm registration request to the access control server 1302. The palm registration request carries the subject's identification and palm image.

[0222] 2. The access control server 1302 receives the palm registration request sent by the object terminal 1301, processes the palm image, obtains the palm features of the palm image, stores the palm features in correspondence with the object identifier, and sends a palm binding success notification to the object terminal 1301.

[0223] Among them, after the access control server 1302 stores the palm feature and the object identifier in correspondence, the palm feature can be used as a preset palm feature, and the corresponding object identifier can be determined later through the stored preset palm feature.

[0224] 3. The object terminal 1301 receives the palm binding success notification, displays the palm binding success notification, and prompts that the object palm image is bound to the object identifier.

[0225] The object completes palm image registration through the interaction between its own object terminal 1301 and the access control server, and can subsequently realize automatic door opening through the palm image.

[0226] 4. When the subject goes out and returns home, the access control device 1303 takes a picture of the subject's palm, obtains the subject's palm image, and sends an identity verification request to the access control server 1302, the identity verification request carrying the verification palm image.

[0227] 5. The access control server 1302 receives the identity authentication request sent by the access control device 1303, identifies and processes the verification palm image, obtains the object identification of the palm image, determines that the object is a registered object, and sends a verification success notification to the access control device 1303.

[0228] 6. The access control device 1303 receives the verification pass notification sent by the access control server 1302, and controls the door to open according to the verification pass notification so that the object can enter the room.

[0229] The above embodiment is a process of implementing cross-device identity authentication through the object terminal 1301 and the access control device 1303 .

[0230] It can be seen from the above cross-device identity authentication scenario that whether it is the palm registration stage of the interaction between the object terminal 1301 and the access control server 1302, or the palm image recognition stage of the interaction between other terminal devices and the server, after the object terminal 1301 or other terminal devices obtain the palm image, they send the palm image to the server, and the server performs palm comparison and recognition processing. In the palm comparison and recognition processing stage, the access control server 1302 compares the palm features with the preset palm features to obtain the recognition result of the current object.

[0231] Illustratively, the application scenarios of the palm image recognition method provided in the embodiments of the present application include but are not limited to the following scenarios:

[0232] For example, in the smart payment scenario:

[0233] The merchant's computer device obtains a palm image of the object by photographing the palm of the object, and uses the palm image recognition method provided in the embodiment of the present application to determine the target object identifier of the palm image, and transfers part of the resources in the resource account corresponding to the target object identifier to the merchant's resource account, thereby realizing automatic payment through the palm.

[0234] For example, in the cross-device payment scenario:

[0235] The subject can complete identity registration using a personal mobile phone at home or other private spaces, bind the subject's account to the subject's palm image, and then use the in-store device to identify the subject's palm image, determine the subject's account, and pay directly through the account.

[0236] For example, in the clock-in scenario:

[0237] The computer device obtains a palm image of the object by photographing the palm of the object, and uses the palm image recognition method provided in the embodiment of the present application to determine the target object identifier of the palm image, establish a punch-in mark for the target object identifier, and determine that the target object identifier has completed the work punch-in at the current time.

[0238] Of course, in addition to being applied to the above-mentioned scenarios, the method provided in the embodiments of the present application can also be applied to other scenarios that require palm image recognition, and the embodiments of the present application are not limited to specific application scenarios.

[0239] Fig.14 The following is a schematic diagram of the structure of a palm image recognition device provided by an exemplary embodiment of the present application. The device can be implemented as all or part of a computer device through software, hardware, or a combination of both. The device includes:

[0240] An acquisition module 1401 is used to acquire a color image and an infrared image of the same palm image, wherein the color image refers to an image obtained by imaging the palm with a color camera based on natural light, and the infrared image refers to an image obtained by imaging the palm with an infrared camera based on infrared light;

[0241] An alignment module 1402 is used to align the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image;

[0242] The recognition module 1403 is used to perform region recognition processing on the infrared image to determine a first palm region on the infrared image;

[0243] The alignment module 1402 is further configured to determine, on the color image, a second palm region corresponding to the first palm region based on an alignment relationship between the color image and the infrared image;

[0244] The recognition module 1403 is further configured to perform palm comparison and recognition processing on the first palm region of the infrared image and the second palm region of the color image to determine a target object identifier corresponding to the palm image.

[0245] In a possible implementation, the alignment module 1402 is further configured to perform spatial alignment processing and / or temporal alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image.

[0246] In a possible implementation, the alignment module 1402 is also used to obtain the coordinate parameters of the palm in the pixel coordinate system of the infrared image; based on the camera intrinsic parameters of the infrared camera, the coordinate parameters of the palm in the infrared image are represented by the infrared camera coordinate system, and the camera intrinsic parameters are used to describe the parameters of the conversion relationship between the coordinate parameters of the palm in the world coordinate system and the coordinate parameters of the palm in the pixel coordinate system; based on the camera extrinsic parameters, the coordinate parameters of the palm in the infrared image are represented by the color camera coordinate system, and the camera extrinsic parameters are used to describe the parameters of the conversion relationship between the color camera coordinate system and the infrared camera coordinate system; based on the camera intrinsic parameters of the color camera, the pixel coordinate system of the color image is used to represent the coordinate parameters of the palm in the infrared image, so as to obtain the spatial alignment relationship between the color image and the infrared image.

[0247] In a possible implementation, the recognition module 1403 is further used to map the first palm area on the infrared image to the color image based on the spatial alignment relationship between the color image and the infrared image, and obtain the second palm area on the color image.

[0248] In a possible implementation, the alignment module 1402 is also used to obtain timestamps marked on the color image and the infrared image, where the timestamp refers to temporal data marked on the color image and the infrared image when the color camera and the infrared camera are exposed; based on the timestamp, a time alignment relationship between the color image and the infrared image is obtained.

[0249] In a possible implementation, the recognition module 1403 is further used to map the first palm area on the infrared image to the color image based on the time alignment relationship between the color image and the infrared image, and obtain the second palm area on the color image.

[0250] In a possible implementation, the recognition module 1403 is further used to adjust the exposure parameter of the second palm area in the color image of the i-th frame to obtain the second palm area in the color image of the i+1-th frame when the quality parameter of the second palm area in the color image of the i-th frame is less than a preset threshold; perform palm comparison and recognition processing on the first palm area in the infrared image of the i+1-th frame and the second palm area in the color image of the i+1-th frame, fuse the palm comparison and recognition results of the first palm area and the palm comparison and recognition results of the second palm area according to a weight value, and determine the target object identifier corresponding to the palm image, where i is a positive integer.

[0251] In a possible implementation, the recognition module 1403 is further configured to detect finger gaps in the infrared image, and determine the first palm region on the infrared image based on the finger gaps.

[0252] In a possible implementation, the recognition module 1403 is further used to perform palm comparison and recognition processing on the first palm area of ​​the infrared image through an infrared image processor to determine a first object identifier corresponding to the palm image; perform palm comparison and recognition processing on the second palm area of ​​the color image through a color image processor to determine a second object identifier corresponding to the palm image; and fuse the first object identifier and the second object identifier based on weight values ​​of the infrared image processor and the color image processor to obtain a target object identifier corresponding to the palm image.

[0253] In one possible implementation, the identification module 1403 is also used to determine the weight values ​​of the infrared image processor and the color image processor based on the quality parameters of the second palm area of ​​the color image; based on the weight values ​​of the infrared image processor and the color image processor, the first object identifier and the second object identifier are fused to obtain the target object identifier corresponding to the palm image.

[0254] The wavelength of the infrared light is 940 nm.

[0255] In a possible implementation, the identification module 1403 is further used to obtain the identification distance of the palm to be identified through a short-range sensor, where the identification distance refers to the distance between the palm to be identified and the color camera and the infrared camera; based on the identification distance, determine the exposure parameters of the color camera and the infrared camera; according to the exposure parameters, obtain the color image and the infrared image of the palm to be identified; perform palm comparison and identification processing on the color image and the infrared image, and obtain the target object identification corresponding to the palm to be identified within a recognition time period, where the recognition time period refers to the time corresponding to the entire process of measuring the identification distance through the short-range sensor and performing palm comparison and identification processing; when the identification time period is greater than the time threshold, execute the palm image recognition method to obtain the target object identification corresponding to the palm image.

[0256] Fig.15 The structural block diagram of a computer device 1500 shown in an exemplary embodiment of the present application is shown. The computer device can be implemented as the server in the above-mentioned solution of the present application. The image computer device 1500 includes a central processing unit (CPU) 1501, a system memory 1504 including a random access memory (RAM) 1502 and a read-only memory (ROM) 1503, and a system bus 1505 connecting the system memory 1504 and the central processing unit 1501. The image computer device 1500 also includes a large-capacity storage device 1506 for storing an operating system 1509, an application program 1510 and other program modules 1511.

[0257] The mass storage device 1506 is connected to the central processing unit 1501 through a mass storage controller (not shown) connected to the system bus 1505. The mass storage device 1506 and its associated computer readable medium provide non-volatile storage for the image computer device 1500. That is, the mass storage device 1506 may include a computer readable medium (not shown) such as a hard disk or a compact disc read-only memory (CD-ROM) drive.

[0258] Without loss of generality, the computer-readable medium may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer storage media include RAM, Erasable Programmable Read Only Memory (EPROM), Electronically-Erasable Programmable Read-Only Memory (EEPROM) flash memory or other solid-state storage technology, CD-ROM, Digital Versatile Disc (DVD) or other optical storage, cassettes, tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer storage medium is not limited to the above. The above-mentioned system memory 1504 and mass storage device 1506 can be collectively referred to as memory.

[0259] According to various embodiments of the present disclosure, the image computer device 1500 can also be connected to a remote computer on a network through a network such as the Internet. That is, the image computer device 1500 can be connected to a network 1508 through a network interface unit 1507 connected to the system bus 1505, or the network interface unit 1507 can be used to connect to other types of networks or remote computer systems (not shown).

[0260] The memory further includes at least one computer program, which is stored in the memory. The central processing unit 1501 implements all or part of the steps in the palm image recognition method shown in the above embodiments by executing the at least one computer program.

[0261] An embodiment of the present application also provides a computer device, which includes a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the palm image recognition method provided by the above-mentioned method embodiments.

[0262] An embodiment of the present application further provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor to implement the palm image recognition method provided by the above-mentioned method embodiments.

[0263] An embodiment of the present application also provides a computer program product, which includes a computer program, and the computer program is stored in a computer-readable storage medium; the computer program is read and executed from the computer-readable storage medium by a processor of a computer device, so that the computer device executes to implement the palm image recognition method provided in the above-mentioned method embodiments.

[0264] It will be understood that in the specific implementation of the present application, the data involved, historical data, and data related to user data processing such as portraits related to user identity or characteristics, when the above embodiments of the present application are applied to specific products or technologies, need to obtain user permission or consent, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0265] It should be understood that the "plurality" mentioned in this article refers to two or more. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0266] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0267] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent switching, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A palm image recognition method, characterized in that: The method comprises: Acquire a color image and an infrared image of the same palm image, wherein the color image refers to an image obtained by imaging the palm with a color camera based on natural light, and the infrared image refers to an image obtained by imaging the palm with an infrared camera based on infrared light; Performing alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image; Performing region recognition processing on the infrared image to determine a first palm region on the infrared image; determining, on the color image, a second palm region corresponding to the first palm region based on an alignment relationship between the color image and the infrared image; When the quality parameter of the second palm area of ​​the color image of the i-th frame is less than a preset threshold, the exposure parameter of the second palm area is adjusted to obtain the second palm area of ​​the color image of the i+1-th frame; palm comparison and recognition processing is performed on the first palm area of ​​the infrared image of the i+1-th frame and the second palm area of ​​the color image of the i+1-th frame, and the palm comparison and recognition results of the first palm area and the second palm area are fused according to the weight value to determine the target object identification corresponding to the palm image, where i is a positive integer.

2. The method according to claim 1, characterized in that The aligning the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image includes: The color image and the infrared image are subjected to spatial alignment processing and / or temporal alignment processing to obtain an alignment relationship between the color image and the infrared image.

3. The method according to claim 2, characterized in that The performing spatial alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image includes: Acquire coordinate parameters of the palm in the pixel coordinate system of the infrared image; Based on the camera intrinsic parameters of the infrared camera, the coordinate parameters of the palm in the infrared image are expressed using an infrared camera coordinate system, wherein the camera intrinsic parameters are parameters for describing the conversion relationship between the coordinate parameters of the palm in the world coordinate system and the coordinate parameters of the palm in the pixel coordinate system; Based on camera extrinsics, a color camera coordinate system is used to represent coordinate parameters of the palm in the infrared image, wherein the camera extrinsics are used to describe parameters of a conversion relationship between the color camera coordinate system and the infrared camera coordinate system; Based on the camera intrinsic parameters of the color camera, the coordinate parameters of the palm in the infrared image are represented by the pixel coordinate system of the color image, so as to obtain the spatial alignment relationship between the color image and the infrared image.

4. The method according to claim 3, characterized in that The determining, on the color image, a second palm area corresponding to the first palm area based on the alignment relationship between the color image and the infrared image comprises: Based on the spatial alignment relationship between the color image and the infrared image, the first palm region on the infrared image is mapped onto the color image, and the second palm region is obtained on the color image.

5. The method according to claim 2, characterized in that: The step of performing time alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image includes: Acquire a timestamp marked on the color image and the infrared image, wherein the timestamp refers to temporal data marked on the color image and the infrared image when the color camera and the infrared camera are exposed; Based on the timestamp, a time alignment relationship between the color image and the infrared image is obtained.

6. The method according to claim 5, characterized in that The determining, on the color image, a second palm area corresponding to the first palm area based on the alignment relationship between the color image and the infrared image comprises: Based on the time alignment relationship between the color image and the infrared image, the first palm region on the infrared image is mapped onto the color image, and the second palm region is obtained on the color image.

7. The method according to claim 1, characterized in that The performing region recognition processing on the infrared image to determine the first palm region on the infrared image includes: Finger gap points in the infrared image are detected, and the first palm area on the infrared image is determined based on the finger gap points.

8. The method according to claim 1, characterized in that: The performing palm comparison and recognition processing on the first palm area of ​​the infrared image and the second palm area of ​​the color image to determine the target object identifier corresponding to the palm image includes: performing palm comparison and recognition processing on the first palm area of ​​the infrared image by an infrared image processor to determine a first object identifier corresponding to the palm image; performing palm comparison and recognition processing on the second palm area of ​​the color image by a color image processor to determine a second object identifier corresponding to the palm image; Based on the weight values ​​of the infrared image processor and the color image processor, the first object identifier and the second object identifier are fused to obtain a target object identifier corresponding to the palm image.

9. The method according to claim 8, characterized in that The step of fusing the first object identifier and the second object identifier based on the weight values ​​of the infrared image processor and the color image processor to obtain a target object identifier corresponding to the palm image includes: determining weight values ​​of the infrared image processor and the color image processor according to a quality parameter of the second palm region of the color image; Based on the weight values ​​of the infrared image processor and the color image processor, the first object identifier and the second object identifier are fused to obtain a target object identifier corresponding to the palm image.

10. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: Acquire the identification distance of the palm to be identified by a short-range sensor, wherein the identification distance refers to the distance between the palm to be identified and the color camera and the infrared camera; Based on the identification distance, determining exposure parameters of the color camera and the infrared camera; Acquiring the color image and the infrared image of the palm to be identified according to the exposure parameters; Performing palm comparison and recognition processing on the color image and the infrared image, and obtaining the target object identifier corresponding to the palm to be recognized within a recognition time period, wherein the recognition time period refers to the time corresponding to the entire process of measuring the recognition distance through the short-range sensor and performing palm comparison and recognition processing; When the recognition time period is greater than the time threshold, a palm image recognition method is executed to obtain a target object identifier corresponding to the palm image.

11. A palm image recognition device, characterized in that: The device comprises: An acquisition module, used to acquire a color image and an infrared image of the same palm image, wherein the color image refers to an image obtained by imaging the palm with a color camera based on natural light, and the infrared image refers to an image obtained by imaging the palm with an infrared camera based on infrared light; an alignment module, used for performing alignment processing on the color image and the infrared image to obtain an alignment relationship between the color image and the infrared image; A recognition module, used for performing region recognition processing on the infrared image to determine a first palm region on the infrared image; The alignment module is further used to determine a second palm area corresponding to the first palm area on the color image based on the alignment relationship between the color image and the infrared image; The recognition module is further used to adjust the exposure parameter of the second palm area in the color image of the i-th frame to obtain the second palm area in the color image of the i+1-th frame when the quality parameter of the second palm area in the color image of the i-th frame is less than a preset threshold; perform palm comparison and recognition processing on the first palm area in the infrared image of the i+1-th frame and the second palm area in the color image of the i+1-th frame, and fuse the palm comparison and recognition results of the first palm area and the palm comparison and recognition results of the second palm area according to a weight value to determine the target object identification corresponding to the palm image, where i is a positive integer.

12. A computer device, characterized in that: The computer device comprises: a processor and a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the palm image recognition method according to any one of claims 1 to 10.

13. A computer storage medium, characterized in that: The computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the palm image recognition method according to any one of claims 1 to 10.

14. A computer program product, characterized in that The computer program product comprises a computer program, which is stored in a computer-readable storage medium; the computer program is read and executed from the computer-readable storage medium by a processor of a computer device, so that the computer device executes the palm image recognition method according to any one of claims 1 to 10.

Images