Iris feature acquisition method, object recognition method, apparatus, device, medium, and product

Abstract

An iris feature acquisition method, executed by an electronic device, the method comprising: determining an iris feature acquisition policy of an iris recognition device for a user, the iris feature acquisition policy indicating a means of acquiring an iris feature by using light spot imaging, the iris feature acquisition policy comprising at least one light spot imaging mode (201); by means of the iris recognition device and on the basis of a light spot imaging attribute indicated by the light spot imaging mode, acquiring an iris image, of the user, on which a light spot is projected, so as to obtain a light spot iris image in the light spot imaging mode (202); performing feature extraction on the light spot iris image in the light spot imaging mode, to obtain a light spot iris feature in the light spot imaging mode (203); on the basis of the light spot iris feature in the light spot imaging mode, determining a light spot iris feature of the user under the iris feature acquisition policy (204); and storing the light spot iris feature of the user under the iris feature acquisition policy into a database associated with the iris recognition device (205).

Description

Iris feature acquisition method, object recognition method, device, equipment, medium and product

[0001] Related applications

[0002] This application claims priority to Chinese patent application number 2023108913835, filed on July 19, 2023, entitled “Iris data processing method, object recognition method and related equipment,” the entire text of which is hereby incorporated by reference. Technical Field

[0003] The present application relates to the field of artificial intelligence technology, and specifically to an iris feature acquisition method, object recognition method, device, equipment, medium and product. Background Art

[0004] With the development of internet technology, identity recognition technology has found an increasingly broad range of applications, including in electronic payments. Common identification methods include fingerprints, faces, palm prints, and irises. Iris recognition, a form of biometric identification, relies on the iris to identify individuals. The uniqueness of iris features also determines the uniqueness of identity recognition. Therefore, iris features can be used for identity recognition.

[0005] In current technologies, during the iris feature entry phase, a single iris image of the user is typically captured, iris features are extracted from the image, and the iris features are stored in a database. During iris recognition, the captured single iris image is also directly matched against the iris features in the database, and the user's identity is determined based on the matching results.

[0006] However, the current method of recording iris features is less secure because the user's iris information is easily leaked and easily misused, posing a security risk to the user.

[0007] Summary of the Invention

[0008] Embodiments of the present application provide an iris feature acquisition method, an object recognition method, an apparatus, a device, a medium, and a product.

[0009] In one aspect, a method for collecting iris features is provided, which is performed by an electronic device and includes:

[0010] Determining an iris feature collection strategy for the user by the iris recognition device, wherein the iris feature collection strategy indicates a method for collecting iris features using light spot imaging, and the iris feature collection strategy includes at least one light spot imaging mode;

[0011] collecting, by the iris recognition device, an iris image of the user projected with a light spot based on the light spot imaging properties indicated by the light spot imaging mode, to obtain a light spot iris image in the light spot imaging mode;

[0012] performing feature extraction on the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode;

[0013] determining the light spot iris features of the user under the iris feature acquisition strategy based on the light spot iris features in the light spot imaging mode; and

[0014] The light spot iris features of the user under the iris feature collection strategy are stored in a database associated with the iris recognition device.

[0015] In another aspect, an object recognition method is provided, which is performed by an electronic device and includes:

[0016] Determining a target iris feature acquisition strategy for an iris recognition device for an object to be identified, wherein the target iris feature acquisition strategy indicates a method for acquiring iris features of the object to be identified using spot imaging, and the target iris feature acquisition strategy includes at least one spot imaging mode;

[0017] By means of the iris recognition device, based on the light spot imaging properties indicated by the light spot imaging mode, an iris image of the object to be identified with a light spot projected thereon is collected to obtain a light spot iris image in the light spot imaging mode;

[0018] performing feature extraction on the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode;

[0019] Determining the target light spot iris features of the object to be identified under the target iris feature acquisition strategy based on the light spot iris features in the light spot imaging mode; and

[0020] The target light spot iris feature is matched with iris data stored in a database associated with the iris recognition device to identify the object to be identified and determine the identity information of the object to be identified. The iris data includes at least one light spot iris feature.

[0021] In another aspect, an iris feature acquisition device is provided, comprising:

[0022] a first strategy determination unit, configured to determine an iris feature collection strategy for the iris recognition device for the user, wherein the iris feature collection strategy indicates a method for collecting iris features using light spot imaging, and the iris feature collection strategy includes at least one light spot imaging mode;

[0023] a first acquisition unit, configured to acquire, through the iris recognition device, an iris image of the user projected with a light spot based on the light spot imaging properties indicated by the light spot imaging mode, to obtain a light spot iris image in the light spot imaging mode;

[0024] a first extraction unit, configured to perform feature extraction on the spot iris image in the spot imaging mode to obtain a spot iris feature in the spot imaging mode;

[0025] A first feature determining unit is configured to determine the light spot iris feature of the user under the iris feature acquisition strategy based on the light spot iris feature in the light spot imaging mode; and

[0026] A storage unit is used to store the light spot iris features of the user under the iris feature collection strategy in a database associated with the iris recognition device.

[0027] In another aspect, an embodiment of the present application provides an object recognition device, comprising:

[0028] a second strategy determination unit, configured to determine a target iris feature acquisition strategy of the iris recognition device for the object to be identified, wherein the target iris feature acquisition strategy indicates a method of acquiring iris features of the object to be identified by using light spot imaging, and the target iris feature acquisition strategy includes at least one light spot imaging mode;

[0029] a second acquisition unit, configured to acquire, by the iris recognition device, an iris image of the object to be identified projected with a light spot based on the light spot imaging properties indicated by the light spot imaging mode, so as to obtain a light spot iris image in the light spot imaging mode;

[0030] a second extraction unit, configured to perform feature extraction on the spot iris image in the spot imaging mode to obtain a spot iris feature in the spot imaging mode;

[0031] A second feature determination unit is configured to determine the target light spot iris feature of the object to be identified under the target iris feature acquisition strategy based on the light spot iris feature in the light spot imaging mode; and

[0032] The recognition unit is used to match the target light spot iris feature with the iris data stored in the database associated with the iris recognition device to identify the object to be identified and determine the identity information of the object to be identified, wherein the iris data includes at least one light spot iris feature.

[0033] On the other hand, an electronic device is provided, including a processor and a memory, wherein the memory stores multiple instructions, and the processor loads the instructions to execute the steps in the iris feature acquisition method and object recognition method provided in the embodiments of the present application.

[0034] On the other hand, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the iris feature acquisition method and the object recognition method provided in the embodiments of the present application are implemented.

[0035] On the other hand, a computer program product is provided, including a computer program or instructions, which, when executed by a processor, implements the steps of the iris feature acquisition method and the object recognition method provided in the embodiments of the present application.

[0036] The details of one or more embodiments of the present application are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the present application will become apparent from the description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the conventional technology, the following briefly introduces the drawings required for use in the embodiments or the conventional technology descriptions. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the disclosed drawings without any creative work.

[0038] FIG1 is a schematic diagram of a scenario of an iris feature acquisition method and an object recognition method provided in an embodiment of the present application;

[0039] FIG2 is a flow chart of an iris feature acquisition method provided in an embodiment of the present application;

[0040] FIG3 is a schematic diagram of an apparatus for an iris feature acquisition method and an object recognition method provided in an embodiment of the present application;

[0041] FIG4 is an illustration of an iris feature acquisition method and an object recognition method provided in an embodiment of the present application;

[0042] FIG5 is another illustration of the iris feature acquisition method and object recognition method provided by an embodiment of the present application;

[0043] FIG6 is another illustration of the iris feature acquisition method and object recognition method provided by an embodiment of the present application;

[0044] FIG7 is another illustration of the iris feature acquisition method and object recognition method provided by an embodiment of the present application;

[0045] FIG8 is another diagram illustrating the iris feature acquisition method and object recognition method provided by an embodiment of the present application;

[0046] FIG9 is another illustration of the iris feature acquisition method and object recognition method provided by an embodiment of the present application;

[0047] FIG10 is another illustration of the iris feature acquisition method and object recognition method provided in an embodiment of the present application;

[0048] FIG11 is another diagram illustrating the iris feature acquisition method and object recognition method provided in an embodiment of the present application;

[0049] FIG12 is another illustration of the iris feature acquisition method and object recognition method provided in an embodiment of the present application;

[0050] FIG13 is a flow chart of an object recognition method provided in an embodiment of the present application;

[0051] FIG14 is another flow chart of the iris feature acquisition method and object recognition method provided in an embodiment of the present application;

[0052] FIG15 is a page diagram of an iris feature acquisition method and an object recognition method provided in an embodiment of the present application;

[0053] FIG16 is a schematic diagram of the structure of an iris feature acquisition device provided in an embodiment of the present application;

[0054] FIG17 is a schematic diagram of the structure of an object recognition device provided in an embodiment of the present application;

[0055] FIG18 is a schematic structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0057] Embodiments of the present application provide an iris feature acquisition method, an object recognition method, an apparatus, a device, a medium, and a product.

[0058] Specifically, an embodiment of the present application provides an iris feature acquisition device suitable for a first electronic device, which may be a terminal or other device; an embodiment of the present application also provides an object recognition device suitable for a second electronic device, which may be a terminal or other device.

[0059] As shown in Figure 1, a terminal and a server jointly perform an iris feature collection method and an object recognition method. The iris feature collection and object recognition system provided in this embodiment includes a terminal 10 and a server 11. The terminal 10 and the server 11 are connected via a network, such as a wired or wireless network. The iris feature collection and object recognition device can be integrated into the terminal.

[0060] In one embodiment, terminal 10 can be configured to: determine an iris feature collection strategy for a user by an iris recognition device, the iris feature collection strategy indicating a method for collecting iris features using spot imaging, and the iris feature collection strategy including at least one spot imaging mode; collect, via the iris recognition device, an iris image of the user projected with a spot based on the spot imaging properties indicated by the spot imaging mode, to obtain a spot iris image in the spot imaging mode; perform feature extraction on the spot iris image in the spot imaging mode to obtain spot iris features in the spot imaging mode; determine the spot iris features of the user under the iris feature collection strategy based on the spot iris features in the spot imaging mode; and transmit the spot iris features of the user under the iris feature collection strategy to server 11, for storage by server 11 in a database associated with the iris recognition device. Terminal 10 can include a mobile phone, an intelligent voice interaction device, a smart home appliance, an in-vehicle terminal, a virtual reality device, an aircraft, a tablet computer, a laptop computer, or a personal computer (PC). Terminal 10 can also be configured with a client, which can be an application client or a browser client.

[0061] The server 11 can be configured to receive the user's light spot iris features under the iris feature collection strategy sent by the terminal 10, and store the user's light spot iris features under the iris feature collection strategy in a database associated with the iris recognition device. The server 11 can be an independent physical server, a server cluster or a distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0062] In another embodiment, the terminal 10 can be used to: determine a target iris feature collection strategy of the iris recognition device for the object to be identified, the target iris feature collection strategy indicating a method of collecting iris features of the object to be identified using spot imaging, and the target iris feature collection strategy including at least one spot imaging mode; collect, through the iris recognition device, an iris image of the object to be identified with a spot projected thereon based on the spot imaging properties indicated by the spot imaging mode, to obtain a spot iris image in the spot imaging mode; send the spot iris image in the spot imaging mode to the server 11, so that the server 11 performs identity recognition on the object to be identified based on the spot iris image in the spot imaging mode; and receive identity information of the object to be identified sent by the server 11.

[0063] Among them, the server 11 can be used to: receive the spot iris image in the spot imaging mode sent by the terminal 10, perform feature extraction on the spot iris image in the spot imaging mode, and obtain the spot iris feature in the spot imaging mode; determine the target spot iris feature of the object to be identified under the target iris feature acquisition strategy based on the spot iris feature in the spot imaging mode; use the target spot iris feature to match the iris data stored in the database associated with the iris recognition device to identify the object to be identified and determine the identity information of the object to be identified, where the iris data includes at least one spot iris feature; and finally, send the identity information of the object to be identified to the terminal 10.

[0064] The iris feature acquisition method and object recognition method provided in the embodiments of the present application relate to the computer vision technology direction in the field of artificial intelligence, and specifically relate to iris recognition technology.

[0065] Artificial intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive field within computer science that seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. AI also studies the design principles and implementation methods of various intelligent machines, enabling them to possess the capabilities of perception, reasoning, and decision-making. AI technology is an interdisciplinary discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, pre-trained models, operating / interaction systems, and mechatronics. Pre-trained models, also known as large models or basic models, can be fine-tuned and widely applied to downstream tasks across various AI domains. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0066] Computer vision (CV) is the science of making machines "see." Specifically, it refers to machine vision, which uses cameras and computers to replace the human eye in identifying and measuring objects, and then further processes the images to create images more suitable for human observation or transmission to instruments. As a scientific discipline, computer vision studies related theories and technologies, aiming to build artificial intelligence systems that can extract information from images or multidimensional data. Large model technology has brought significant changes to the development of computer vision technology. Pre-trained models in the field of vision, such as the Swin Transformer, ViT, V-MOE, and MAE, can be fine-tuned to quickly and widely apply to specific downstream tasks. Computer vision technology generally includes image processing, image recognition, image semantic understanding, image retrieval, optical character recognition (OCR), video processing, video semantic understanding, video content / behavior recognition, 3D object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, and other technologies. It also includes common biometric recognition technologies such as facial recognition, fingerprint recognition, and iris recognition.

[0067] Iris recognition technology, a biometric identification technology within artificial intelligence, uses iris texture information to identify individuals. The human eye is composed of the sclera, iris, pupil, lens, and retina. The iris is the circular ring-shaped portion between the black pupil and the white sclera. It contains numerous interwoven features such as spots, filaments, coronae, striae, and crypts. Iris features are unique, which in turn determines the uniqueness of identity recognition. Therefore, iris features can be used for identity recognition.

[0068] It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments.

[0069] This embodiment will be described from the perspective of an iris feature acquisition device. The iris feature acquisition device can be integrated into a first electronic device, which can be a server, a terminal or other device.

[0070] This embodiment can be applied to various scenarios such as cloud technology, artificial intelligence, smart transportation, and assisted driving.

[0071] It is understandable that in the specific implementation of this application, related data such as user information (such as iris) is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0072] As shown in FIG2 , the specific process of the iris feature collection method may be as follows:

[0073] 201. Determine an iris feature collection strategy for a user by an iris recognition device. The iris feature collection strategy indicates a method of collecting iris features using light spot imaging. The iris feature collection strategy includes at least one light spot imaging mode.

[0074] Specifically, the iris recognition device can be used to collect iris features and perform identity recognition on the collected iris image. For example, the iris recognition device can be VR (Virtual Reality) glasses, door locks, safes, etc. The VR device can be in the form of the device shown in Figure 3. The iris recognition device can be the first electronic device or the second electronic device, or it can be a standalone device connected to the first electronic device or the second electronic device.

[0075] The user is specifically the natural person whose light spot iris features need to be collected. The collected light spot iris features can be used for subsequent iris recognition.

[0076] The iris feature collection policy can be set by the iris recognition device or customized by the user. Specifically, different devices can use different iris feature collection policies. This supports device differentiation, ensuring that iris features collected by device A can only be used by device A and not by device B, thereby improving the security of iris recognition. Furthermore, different users can customize their own iris feature collection policies, which will be used for every iris recognition session.

[0077] Specifically, the iris feature acquisition strategy includes at least one light spot imaging mode, which can be a mode that forms a light spot on the iris when imaging the iris. The light spot can be formed using a mask, which can be located in front of the iris recognition device's infrared light or camera lens. Optionally, in some embodiments, the mask shapes of different iris recognition devices can be different, so that the light spot shapes formed under the masks of different shapes also vary. This allows different iris feature acquisition strategies to be implemented on different iris recognition devices, achieving device differentiation in iris feature acquisition strategies and improving iris recognition security.

[0078] Different light spot imaging modes indicate different light spot imaging attributes, which may refer to the imaging attributes of the light spot on the iris. These imaging attributes may include the distribution position of the light spot on the iris, the light spot shape, the light spot illumination order, etc., which are not limited in this embodiment. The light spot illumination order specifically refers to the order in which the light spot imaging modes are executed in the iris feature acquisition strategy.

[0079] For example, a certain iris feature acquisition strategy may be to first apply a light spot below the iris, then apply a light spot above the iris, and finally apply a light spot to the right of the iris. The iris feature acquisition strategy includes three light spot imaging modes, which are: applying a light spot below the iris, applying a light spot above the iris, and applying a light spot to the right of the iris.

[0080] Specifically, the iris recognition technology solution mainly includes the following five steps:

[0081] 1. Collect iris images: Use an iris camera or other equipment to photograph and collect the subject's iris to obtain an iris image.

[0082] 2. Preprocessing iris images: The collected iris images are preprocessed, including image denoising, cropping, enhancement and other operations to improve the quality of the iris images.

[0083] 3. Feature extraction: Through the texture features, stability features and other information in the iris image, the independent identification features of the iris are extracted, and an iris feature template library is established based on the extracted independent identification features of the iris.

[0084] 4. Matching and recognition: Compare and match the iris image to be identified with the stored iris feature template to confirm the iris identity information.

[0085] 5. Decision output: Make judgments based on the matching score and threshold, output the iris recognition results, and determine authentication or rejection based on the iris recognition results.

[0086] In current related technologies, a single-frame iris image is usually used for matching, so the user's iris information can be easily stolen, posing a security risk to the user.

[0087] The iris feature collection method of this application can integrate light spot imaging into iris information, which can play a certain protective role. Specifically, this application can require combining the light spot imaging of a specific device and fusing multiple frames to calculate a unique feature, rather than directly using the user's single-frame iris feature. This can better protect the iris biometric feature and can also perform differentiated adaptation for each device, so that the features collected by device A can only be used by device A, and cannot be used by device B.

[0088] It should be noted that if a user uses a target iris feature acquisition strategy to record spot iris features during the iris feature entry phase, then during the iris recognition phase, the user must use the same target iris feature acquisition strategy to acquire iris images in order to successfully identify the user. The same target iris feature acquisition strategy here specifically refers to the same attributes, which can include the same order of spot imaging patterns, the same spot shape, and the same spot location on the iris.

[0089] 202. Using an iris recognition device, based on the light spot imaging properties indicated by the light spot imaging mode, collect an iris image of the user projected with a light spot, to obtain a light spot iris image in the light spot imaging mode.

[0090] The spot iris image in the spot imaging mode includes the spot formed in the spot imaging mode. Specifically, the spot iris image can be an infrared image. As shown in Figure 4, the spot iris image collected by the iris recognition device is fused with the spot.

[0091] Specifically, the iris feature acquisition module of an iris recognition device captures an infrared image. When infrared light is projected onto the user's iris, it forms a light spot. When the user's eyes turn at different angles, the light spot image will differ, and thus the calculated iris features will differ. Similarly, different lighting methods can also lead to differences in light spot image formation. Therefore, in some embodiments, different devices can use different lighting methods to achieve device differentiation in iris recognition.

[0092] In this embodiment, the user's eyeballs can rotate in different directions for different spot imaging modes, or different lighting methods can be used for different spot imaging modes. These different lighting methods may include different lighting angles or different spot shapes. This allows different spot imaging modes to form different spots, resulting in multiple frames of different spot imaging images, which can then be fused into a unique feature.

[0093] Optionally, in this embodiment, the step of “collecting, by the iris recognition device, an iris image of the user projected with a light spot based on the light spot imaging properties indicated by the light spot imaging mode, to obtain a light spot iris image in the light spot imaging mode” may include:

[0094] Through the iris recognition device, based on the spot imaging properties indicated by the spot imaging mode, the user is guided to rotate his eyeballs to collect the iris image with the spot projected by the user, and obtain the spot iris image in the spot imaging mode.

[0095] For example, if the light spot imaging attribute indicated by the light spot imaging mode is that the light spot is hitting the right side of the iris, the user may be guided to turn the eyeball to a corresponding angle so that the light spot is hitting the right side of the iris.

[0096] In a specific embodiment, the iris recognition device may include a display screen that can display information for guiding the user to rotate their eyeballs. It is understood that other methods can also be used to guide the user to rotate their eyeballs.

[0097] Optionally, in this embodiment, the iris recognition device includes an image acquisition module and at least one infrared light module.

[0098] The step of "collecting, through the iris recognition device, an iris image of the user projected with a light spot based on the spot imaging properties indicated by the spot imaging mode, to obtain a spot iris image in the spot imaging mode" may include: controlling the lighting mode of the infrared light module to switch to a target lighting mode based on the spot imaging properties indicated by the spot imaging mode; and collecting, through the image acquisition module, an iris image of the user projected with a light spot based on the target lighting mode, to obtain a spot iris image in the spot imaging mode.

[0099] The image acquisition module may be a camera or other image capturing module. The infrared light module may include an infrared light angle and a corresponding light spot shape.

[0100] For example, if the light spot imaging attribute indicated by the light spot imaging mode is that the light spot is projected onto the right side of the iris, the lighting angle of the infrared light module may be controlled so that the formed light spot is projected onto the right side of the iris.

[0101] Optionally, in one embodiment, the step of “controlling the infrared light module's lighting mode to switch to the target lighting mode based on the spot imaging properties indicated by the spot imaging mode” may include: controlling the on / off state of each infrared light module based on the spot imaging properties indicated by the spot imaging mode, so that the lighting mode of the infrared light module is switched to the target lighting mode. Optionally, in one embodiment, the step of “controlling the infrared light module's lighting mode to switch to the target lighting mode based on the spot imaging properties indicated by the spot imaging mode” may include: moving the position of the infrared light module based on the spot imaging properties indicated by the spot imaging mode, so that the lighting mode of the infrared light module is switched to the target lighting mode.

[0102] The infrared light on the iris recognition device can be turned on and off according to a preset method to achieve lighting at different angles. The infrared light module can also be moved on the iris recognition device according to a preset movement pattern to achieve lighting at different angles.

[0103] In some embodiments, as shown in Figure 5, the infrared light on the iris recognition device can support multiple lighting angles by rotating or moving left and right, thereby achieving different light spot imaging and capturing different light spot effect frames. It is understood that rotation / movement of the infrared light is not required. In other embodiments, multiple infrared lights can be equipped and multiple lighting angles can be achieved by controlling the on and off of the infrared lights.

[0104] As shown in Figure 6, the shape of the light spot in this embodiment can also be customized. Specifically, the shape of the light spot can be changed using a mask. Masks can be mainly divided into lens masks and light masks. Lens masks are placed in front of the camera lens of the infrared camera, while light masks are placed in front of the infrared light. Figure 6 shows a lens mask. The four-pointed star hole in the center of the shape mask can be used to make the formed light spot have a corresponding shape.

[0105] In a specific scenario, refer to Figure 7, which shows a schematic diagram of a stand for iris recognition for both eyes. The display screen in Figure 7 is optional and can be omitted. Refer to Figure 8, which shows a schematic diagram of a stand for iris recognition for one eye. Similarly, the display screen in Figure 8 is optional and can be omitted. In this embodiment, a glasses stand equipped with an infrared fill light and an infrared camera is required to support the collection of iris information. This glasses stand can be part of the iris recognition device.

[0106] Among them, for the infrared light, it is necessary to be able to achieve lighting at different angles to facilitate the camera to capture different light spots and iris imaging. Specifically, the infrared light can be designed to be static and fixed, or it can be designed to be moving and rotatable, allowing the device to control the movement mode to achieve lighting at different angles. In addition, multiple infrared lights can be equipped as needed, and lighting at different angles can be achieved by controlling the on and off of multiple infrared lights. In some embodiments, the user may also be required to rotate the eyeballs to form different light spot features during recognition, such as by guiding the user to rotate the eyeballs through a display screen; it is understandable that if the user can know the operation method through other means, a display screen may not be required.

[0107] Optionally, in this embodiment, lens masks, light masks, and other methods can be used to customize the spot shape and achieve device differentiation. Different devices can use different spot shapes. For example, the mask shape used by device A can be circular, while the mask shape used by device B can be diamond-shaped. In this way, the spot shapes formed by the two devices are different.

[0108] It should be noted that device differentiation can also be achieved through other means, such as through the direction of lighting. For example, the iris feature acquisition strategy of device A may have lighting directions above and below the iris, while the iris feature acquisition strategy of device B may have lighting directions to the left and right of the iris.

[0109] Optionally, in this embodiment, the spot imaging modes in the iris feature acquisition strategy are arranged in a preset acquisition order. The step of "capturing, by the iris recognition device, an iris image of the user projected with a spot based on the spot imaging properties indicated by the spot imaging mode, to obtain a spot iris image in the spot imaging mode" may include determining, based on the preset acquisition order, a target spot imaging mode to be currently executed from the iris feature acquisition strategy; capturing, by the iris recognition device, an iris image of the user projected with a spot based on the spot imaging properties indicated by the target spot imaging mode, to obtain a spot iris image in the target spot imaging mode; after the spot iris image in the target spot imaging mode passes quality inspection, determining, based on the preset acquisition order, a new target spot imaging mode to be currently executed from the iris feature acquisition strategy; and returning to the step of capturing, by the iris recognition device, an iris image of the user projected with a spot based on the spot imaging properties indicated by the target spot imaging mode, to obtain a spot iris image in the target spot imaging mode, until a spot iris image that passes quality inspection under each spot imaging mode in the iris feature acquisition strategy is obtained.

[0110] The quality detection of the light spot iris image may include iris and eyelash occlusion judgment, exposure judgment, eyelid occlusion judgment, etc.

[0111] For example, the iris feature acquisition strategy includes three spot imaging modes, which are arranged in the following order: applying a spot below the iris, applying a spot above the iris, and applying a spot to the right of the iris. When acquiring a spot iris image, the first spot imaging mode can be used as the target spot imaging mode, applying a spot below the iris, obtaining a spot iris image with the spot below the iris, and then performing a quality inspection on the image using the optimization algorithm. After the quality inspection passes, the second spot imaging mode can be used as the target spot imaging mode, applying a spot above the iris, obtaining a spot iris image with the spot above the iris, and then performing a quality inspection on the image using the optimization algorithm. After the quality inspection passes, the third spot imaging mode can be used as the target spot imaging mode, applying a spot above the iris, obtaining a spot iris image with the spot above the iris, and then performing a quality inspection on the image using the optimization algorithm.

[0112] 203. Perform feature extraction on the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode.

[0113] Optionally, in this embodiment, the step of “performing feature extraction on the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode” may include: performing iris segmentation processing on the spot iris image in the spot imaging mode to obtain the spot iris area in the spot imaging mode; performing normalization processing on the spot iris area to obtain the normalized spot iris area; performing feature extraction on the normalized spot iris area to obtain the spot iris features in the spot imaging mode.

[0114] Specifically, before performing iris segmentation processing, the original spot iris image in the spot imaging mode can be subjected to image preprocessing. The image preprocessing here can include preprocessing operations such as filtering, histogram equalization, and grayscale conversion. Image quality can be improved through image preprocessing.

[0115] Among them, after obtaining the spot iris area in the spot imaging mode, the light spot iris area can also be subjected to quality detection. The quality detection can include iris eyelash occlusion judgment, exposure judgment, eyelid occlusion judgment, etc. Through quality detection, higher quality pictures can be screened out.

[0116] Optionally, in this embodiment, the step of “performing iris segmentation processing on the spot iris image in the spot imaging mode to obtain the spot iris area in the spot imaging mode” may include: calculating gradient information of each pixel point in the spot iris image in the spot imaging mode; selecting at least one target pixel point from the pixel points of the spot iris image according to the gradient information; performing a connection operation on the target pixel points to obtain a closed contour; and performing iris segmentation processing on the spot iris image according to the closed contour to obtain the spot iris area in the spot imaging mode.

[0117] Iris segmentation can be used to segment the iris region from the iris image. Iris segmentation isolates the iris from the entire image, so the inner and outer boundaries of the iris must be located. Edge detection algorithms, such as the Canny edge detection operator, can be used to extract the iris edge. Specifically, the inner and outer boundaries of the iris can be searched for by applying the gradient of the image's grayscale relative to position, taking advantage of the approximate circular shape of the inner and outer boundaries.

[0118] The gradient information of a pixel point may include information on the gradient magnitude and gradient direction.

[0119] In a specific embodiment, before performing gradient calculation, the spot iris image in the spot imaging mode can be grayscaled and smoothed. After grayscale and smoothing, a smoothed grayscale image is obtained. The gradient amplitude and direction of the smoothed grayscale image are then calculated to obtain the corresponding gradient amplitude and direction image, where the gradient amplitude and gradient direction can be calculated using equations (1) and (2), respectively, as follows:

[0120] Among them, G represents the gradient amplitude, G x and G y They represent the gradient values ​​of the image in the x-axis and y-axis directions respectively, and α represents the gradient direction.

[0121] After obtaining the gradient magnitude and direction, the non-maximum suppression technique can be used to filter pixels near the gradient direction, retaining the pixel with the largest gradient magnitude as the target pixel. Specifically, the non-maximum suppression method can be to compare each pixel with two neighboring pixels with the same gradient. If the gradient value is not the maximum value among these three pixels, the pixel is suppressed, that is, the pixel value of this pixel is set to zero. The final non-zero pixel is the target pixel; non-maximum suppression can eliminate non-edge pixels.

[0122] Target pixels can be divided into high-threshold and low-threshold groups based on their gradient magnitudes. High-threshold pixels are identified as foreground points, and these pixels are then connected to form edges based on the foreground points. Specifically, starting from the foreground point, the low-threshold pixels can be connected to the foreground point to form a closed contour, or a complete edge, thereby achieving iris segmentation.

[0123] As shown in FIG9 , the light spot iris region obtained by segmenting the light spot iris image using the segmentation algorithm of the above embodiment is shown, wherein the predicted light spot iris region is the light spot iris region obtained using the above segmentation algorithm. As can be seen from FIG9 , the predicted light spot iris region and the actual light spot iris region are almost identical, therefore, the above segmentation algorithm has high accuracy.

[0124] In one embodiment, the step of "normalizing the light spot iris region to obtain a normalized light spot iris region" may involve converting different light spot iris regions to the same features and measurement scale, thereby facilitating subsequent feature extraction and matching. Specifically, there are various iris normalization methods, such as polar coordinate transformation and strip projection.

[0125] The method of achieving iris normalization based on strip projection is to project the annular spot iris area into a strip. Specifically, the iris image is converted into a strip of fixed width. Unlike polar coordinate transformation, the strip projection method can better preserve the horizontal and vertical information in the iris image and eliminate the influence of transformations such as scaling and translation on iris recognition. This process can be expressed by the following equation (3): P(x,y)=I(xcosθ+ysinθ) (3)

[0126] Where P(x,y) is the projected strip image, and I(x,y) is the original iris image, i.e., the iris area of ​​the light spot before normalization. Figure 10 shows the normalized iris area of ​​the light spot obtained by strip projection.

[0127] Optionally, in this embodiment, the step of “performing feature extraction on the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode” may include: performing filtering processing on the spot iris image in the spot imaging mode to obtain a response function of each pixel point in the spot iris image in the spot imaging mode; extracting frequency information and direction information corresponding to the response function of each pixel point; and performing mapping processing on the spot iris image in the spot imaging mode according to the frequency information and direction information to obtain the spot iris features in the spot imaging mode.

[0128] Among them, the step of "extracting features from the spot iris image in the spot imaging mode" may specifically include: performing iris segmentation processing on the spot iris image in the spot imaging mode, normalizing the spot iris area obtained by segmentation, and then extracting features from the normalized spot iris area to obtain the spot iris features in the spot imaging mode.

[0129] The light spot iris features include light spot iris frequency features and light spot iris direction features.

[0130] In a specific embodiment, a set of appropriate Gabor filters can be selected and applied to the normalized spot iris area to obtain the response function of each pixel; specifically, as shown in equations (4) and (5): R(x,y,λ,θ,ψ,γ)=G(x,y,λ,θ,ψ,γ)*I(x,y) (5)

[0131] Among them, formula (4) is the formula corresponding to the Gabor filter, formula (5) is the formula corresponding to the response function, G represents the Gabor filter, R represents the response function, λ represents the spatial frequency, θ represents the direction, ψ represents the phase offset, γ represents the aspect ratio, and I represents the input spot iris image (specifically, the spot iris area).

[0132] After obtaining the response function of each pixel, the frequency and direction of the response function can be extracted. That is, the frequency and direction of the response function can be extracted through the corresponding Gabor filter. Then, the frequency and direction features corresponding to the light spot iris area are mapped to a polar coordinate system. Then, a suitable threshold is used for binarization processing. Points greater than the preset threshold are set to 1, and points less than the preset threshold are set to 0. This binary iris feature map is obtained. This binary iris feature map is the light spot iris feature of the above embodiment. It can include frequency feature encoding and directional feature encoding, as shown in Figure 11.

[0133] Among them, Gabor is a linear filter used for edge extraction. Its frequency and direction expression are similar to the human visual system. It can provide good direction selection and scale selection characteristics, and is insensitive to illumination changes. Therefore, it is very suitable for texture analysis.

[0134] 204. Determine the light spot iris features of the user under the iris feature collection strategy based on the light spot iris features in the light spot imaging mode.

[0135] Specifically, the light spot iris features under each light spot imaging mode can be fused to obtain the light spot iris features of the user under the iris feature acquisition strategy. The fusion method here can include weighted averaging, etc., which is not limited in this embodiment.

[0136] Optionally, in one embodiment, different spot imaging modes indicate different spot imaging properties; the step of "determining the spot iris features of the user under the iris feature acquisition strategy based on the spot iris features under the spot imaging mode" may include: determining the weight information corresponding to each spot iris feature under each spot imaging mode; according to the weight information corresponding to each spot iris feature under each spot imaging mode, fusing the spot iris features under each spot imaging mode to obtain the spot iris features of the user under the iris feature acquisition strategy for iris recognition.

[0137] The weight information corresponding to each light spot iris feature in each light spot imaging mode may be determined according to the clarity of the light spot iris feature in each light spot imaging mode.

[0138] In one specific embodiment, a weight can be assigned to each spot iris feature under each spot imaging mode to indicate its importance. The weight can be customized by the algorithm designer, for example, by evaluating the weight based on iris feature clarity. The weighted average of the spot iris features under all spot imaging modes is then calculated as the final spot iris feature representation, i.e., the user's spot iris feature under the iris feature acquisition strategy.

[0139] For example, the iris feature acquisition strategy includes n light spot imaging modes, and the light spot iris features extracted by them are f1, f2, ..., f n , the corresponding weights are ω1, ω2, …, ω n , then the final light spot iris feature representation can be expressed by formula (6):

[0140] Among them, F is the final light spot iris feature representation, that is, the light spot iris feature of the user under the iris feature collection strategy.

[0141] 205. Store the light spot iris features of the user under the iris feature collection strategy in a database associated with the iris recognition device.

[0142] Specifically, as shown in FIG12 , the spot iris features obtained under different spot imaging modes are different. Specifically, since the spots are distributed at different positions in the spot iris image, the extracted spot iris features are also different. Different weights can be assigned to different spot iris features. For example, for spot iris feature 1 including spot 1, its weight can be set to a; for spot iris feature 2 including spot 2, its weight can be set to b; for spot iris feature 3 including spot 3, its weight can be set to c. After obtaining the spot iris features obtained under each spot imaging mode, the spot iris features obtained under all spot imaging modes can be fused, such as weighted averaging, to obtain a unique fused feature (i.e., the spot iris feature under the iris feature acquisition strategy in the above embodiment). This feature fuses multiple spot features, and the feature is then stored in a database for subsequent iris recognition.

[0143] The iris feature acquisition method provided in this application utilizes the differences in light spot imaging to collect multiple frames of light spot iris images for cache fusion processing, thereby improving the security and robustness of iris recognition and effectively preventing the misuse of a user's iris information. Specifically, by changing the position and shape of the eye spot, it is possible to confirm whether the eye is actually an eyeball during recognition, preventing the iris recognition device from being spoofed by an unauthorized user using iris information recorded on a flat surface. For example, in traditional technology, printing specific iris information on paper can deceive the iris recognition device.

[0144] Moreover, this application can support user encryption and confirm the corresponding iris feature collection strategy according to the user's wishes. The user can define different light spot shapes, light spot positions or lighting sequences, and use these light spot shapes, light spot positions or lighting sequences as passwords and enter them into the algorithm. Only by using the corresponding light spot shape, position and sequence to collect iris features can the user be identified.

[0145] As can be seen from the above, this embodiment can determine the iris feature collection strategy of the iris recognition device for the user, the iris feature collection strategy indicates the method of collecting iris features using spot imaging, and the iris feature collection strategy includes at least one spot imaging mode; through the iris recognition device, based on the spot imaging properties indicated by the spot imaging mode, collect the user's iris image with a spot projected on it to obtain a spot iris image in the spot imaging mode; perform feature extraction on the spot iris image in the spot imaging mode to obtain the spot iris feature in the spot imaging mode; based on the spot iris feature in the spot imaging mode, determine the spot iris feature of the user under the iris feature collection strategy; store the spot iris feature of the user under the iris feature collection strategy in a database associated with the iris recognition device.

[0146] This application utilizes spot imaging to encrypt iris images and stores the corresponding encrypted iris features in a database. When the spot iris features stored in the database are used for iris recognition, unlike the traditional method of directly collecting the iris features of the object to be identified, the object can only be recognized by iris recognition if its iris features are collected using the corresponding iris feature collection strategy. If the iris data in the database is leaked, the user's true iris features cannot be directly obtained based on the leaked iris data. This improves the security and robustness of the iris information and effectively prevents the theft of the user's iris information.

[0147] This embodiment will be described from the perspective of an object recognition device. The object recognition device may be integrated into a second electronic device, which may be a terminal or a server.

[0148] As shown in FIG13 , the specific process of the object recognition method is as follows:

[0149] 1301. Determine a target iris feature acquisition strategy of an iris recognition device for an object to be recognized. The target iris feature acquisition strategy indicates a method of acquiring iris features of the object to be recognized using light spot imaging. The target iris feature acquisition strategy includes at least one light spot imaging mode.

[0150] Specifically, in this embodiment, iris recognition requires the user's cooperation in capturing iris images from different light spots. Furthermore, it should be noted that during identity verification, the target iris feature capture strategy for the subject to be identified must be consistent with the iris feature capture strategy used when recording the subject's light spot iris features; otherwise, the subject will fail identity verification.

[0151] The iris recognition device can be used to collect iris features and perform identity recognition on the collected iris image. For example, the iris recognition device can be VR (Virtual Reality) glasses, door locks, safes, etc.

[0152] The target iris feature collection strategy can be set by the iris recognition device or customized by the subject to be recognized. Specifically, different devices can use different iris feature collection strategies. This supports device differentiation, ensuring that iris features collected by device A can only be used by device A and not by device B, thereby improving the security of iris recognition. Furthermore, different users can also customize their own target iris feature collection strategy, which will be used for every iris recognition attempt.

[0153] Specifically, the iris feature acquisition strategy includes at least one light spot imaging mode, which can be a mode that forms a light spot on the iris when imaging the iris. The light spot can be formed using a mask, which can be located in front of the iris recognition device's infrared light or camera lens. Optionally, in some embodiments, the mask shapes of different iris recognition devices can be different, so that the light spot shapes formed under the masks of different shapes also vary. This allows different iris feature acquisition strategies to be implemented on different iris recognition devices, achieving device differentiation in iris feature acquisition strategies and improving iris recognition security.

[0154] Different light spot imaging modes indicate different light spot imaging attributes, which may refer to the imaging attributes of the light spot on the iris. These imaging attributes may include the distribution position of the light spot on the iris, the light spot shape, the light spot illumination order, etc., which are not limited in this embodiment. The light spot illumination order specifically refers to the order in which the light spot imaging modes are executed in the iris feature acquisition strategy.

[0155] For example, a certain iris feature acquisition strategy may be to first apply a light spot below the iris, then apply a light spot above the iris, and finally apply a light spot to the right of the iris. The iris feature acquisition strategy includes three light spot imaging modes, which are: applying a light spot below the iris, applying a light spot above the iris, and applying a light spot to the right of the iris.

[0156] 1302. Using an iris recognition device, based on the light spot imaging properties indicated by the light spot imaging mode, collect an iris image of the object to be identified with a light spot projected thereon, to obtain a light spot iris image in the light spot imaging mode.

[0157] The light spot iris image in the light spot imaging mode includes the light spot formed in the light spot imaging mode. Specifically, the light spot iris image may be an infrared image.

[0158] Specifically, the iris feature acquisition module of an iris recognition device captures an infrared image. When infrared light is projected onto the user's iris, it forms a light spot. When the user's eyes turn at different angles, the light spot image will differ, and thus the calculated iris features will differ. Similarly, different lighting methods can also lead to differences in light spot image formation. Therefore, in some embodiments, different devices can use different lighting methods to achieve device differentiation in iris recognition.

[0159] In this embodiment, the user's eyeballs can rotate in different directions for different spot imaging modes, or different lighting methods can be used for different spot imaging modes. These different lighting methods may include different lighting angles or different spot shapes. This allows different spot imaging modes to form different spots, resulting in multiple frames of different spot imaging images, which can then be fused into a unique feature.

[0160] Optionally, in this embodiment, the step of “collecting, by the iris recognition device, an iris image of the object to be identified projected with a light spot based on the light spot imaging properties indicated by the light spot imaging mode, to obtain a light spot iris image in the light spot imaging mode” may include:

[0161] Through the iris recognition device, based on the spot imaging properties indicated by the spot imaging mode, the object to be identified is guided to rotate the eyeball to collect the iris image of the object to be identified with the spot projected, and obtain the spot iris image in the spot imaging mode.

[0162] For example, if the light spot imaging attribute indicated by the light spot imaging mode is that the light spot hits the right side of the iris, the subject to be identified can be guided to turn the eyeball to a corresponding angle so that the light spot hits the right side of the iris.

[0163] In a specific embodiment, the iris recognition device may include a display screen that can display information for guiding the user to rotate their eyeballs. It is understood that other methods can also be used to guide the user to rotate their eyeballs.

[0164] Optionally, in this embodiment, the iris recognition device includes an image acquisition module and at least one infrared light module; the step of "using the iris recognition device to acquire an iris image with a light spot projected by the object to be identified based on the spot imaging properties indicated by the spot imaging mode, so as to obtain a spot iris image in the spot imaging mode" may include: controlling the lighting mode of the infrared light module to switch to a target lighting mode based on the spot imaging properties indicated by the spot imaging mode; and using the image acquisition module to acquire an iris image with a light spot projected by the object to be identified based on the target lighting mode, so as to obtain a spot iris image in the spot imaging mode.

[0165] The image acquisition module may be a camera or other image capturing module. The infrared light module may include an infrared light angle and a corresponding light spot shape.

[0166] For example, if the light spot imaging attribute indicated by the light spot imaging mode is that the light spot is projected onto the right side of the iris, the lighting angle of the infrared light module may be controlled so that the formed light spot is projected onto the right side of the iris.

[0167] Optionally, in this embodiment, the step of "controlling the lighting mode of the infrared light module to switch to the target lighting mode based on the spot imaging properties indicated by the spot imaging mode" may include: controlling the on and off states of each infrared light module based on the spot imaging properties indicated by the spot imaging mode, so that the lighting mode of the infrared light module is switched to the target lighting mode; or, moving the position of the infrared light module based on the spot imaging properties indicated by the spot imaging mode, so that the lighting mode of the infrared light module is switched to the target lighting mode.

[0168] The infrared light on the iris recognition device can be turned on and off according to a preset method to achieve lighting at different angles. The infrared light module can also be moved on the iris recognition device according to a preset movement pattern to achieve lighting at different angles.

[0169] Optionally, in this embodiment, the spot imaging modes in the target iris feature acquisition strategy are arranged in a preset acquisition order;

[0170] The step of "collecting, by the iris recognition device, an iris image of the object to be identified with a light spot projected based on the spot imaging properties indicated by the spot imaging mode, to obtain a spot iris image under the spot imaging mode" may include: determining, from the target iris feature acquisition strategy, a target light spot imaging mode to be currently executed based on a preset acquisition sequence; collecting, by the iris recognition device, an iris image of the object to be identified with a light spot projected based on the spot imaging properties indicated by the target light spot imaging mode, to obtain a spot iris image under the target light spot imaging mode; after the spot iris image under the target light spot imaging mode passes the quality inspection, determining, from the target iris feature acquisition strategy, a new target light spot imaging mode to be currently executed based on the preset acquisition sequence; and returning to the step of collecting, by the iris recognition device, an iris image of the object to be identified with a light spot projected based on the spot imaging properties indicated by the target light spot imaging mode, to obtain a spot iris image under the target light spot imaging mode, until a spot iris image that passes the quality inspection under each spot imaging mode in the target iris feature acquisition strategy is obtained.

[0171] 1303. Perform feature extraction on the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode.

[0172] Optionally, in this embodiment, the step of “performing feature extraction on the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode” may include: performing iris segmentation processing on the spot iris image in the spot imaging mode to obtain the spot iris area in the spot imaging mode; performing normalization processing on the spot iris area to obtain the normalized spot iris area; performing feature extraction on the normalized spot iris area to obtain the spot iris features in the spot imaging mode.

[0173] Specifically, before performing iris segmentation processing, the original spot iris image in the spot imaging mode can be subjected to image preprocessing. The image preprocessing here can include preprocessing operations such as filtering, histogram equalization, and grayscale conversion. Image quality can be improved through image preprocessing.

[0174] Among them, after obtaining the spot iris area in the spot imaging mode, the light spot iris area can also be subjected to quality detection. The quality detection can include iris eyelash occlusion judgment, exposure judgment, eyelid occlusion judgment, etc. Through quality detection, higher quality pictures can be screened out.

[0175] Optionally, in this embodiment, the step of “performing iris segmentation processing on the spot iris image in the spot imaging mode to obtain the spot iris area in the spot imaging mode” may include: calculating gradient information of each pixel point in the spot iris image in the spot imaging mode; selecting at least one target pixel point from the pixel points of the spot iris image based on the gradient information; connecting the target pixel points to obtain a closed contour; and performing iris segmentation processing on the spot iris image based on the closed contour to obtain the spot iris area in the spot imaging mode.

[0176] In one embodiment, the step of "normalizing the light spot iris region to obtain a normalized light spot iris region" may involve converting different light spot iris regions to the same features and measurement scale, thereby facilitating subsequent feature extraction and matching. Specifically, there are various iris normalization methods, such as polar coordinate transformation and strip projection.

[0177] Optionally, in this embodiment, the step of “performing feature extraction on the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode” may include: performing filtering processing on the spot iris image in the spot imaging mode to obtain a response function of each pixel point in the spot iris image in the spot imaging mode; extracting frequency information and direction information corresponding to the response function of each pixel point; and performing mapping processing on the spot iris image in the spot imaging mode according to the frequency information and direction information to obtain the spot iris features in the spot imaging mode.

[0178] Among them, the step of "extracting features from the spot iris image in the spot imaging mode" may specifically include: performing iris segmentation processing on the spot iris image in the spot imaging mode, normalizing the spot iris area obtained by segmentation, and then extracting features from the normalized spot iris area to obtain the spot iris features in the spot imaging mode.

[0179] The light spot iris features include light spot iris frequency features and light spot iris direction features.

[0180] 1304. Determine the target light spot iris features of the object to be identified under the target iris feature acquisition strategy based on the light spot iris features in the light spot imaging mode.

[0181] Specifically, the spot iris features under each spot imaging mode can be fused to obtain the target spot iris features of the object to be identified under the target iris feature acquisition strategy. The fusion method here can include weighted averaging, etc., which is not limited in this embodiment.

[0182] Optionally, in this embodiment, different spot imaging modes indicate different spot imaging properties; the step of "determining the target spot iris features of the object to be identified under the target iris feature acquisition strategy based on the spot iris features under the spot imaging mode" may include: determining the weight information corresponding to each spot iris feature under each spot imaging mode; according to the weight information corresponding to each spot iris feature under each spot imaging mode, fusing the spot iris features under each spot imaging mode to obtain the target spot iris features of the object to be identified under the target iris feature acquisition strategy.

[0183] The weight information corresponding to each light spot iris feature in each light spot imaging mode may be determined according to the clarity of the light spot iris feature in each light spot imaging mode.

[0184] 1305. Match the target light spot iris feature with the iris data stored in the database associated with the iris recognition device to identify the object to be identified and determine the identity information of the object to be identified. The iris data includes at least one light spot iris feature.

[0185] The iris data includes at least one user's light spot iris feature under the corresponding iris feature collection strategy. One light spot iris feature belongs to one user, and one user may have multiple light spot iris features in the database.

[0186] Optionally, in this embodiment, the step of "matching the iris features of the target light spot with the iris data stored in the database associated with the iris recognition device to perform identity identification on the object to be identified and determine the identity information of the object to be identified" may include: calculating the matching degree between the iris features of the target light spot and the iris features of each light spot in the database; and based on the matching degree, performing identity identification on the object to be identified and determining the identity information of the object to be identified.

[0187] The object identity information corresponding to the light spot iris feature with the highest matching degree may be used as the identity information of the object to be identified.

[0188] In a specific scenario, as shown in FIG14 , the specific process of the object recognition method of the present application is shown, which is described as follows:

[0189] Step A: As shown in steps 1 to 5 in FIG14 , the user can adopt a customized target iris feature acquisition strategy to acquire irises and obtain multiple frames of iris images with light spots at specific angles.

[0190] Specifically, the target iris feature acquisition strategy can be to illuminate the lower part of the iris first, then illuminate the upper part of the iris, and finally illuminate the right side of the iris. During the specific acquisition process, a light spot can be applied below the iris to obtain an iris image with the light spot below the iris, and then the quality of the image is tested using the optimization algorithm. After the quality test passes, a light spot can be applied above the iris to obtain an iris image with the light spot above the iris, and then the quality of the image is tested using the optimization algorithm. After the quality test passes, a light spot can be applied to the right side of the iris to obtain an iris image with the light spot to the right of the iris, and then the quality of the image is tested using the optimization algorithm.

[0191] Among them, the preferred algorithm may include iris detection, iris segmentation and quality detection algorithms. The purpose of iris detection, iris segmentation and quality detection is to screen out pictures with better quality to facilitate feature extraction.

[0192] Step B: After the collection and optimization in step A, multiple frames of high-quality multi-angle iris images with light spots are obtained.

[0193] Step C: Iris feature extraction: Perform iris segmentation on the spot iris image to obtain the spot iris area, perform normalization on it, and then perform feature extraction on the normalized spot iris area to obtain the spot iris features under each spot imaging mode.

[0194] It should be noted that, in this embodiment, the light spot is directly retained and the iris features are calculated together.

[0195] Step D: Feature fusion to obtain a unique feature: The different light spot iris features are refined and classified, and recombined according to certain weights (such as weighted average, maximization, etc.), and finally a unique iris feature is obtained, that is, the target light spot iris feature under the target iris feature acquisition strategy.

[0196] Step E: Feature retrieval and matching:

[0197] The target spot iris features calculated in step D are generally stored in a local database or a server cloud database. When performing identity authentication or identification, it is necessary to retrieve and match the most similar iris features from the database to achieve identity authentication or identification.

[0198] Iris features in the database can be stored as feature vectors, with each iris feature vector corresponding to a unique identifier. When identity verification or identification is required, the feature vector of the iris to be verified is input. The database is then searched and matched to the feature vector that most closely resembles the iris to be verified, resulting in an identity verification or identification result.

[0199] Among them, iris matching algorithms may include Euclidean distance, cosine similarity, Mahalanobis distance, Hamming distance, etc. The specific matching method and similarity measurement method need to be selected according to the actual situation.

[0200] Taking the Euclidean distance as an example, let the iris feature vector to be verified (i.e., the target spot iris feature) be x, and a set of iris feature vectors in the database be y. Their Euclidean distance is d(x, y). Then the iris feature vector that is most similar to the iris to be verified and the database can be calculated as follows:

[0201] in, Represents the iris feature vector in the database that is most similar to the iris to be verified. database represents the database.

[0202] In a specific scenario, as shown in Figure 15, a schematic diagram of iris recognition interaction for a VR device is provided. The VR device can be equipped with a custom camera bracket equipped with an infrared light and an infrared camera to capture the user's iris image. The specific recognition process is as follows:

[0203] 1. Start Recognition: Recognition automatically begins when the user looks at the circle in front of them. Specifically, the user's gaze range can be determined through a gyroscope or eye tracking to confirm the user's intention to recognize the object. If the user's gaze range is not within the circle in front of them, recognition is not performed.

[0204] 2. During recognition: By changing the lighting position of the device or guiding the user to move their eyeballs, the camera collects multiple frames of iris images with light spots and processes and fuses the images into a unique feature.

[0205] 3. Successful identification: After successful matching and identification, it will turn into a check mark, and then enter the VR system or application internal interface.

[0206] Specifically, this embodiment requires the terminal to have the ability to run the optimal algorithm, graphics rendering capabilities, database storage capabilities, and sufficient performance to run the recognition logic. This embodiment allows for both networked and local recognition. If networked, the terminal device must have network connectivity and a backend recognition service must be established.

[0207] As can be seen from the above, this embodiment can determine the target iris feature collection strategy of the iris recognition device for the object to be identified, the target iris feature collection strategy indicates the way of collecting iris features of the object to be identified using spot imaging, and the target iris feature collection strategy includes at least one spot imaging mode; through the iris recognition device, based on the spot imaging properties indicated by the spot imaging mode, an iris image of the object to be identified with a spot projected on it is collected to obtain a spot iris image under the spot imaging mode; feature extraction is performed on the spot iris image under the spot imaging mode to obtain a spot iris feature under the spot imaging mode; based on the spot iris feature under the spot imaging mode, the target spot iris feature of the object to be identified under the target iris feature collection strategy is determined; the target spot iris feature is matched with the iris data stored in the database associated with the iris recognition device to identify the object to be identified and determine the identity information of the object to be identified, and the iris data includes at least one spot iris feature.

[0208] This application can use spot imaging to encrypt iris images and store the corresponding encrypted iris features in a database; for a certain object to be identified, only by using its corresponding iris feature collection strategy to collect the iris features of the object to be identified can the object to be identified pass iris recognition; if the iris data in the database is leaked, the user's real iris features cannot be directly obtained based on the leaked iris data, thereby improving the security and robustness of the iris information, and effectively preventing iris information fraud caused by the theft of iris equipment.

[0209] To better implement the above method, the embodiment of the present application also provides an iris feature acquisition and object recognition system. The iris feature acquisition and object recognition system includes an iris feature acquisition device 31 and an object recognition device 32. As shown in Figure 16, the iris feature acquisition device 31 may include a first strategy determination unit 1601, a first acquisition unit 1602, a first extraction unit 1603, a first feature determination unit 1604, and a storage unit 1605; as shown in Figure 17, the object recognition device 32 may include a second strategy determination unit 1701, a second acquisition unit 1702, a second extraction unit 1703, a second feature determination unit 1704, and a recognition unit 1705, as follows:

[0210] A. Iris feature acquisition device 31

[0211] (1) First strategy determination unit 1601.

[0212] The first strategy determination unit is used to determine the iris feature collection strategy of the iris recognition device for the user. The iris feature collection strategy indicates the way of collecting iris features by using light spot imaging. The iris feature collection strategy includes at least one light spot imaging mode.

[0213] (2) First acquisition unit 1602.

[0214] The first acquisition unit is configured to acquire an iris image of a user projected with a light spot based on the light spot imaging properties indicated by the light spot imaging mode through an iris recognition device, so as to obtain a light spot iris image in the light spot imaging mode.

[0215] Optionally, in some embodiments of the present application, the first acquisition unit can be specifically used to guide the user to rotate his eyeballs through an iris recognition device based on the spot imaging properties indicated by the spot imaging mode, so as to acquire an iris image of the user projected with a spot, and obtain a spot iris image under the spot imaging mode.

[0216] Optionally, in some embodiments of the present application, the iris recognition device includes an image acquisition module and at least one infrared light module.

[0217] The first acquisition unit may include a control subunit and an acquisition subunit, as follows:

[0218] The control subunit is used to control the lighting mode of the infrared light module to switch to the target lighting mode based on the light spot imaging properties indicated by the light spot imaging mode.

[0219] The acquisition subunit is used to acquire the iris image with the light spot projected by the user based on the target lighting mode through the image acquisition module to obtain the light spot iris image in the light spot imaging mode.

[0220] Optionally, in some embodiments of the present application, the control subunit can be specifically used to control the on and off states of each infrared light module based on the spot imaging properties indicated by the spot imaging mode, so that the lighting mode of the infrared light module is switched to the target lighting mode; or, based on the spot imaging properties indicated by the spot imaging mode, the position of the infrared light module is moved so that the lighting mode of the infrared light module is switched to the target lighting mode.

[0221] Optionally, in some embodiments of the present application, the spot imaging modes in the iris feature acquisition strategy are arranged in a preset acquisition order;

[0222] The first acquisition unit may include a first mode determination subunit, an image acquisition subunit, a second mode determination subunit, and a return subunit, as follows:

[0223] A first mode determination subunit is configured to determine a target spot imaging mode to be currently executed from an iris feature acquisition strategy based on a preset acquisition sequence;

[0224] The image acquisition subunit is used to acquire an iris image of a user projected with a light spot based on the light spot imaging properties indicated by the target light spot imaging mode through the iris recognition device, and obtain a light spot iris image in the target light spot imaging mode;

[0225] The second mode determination subunit is configured to determine the current new target light spot imaging mode to be executed from the iris feature acquisition strategy based on a preset acquisition order after the light spot iris image in the target light spot imaging mode passes the quality detection;

[0226] The return subunit is used to return to the step of collecting, by the iris recognition device, an iris image of the user projected with a light spot based on the light spot imaging properties indicated by the target light spot imaging mode, and obtaining a light spot iris image in the target light spot imaging mode, until a light spot iris image that passes the quality inspection in each light spot imaging mode in the iris feature collection strategy is obtained.

[0227] (3) First extraction unit 1603.

[0228] The first extraction unit is configured to perform feature extraction on the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode.

[0229] Optionally, in some embodiments of the present application, the first extraction unit may include a segmentation subunit, a normalization subunit, and an extraction subunit, as follows:

[0230] a segmentation subunit, configured to perform iris segmentation processing on the spot iris image in the spot imaging mode to obtain a spot iris area in the spot imaging mode;

[0231] A normalization subunit, configured to perform normalization processing on the light spot iris area to obtain a normalized light spot iris area;

[0232] The extraction subunit is used to extract features from the normalized light spot iris area to obtain light spot iris features in the light spot imaging mode.

[0233] Optionally, in some embodiments of the present application, the segmentation subunit can be specifically used to calculate the gradient information of each pixel point in the spot iris image under the spot imaging mode; based on the gradient information, select at least one target pixel point from the pixel points of the spot iris image; perform a connection operation on the target pixel points to obtain a closed contour; perform iris segmentation processing on the spot iris image according to the closed contour to obtain the spot iris area under the spot imaging mode.

[0234] Optionally, in some embodiments of the present application, the first extraction unit may include a filtering subunit, an information extraction subunit, and a mapping subunit, as follows:

[0235] A filtering subunit, configured to filter the spot iris image in the spot imaging mode to obtain a response function of each pixel in the spot iris image in the spot imaging mode;

[0236] An information extraction subunit, used to extract frequency information and direction information corresponding to the response function of each pixel;

[0237] The mapping subunit is used to perform mapping processing on the spot iris image in the spot imaging mode according to the frequency information and the direction information, so as to obtain the spot iris features in the spot imaging mode.

[0238] (4) First feature determination unit 1604.

[0239] The first feature determination unit is configured to determine the light spot iris feature of the user under the iris feature acquisition strategy based on the light spot iris feature in the light spot imaging mode.

[0240] Optionally, in some embodiments of the present application, different light spot imaging modes indicate different light spot imaging properties;

[0241] The first feature determination unit may include a first weight determination subunit and a first fusion subunit, as follows:

[0242] The first weight determination subunit is used to determine the weight information corresponding to each light spot iris feature in each light spot imaging mode;

[0243] The first fusion subunit is used to fuse the light spot iris features in each light spot imaging mode according to the weight information corresponding to each light spot iris feature in each light spot imaging mode, so as to obtain the light spot iris features of the user under the iris feature collection strategy for iris recognition.

[0244] (5) Storage unit 1605;

[0245] The storage unit is used to store the user's light spot iris features under the iris feature collection strategy in a database associated with the iris recognition device.

[0246] B. Object recognition device 32

[0247] (6) Second strategy determination unit 1701;

[0248] The second strategy determination unit is used to determine the target iris feature collection strategy of the iris recognition device for the object to be identified. The target iris feature collection strategy indicates the way of collecting iris features of the object to be identified using light spot imaging. The target iris feature collection strategy includes at least one light spot imaging mode.

[0249] (7) second acquisition unit 1702;

[0250] The second acquisition unit is used to acquire an iris image of the object to be identified with a light spot projected thereon through the iris recognition device based on the light spot imaging properties indicated by the light spot imaging mode, so as to obtain a light spot iris image in the light spot imaging mode.

[0251] (8) second extraction unit 1703;

[0252] The second extraction unit is used to extract features from the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode.

[0253] (9) second feature determination unit 1704;

[0254] The second feature determination unit is configured to determine the target light spot iris feature of the object to be identified under the target iris feature acquisition strategy based on the light spot iris feature in the light spot imaging mode.

[0255] Optionally, in some embodiments of the present application, different light spot imaging modes indicate different light spot imaging properties;

[0256] The second feature determination unit may include a second weight determination subunit and a second fusion subunit, as follows:

[0257] The second weight determination subunit is used to determine the weight information corresponding to each light spot iris feature in each light spot imaging mode;

[0258] The second fusion subunit is used to fuse the light spot iris features in each light spot imaging mode according to the weight information corresponding to each light spot iris feature in each light spot imaging mode, and obtain the target light spot iris feature of the object to be identified under the target iris feature acquisition strategy.

[0259] (10) Identification unit 1705;

[0260] The recognition unit is used to match the target light spot iris feature with the iris data stored in the database associated with the iris recognition device to identify the object to be identified and determine the identity information of the object to be identified. The iris data includes at least one light spot iris feature.

[0261] As can be seen from the above, in this embodiment, the first strategy determination unit 1601 can determine the iris feature collection strategy of the iris recognition device for the user, where the iris feature collection strategy indicates a method of collecting iris features using spot imaging, and the iris feature collection strategy includes at least one spot imaging mode. The first collection unit 1602 collects an iris image of the user projected with a spot through the iris recognition device based on the spot imaging properties indicated by the spot imaging mode to obtain a spot iris image in the spot imaging mode. The first extraction unit 1603 performs feature extraction on the spot iris image in the spot imaging mode to obtain a spot iris feature in the spot imaging mode. The first feature determination unit 1604 determines the spot iris feature of the user under the iris feature collection strategy based on the spot iris feature in the spot imaging mode. The storage unit 1605 stores the spot iris feature of the user under the iris feature collection strategy in a database associated with the iris recognition device.

[0262] Alternatively, the second strategy determination unit 1701 determines a target iris feature collection strategy of the iris recognition device for the object to be identified, where the target iris feature collection strategy indicates a method of collecting iris features of the object to be identified using spot imaging, and the target iris feature collection strategy includes at least one spot imaging mode. The second collection unit 1702 uses the iris recognition device to collect an iris image of the object to be identified, projected with a spot, based on the spot imaging properties indicated by the spot imaging mode, to obtain a spot iris image in the spot imaging mode. The second extraction unit 1703 performs feature extraction on the spot iris image in the spot imaging mode to obtain a spot iris feature in the spot imaging mode. The second feature determination unit 1704 determines a target spot iris feature of the object to be identified under the target iris feature collection strategy based on the spot iris feature in the spot imaging mode. The identification unit 1705 matches the target spot iris feature with iris data stored in a database associated with the iris recognition device to identify the object to be identified and determine identity information of the object to be identified, where the iris data includes at least one spot iris feature.

[0263] The present application can utilize spot imaging to encrypt iris images and store the corresponding encrypted iris features in a database. For a certain object to be identified, only by using its corresponding iris feature collection strategy to collect the iris features of the object to be identified can the object to be identified pass iris recognition. If the iris data in the database is leaked, the user's true iris features cannot be directly obtained based on the leaked iris data, thereby improving the security and robustness of the iris information and effectively preventing the iris recognition device from being stolen and deceived by iris information.

[0264] The present application also provides an electronic device, as shown in FIG18 , which shows a schematic diagram of the structure of the electronic device involved in the present application embodiment. The electronic device may be a terminal or a server, etc. Specifically:

[0265] The electronic device may include components such as a processor 1801 with one or more processing cores, a memory 1802 with one or more computer-readable storage media, a power supply 1803, and an input unit 1804. Those skilled in the art will appreciate that the electronic device structure shown in FIG18 does not limit the electronic device and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0266] Processor 1801 is the control center of the electronic device, connecting all parts of the electronic device using various interfaces and circuits. It executes the various functions of the electronic device and processes data by running or executing software programs and / or modules stored in memory 1802 and accessing data stored in memory 1802. Optionally, processor 1801 may include one or more processing cores; preferably, processor 1801 may integrate an application processor and a modem processor, where the application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 1801.

[0267] The memory 1802 can be used to store software programs and modules. The processor 1801 executes various functional applications and data processing by running the software programs and modules stored in the memory 1802. The memory 1802 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 1802 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 1802 may also include a memory controller to provide the processor 1801 with access to the memory 1802.

[0268] The electronic device also includes a power supply 1803 for supplying power to various components. Preferably, the power supply 1803 can be logically connected to the processor 1801 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 1803 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0269] The electronic device may further include an input unit 1804, which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0270] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 1801 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 1802 according to the following instructions, and the processor 1801 will run the application programs stored in the memory 1802 to implement various functions as follows:

[0271] Determining an iris feature collection strategy for the user by the iris recognition device, the iris feature collection strategy indicating a method for collecting iris features using spot imaging, the iris feature collection strategy including at least one spot imaging mode; collecting, by the iris recognition device, an iris image of the user projected with a spot based on the spot imaging properties indicated by the spot imaging mode, to obtain a spot iris image in the spot imaging mode; performing feature extraction on the spot iris image in the spot imaging mode to obtain spot iris features in the spot imaging mode; determining the spot iris features of the user under the iris feature collection strategy based on the spot iris features in the spot imaging mode; and storing the spot iris features of the user under the iris feature collection strategy in a database associated with the iris recognition device;

[0272] Alternatively, a target iris feature collection strategy of the iris recognition device for the object to be identified is determined, the target iris feature collection strategy indicates a method of collecting iris features of the object to be identified using spot imaging, and the target iris feature collection strategy includes at least one spot imaging mode; through the iris recognition device, based on the spot imaging properties indicated by the spot imaging mode, an iris image of the object to be identified with a light spot projected thereon is collected to obtain a spot iris image under the spot imaging mode; feature extraction is performed on the spot iris image under the spot imaging mode to obtain a spot iris feature under the spot imaging mode; based on the spot iris feature under the spot imaging mode, the target spot iris feature of the object to be identified under the target iris feature collection strategy is determined; the target spot iris feature is matched with iris data stored in a database associated with the iris recognition device to perform identity identification on the object to be identified and determine the identity information of the object to be identified, wherein the iris data includes at least one spot iris feature.

[0273] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0274] As can be seen from the above, this embodiment can determine the iris feature collection strategy of the iris recognition device for the user. The iris feature collection strategy indicates a method for collecting iris features using spot imaging, and the iris feature collection strategy includes at least one spot imaging mode. The iris recognition device collects an iris image of the user projected with a spot based on the spot imaging properties indicated by the spot imaging mode to obtain a spot iris image in the spot imaging mode. Feature extraction is performed on the spot iris image in the spot imaging mode to obtain spot iris features in the spot imaging mode. Based on the spot iris features in the spot imaging mode, the spot iris features of the user under the iris feature collection strategy are determined. The spot iris features of the user under the iris feature collection strategy are stored in a database associated with the iris recognition device.

[0275] Alternatively, a target iris feature collection strategy of the iris recognition device for the object to be identified is determined, the target iris feature collection strategy indicates a method of collecting iris features of the object to be identified using spot imaging, and the target iris feature collection strategy includes at least one spot imaging mode; through the iris recognition device, based on the spot imaging properties indicated by the spot imaging mode, an iris image of the object to be identified with a light spot projected thereon is collected to obtain a spot iris image under the spot imaging mode; feature extraction is performed on the spot iris image under the spot imaging mode to obtain a spot iris feature under the spot imaging mode; based on the spot iris feature under the spot imaging mode, the target spot iris feature of the object to be identified under the target iris feature collection strategy is determined; the target spot iris feature is matched with iris data stored in a database associated with the iris recognition device to perform identity identification on the object to be identified and determine the identity information of the object to be identified, wherein the iris data includes at least one spot iris feature.

[0276] The present application can utilize spot imaging to encrypt iris images and store the corresponding encrypted iris features in a database. For a certain object to be identified, only by using its corresponding iris feature collection strategy to collect the iris features of the object to be identified can the object to be identified pass iris recognition. If the iris data in the database is leaked, the user's true iris features cannot be directly obtained based on the leaked iris data, thereby improving the security and robustness of the iris information and effectively preventing the iris recognition device from being stolen and deceived by iris information.

[0277] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0278] To this end, an embodiment of the present application provides a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute the steps of any of the iris feature acquisition methods and object recognition methods provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0279] Determining an iris feature collection strategy for the user by the iris recognition device, the iris feature collection strategy indicating a method for collecting iris features using spot imaging, the iris feature collection strategy including at least one spot imaging mode; collecting, by the iris recognition device, an iris image of the user projected with a spot based on the spot imaging properties indicated by the spot imaging mode, to obtain a spot iris image in the spot imaging mode; performing feature extraction on the spot iris image in the spot imaging mode to obtain spot iris features in the spot imaging mode; determining the spot iris features of the user under the iris feature collection strategy based on the spot iris features in the spot imaging mode; and storing the spot iris features of the user under the iris feature collection strategy in a database associated with the iris recognition device;

[0280] Alternatively, a target iris feature collection strategy of the iris recognition device for the object to be identified is determined, the target iris feature collection strategy indicates a method of collecting iris features of the object to be identified using spot imaging, and the target iris feature collection strategy includes at least one spot imaging mode; through the iris recognition device, based on the spot imaging properties indicated by the spot imaging mode, an iris image of the object to be identified with a light spot projected thereon is collected to obtain a spot iris image under the spot imaging mode; feature extraction is performed on the spot iris image under the spot imaging mode to obtain a spot iris feature under the spot imaging mode; based on the spot iris feature under the spot imaging mode, the target spot iris feature of the object to be identified under the target iris feature collection strategy is determined; the target spot iris feature is matched with iris data stored in a database associated with the iris recognition device to perform identity identification on the object to be identified and determine the identity information of the object to be identified, wherein the iris data includes at least one spot iris feature.

[0281] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0282] The computer-readable storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0283] Since the instructions stored in the computer-readable storage medium can execute the steps of any one of the iris feature acquisition methods and object recognition methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the iris feature acquisition methods and object recognition methods provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0284] According to one aspect of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in various optional implementations of the aforementioned iris feature acquisition and object recognition.

[0285] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0286] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for collecting iris features, performed by an electronic device, comprising: Determine an iris feature collection strategy for the user by the iris recognition device, wherein the iris feature collection strategy indicates a method of collecting iris features by using light spot imaging, and the iris feature collection strategy includes at least one light spot imaging mode; By means of the iris recognition device, based on the light spot imaging properties indicated by the light spot imaging mode, an iris image of the user projected with a light spot is collected to obtain a light spot iris image in the light spot imaging mode; Extracting features of the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode; Determining the light spot iris feature of the user under the iris feature acquisition strategy based on the light spot iris feature in the light spot imaging mode; and The light spot iris features of the user under the iris feature collection strategy are stored in a database associated with the iris recognition device.

2. The method according to claim 1, wherein the different light spot imaging modes indicate different light spot imaging properties; The determining, based on the light spot iris feature in the light spot imaging mode, the light spot iris feature of the user under the iris feature acquisition strategy includes: Determine the weight information corresponding to each light spot iris feature under each light spot imaging mode; According to the weight information corresponding to the light spot iris features in each light spot imaging mode, the light spot iris features in each light spot imaging mode are fused to obtain the light spot iris features of the user under the iris feature collection strategy for iris recognition.

3. The method according to claim 1 or 2, wherein the step of collecting, by the iris recognition device, an iris image of the user projected with a light spot based on the light spot imaging attribute indicated by the light spot imaging mode to obtain a light spot iris image in the light spot imaging mode comprises: The iris recognition device guides the user to rotate his eyeballs based on the light spot imaging properties indicated by the light spot imaging mode, so as to capture an iris image of the user projected with a light spot, and obtain a light spot iris image in the light spot imaging mode.

4. The method according to any one of claims 1 to 3, wherein the iris recognition device comprises an image acquisition module and at least one infrared light module; The step of collecting, by the iris recognition device, an iris image of the user projected with a light spot based on the light spot imaging attribute indicated by the light spot imaging mode to obtain a light spot iris image in the light spot imaging mode includes: Based on the spot imaging properties indicated by the spot imaging mode, controlling the lighting mode of the infrared light module to switch to a target lighting mode; The image acquisition module is used to acquire the iris image of the user projected with a light spot based on the target lighting mode, so as to obtain the light spot iris image in the light spot imaging mode.

5. The method according to claim 4, wherein the controlling the lighting mode of the infrared light module to switch to the target lighting mode based on the light spot imaging property indicated by the light spot imaging mode comprises: Based on the light spot imaging property indicated by the light spot imaging mode, the on and off states of each infrared light module are controlled so that the lighting mode of the infrared light module is switched to the target lighting mode.

6. The method according to claim 4, wherein the controlling the lighting mode of the infrared light module to switch to the target lighting mode based on the light spot imaging property indicated by the light spot imaging mode comprises: Based on the light spot imaging property indicated by the light spot imaging mode, the position of the infrared light module is moved so that the lighting mode of the infrared light module is switched to the target lighting mode.

7. The method according to any one of claims 1 to 6, wherein the spot imaging modes in the iris feature acquisition strategy are arranged in a preset acquisition order; The step of collecting, by the iris recognition device, an iris image of the user projected with a light spot based on the light spot imaging attribute indicated by the light spot imaging mode to obtain a light spot iris image in the light spot imaging mode includes: Based on the preset acquisition sequence, determining the target spot imaging mode to be currently executed from the iris feature acquisition strategy; By means of the iris recognition device, based on the light spot imaging properties indicated by the target light spot imaging mode, an iris image of the user projected with a light spot is collected to obtain a light spot iris image in the target light spot imaging mode; After the spot iris image in the target spot imaging mode passes the quality detection, based on the preset acquisition sequence, determining the current new target spot imaging mode to be executed from the iris feature acquisition strategy; Return to executing the step of collecting, by the iris recognition device, an iris image of the user projected with a light spot based on the light spot imaging attribute indicated by the target light spot imaging mode, and obtaining the light spot iris image under the target light spot imaging mode, until a light spot iris image that passes the quality inspection under each light spot imaging mode in the iris feature acquisition strategy is obtained.

8. The method according to any one of claims 1 to 7, wherein extracting features from the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode comprises: Performing iris segmentation processing on the spot iris image in the spot imaging mode to obtain a spot iris area in the spot imaging mode; Performing normalization processing on the light spot iris area to obtain a normalized light spot iris area; Feature extraction is performed on the normalized light spot iris area to obtain the light spot iris feature in the light spot imaging mode.

9. The method according to claim 8, wherein the step of performing iris segmentation processing on the spot iris image in the spot imaging mode to obtain the spot iris area in the spot imaging mode comprises: Calculate the gradient information of each pixel in the spot iris image under the spot imaging mode; Selecting at least one target pixel point from the pixel points of the light spot iris image according to the gradient information; Performing a connection operation on the target pixel points to obtain a closed contour; The light spot iris image is subjected to iris segmentation processing according to the closed contour to obtain a light spot iris area in the light spot imaging mode.

10. The method according to any one of claims 1 to 9, wherein extracting features from the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode comprises: Performing filtering processing on the spot iris image in the spot imaging mode to obtain a response function of each pixel point in the spot iris image in the spot imaging mode; Extracting frequency information and direction information corresponding to the response function of each pixel point; The light spot iris image in the light spot imaging mode is mapped according to the frequency information and the direction information to obtain the light spot iris feature in the light spot imaging mode.

11. An object recognition method, performed by an electronic device, comprising: Determine a target iris feature acquisition strategy of the iris recognition device for the object to be recognized, wherein the target iris feature acquisition strategy indicates a method of acquiring iris features of the object to be recognized by using light spot imaging, and the target iris feature acquisition strategy includes at least one light spot imaging mode; By means of the iris recognition device, based on the light spot imaging properties indicated by the light spot imaging mode, an iris image of the object to be identified with a light spot projected thereon is collected to obtain a light spot iris image in the light spot imaging mode; Extracting features of the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode; Determining the target light spot iris feature of the object to be identified under the target iris feature acquisition strategy based on the light spot iris feature in the light spot imaging mode; and The target light spot iris feature is matched with iris data stored in a database associated with the iris recognition device to identify the object to be identified and determine the identity information of the object to be identified, wherein the iris data includes at least one light spot iris feature.

12. The method according to claim 11, wherein the different light spot imaging modes indicate different light spot imaging properties; The step of determining the target iris of the object to be identified based on the light spot iris feature in the light spot imaging mode The target spot iris features under the feature acquisition strategy include: Determine the weight information corresponding to each light spot iris feature under each light spot imaging mode; According to the weight information corresponding to the spot iris features in each spot imaging mode, the spot iris features in each spot imaging mode are fused to obtain the target spot iris features of the object to be identified under the target iris feature acquisition strategy.

13. An iris feature acquisition device, comprising: A first strategy determination unit, configured to determine an iris feature collection strategy for an iris recognition device for a user, wherein the iris feature collection strategy indicates a method of collecting iris features using light spot imaging, and the iris feature collection strategy includes at least one light spot imaging mode; A first acquisition unit is configured to acquire, through the iris recognition device, an iris image of the user projected with a light spot based on the light spot imaging attribute indicated by the light spot imaging mode, so as to obtain a light spot iris image in the light spot imaging mode; A first extraction unit is used to extract features of the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode; A first feature determination unit, configured to determine the light spot iris feature of the user under the iris feature acquisition strategy based on the light spot iris feature in the light spot imaging mode; The storage unit is used to store the light spot iris features of the user under the iris feature collection strategy in a database associated with the iris recognition device.

14. An object recognition device, comprising: a second strategy determination unit, configured to determine a target iris feature acquisition strategy of the iris recognition device for the object to be recognized, wherein the target iris feature acquisition strategy indicates a method of acquiring iris features of the object to be recognized by using light spot imaging, and the target iris feature acquisition strategy includes at least one light spot imaging mode; A second acquisition unit is used to acquire, through the iris recognition device, an iris image of the object to be identified projected with a light spot based on the light spot imaging attribute indicated by the light spot imaging mode, so as to obtain a light spot iris image in the light spot imaging mode; A second extraction unit is used to extract features of the spot iris image in the spot imaging mode to obtain the spot iris features in the spot imaging mode; A second feature determination unit, configured to determine the target light spot iris feature of the object to be identified under the target iris feature acquisition strategy based on the light spot iris feature in the light spot imaging mode; The recognition unit is used to match the target light spot iris feature with the iris data stored in the database associated with the iris recognition device to identify the object to be identified and determine the identity information of the object to be identified, wherein the iris data includes at least one light spot iris feature.

15. An electronic device comprising a memory and a processor; the memory stores an application, and the processor is used to run the application in the memory to perform the operations in the iris feature acquisition method described in any one of claims 1 to 10 or the object recognition method described in any one of claims 11 to 12.

16. A computer-readable storage medium storing a plurality of instructions, wherein the instructions are suitable for being loaded by a processor to execute the steps in the iris feature acquisition method according to any one of claims 1 to 10 or the object recognition method according to any one of claims 11 to 12.

17. A computer program product, comprising a computer program or an instruction, which, when executed by a processor, implements the steps in the iris feature acquisition method according to any one of claims 1 to 10 or the object recognition method according to any one of claims 11 to 12.

Images