Iris obstruction analysis method and apparatus, and computer device

Abstract

The present application relates to an iris obstruction analysis method and apparatus, and a computer device. The method comprises: performing key point prediction on an eye image of a target object to obtain a plurality of iris boundary key points and a plurality of eyelid boundary key points (S202); on the basis of an iris contour shape condition, performing contour fitting on the iris boundary key points to obtain a predicted iris area (S204); determining an eyelid boundary formed by the eyelid boundary key points (S206); and on the basis of a relative position relationship between the predicted iris area and an area formed by the eyelid boundary, performing iris obstruction analysis to obtain an analysis result (S208). By using the present method, the iris obstruction analysis result can be quickly and accurately obtained.

Description

Iris occlusion analysis method, device and computer equipment

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on July 28, 2023, with application number 202310949785.6 and application name “Iris Occlusion Analysis Method, Device, Computer Equipment and Storage Medium”, all contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of computer technology, and in particular to an iris occlusion analysis method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0004] The iris is the annular area located between the black pupil and the white sclera on the surface of the human eye. Each iris contains unique characteristics. The characteristic information of the iris in the eye can be used to achieve the purpose of identity authentication, which is suitable for identity authentication technology in information security.

[0005] However, in actual applications, iris recognition can be affected by varying degrees of eyelid occlusion due to differences in eye size. This requires determining the degree of iris obstruction to ensure effective iris recognition. Existing algorithms for determining iris occlusion primarily perform semantic segmentation of the eyelid and iris, then determine iris occlusion. However, due to interference from factors like eyelid shadows and eyelashes, semantic segmentation accuracy is low and processing speed is slow.

[0006] Summary of the Invention

[0007] Embodiments of the present application provide an iris occlusion analysis method, apparatus, computer device, computer-readable storage medium, and computer program product.

[0008] An iris occlusion analysis method, executed by a computer device, comprising:

[0009] Perform key point prediction on the target object's eye image to obtain multiple iris boundary key points and multiple eyelid boundary key points;

[0010] According to the iris contour shape condition, contour fitting is performed on each of the iris boundary key points to obtain a predicted iris area; and the eyelid boundary formed by each of the eyelid boundary key points is determined; and

[0011] Based on the relative positional relationship between the predicted iris area and the area formed by the eyelid boundary, an iris occlusion analysis is performed on the target object to obtain an iris occlusion analysis result.

[0012] An iris occlusion analysis device. The device comprises:

[0013] A key point prediction module is used to predict key points of the eye image of the target object to obtain multiple iris boundary key points and multiple eyelid boundary key points;

[0014] A contour fitting module is used to perform contour fitting on each of the iris boundary key points according to the iris contour shape conditions to obtain a predicted iris area;

[0015] a boundary determination module, configured to determine the eyelid boundary formed by each of the eyelid boundary key points; and

[0016] The occlusion analysis module is used to perform iris occlusion analysis on the target object based on the relative position relationship between the predicted iris area and the area formed by the eyelid boundary to obtain an iris occlusion analysis result.

[0017] A computer device includes a memory and one or more processors, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the one or more processors perform the steps of the above-mentioned iris occlusion analysis method.

[0018] One or more non-volatile computer-readable storage media storing computer-readable instructions, wherein computer-readable instructions are stored thereon, and when the computer-readable instructions are executed by one or more processors, the one or more processors are caused to perform the steps of the above-mentioned iris occlusion analysis method.

[0019] A computer program product or computer program includes computer-readable instructions stored in a computer-readable storage medium. One or more processors of a computer device read the computer-readable instructions from the computer-readable storage medium. The one or more processors execute the computer-readable instructions, causing the computer device to perform the steps of the above-mentioned iris occlusion analysis method.

[0020] 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

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] FIG1 is a diagram illustrating an application environment of an iris occlusion analysis method according to an embodiment;

[0023] FIG2 is a schematic flow chart of an iris occlusion analysis method according to an embodiment;

[0024] FIG3 is a schematic diagram of various key points in an iris occlusion analysis method according to an embodiment;

[0025] FIG4 is a schematic diagram of a boundary determined based on key points in one embodiment;

[0026] FIG5 is a schematic diagram of an embodiment in which the iris is not obscured by the eyelid;

[0027] FIG6 is a schematic diagram showing a portion of the iris being obscured by the eyelid in one embodiment;

[0028] FIG7 is a schematic diagram of the structure of a key point prediction model in one embodiment;

[0029] FIG8 is a schematic diagram of the regression process of a key point prediction model in one embodiment;

[0030] FIG9 is a schematic flow chart of an iris occlusion analysis method according to an embodiment;

[0031] FIG10 is a structural block diagram of an iris occlusion analysis device according to one embodiment;

[0032] FIG11 is a diagram showing the internal structure of a computer device according to one embodiment;

[0033] FIG12 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0035] The solution provided in the embodiments of the present application involves technologies such as artificial intelligence computer vision, which locates the key points of the eyes of the target object in the eye image, determines the predicted iris area and eyelid boundary in the eye image, and performs iris occlusion analysis on the target object to obtain the iris occlusion analysis results. Based on the iris occlusion analysis results, it is determined whether iris recognition can be performed on the target object, or whether the target object needs to be reminded to open their eyes and re-capture and analyze the image.

[0036] The iris occlusion analysis method provided in the embodiment of the present application can be applied in the application environment shown in Figure 1. In this case, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the eye image of the target object to the server 104. The server 104 performs key point prediction on the eye image of the target object to obtain multiple iris boundary key points and multiple eyelid boundary key points. According to the iris contour shape conditions, the server 104 performs contour fitting on each iris boundary key point to obtain a predicted iris area, determines the eyelid boundary formed by each eyelid boundary key point, and performs iris occlusion analysis on the target object based on the relative positional relationship between the predicted iris area and the area formed by the eyelid boundary to obtain an iris occlusion analysis result, and sends the iris occlusion analysis result to the terminal 102. In other embodiments, the iris occlusion analysis method can also be performed by the terminal 102 alone, or by the server 104 alone.

[0037] Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented as an independent server or a server cluster consisting of multiple servers. The client of the target application can be installed in the terminal 102. The target application can be any application that can provide image processing functions. Typically, the application is an image processing application that provides the function of analyzing the content of the input image. Of course, in addition to image processing applications, other types of applications can also provide image processing services, such as news applications, shopping applications, social applications, interactive entertainment applications, browser applications, content sharing applications, virtual reality (VR) applications, augmented reality (AR) applications, etc., which are not limited in the embodiments of the present application. In addition, different applications may process different types of images and have different corresponding functions, which can be pre-configured according to actual needs and are not limited in this embodiment of the present application. Optionally, the client running the above application in the terminal device 102 can implement iris occlusion analysis of the eye image.

[0038] In one example, the key point prediction process is performed in a key point prediction model, and the key point prediction model runs on a computer device. That is, in the method provided herein, the execution entity of each step can be a computer device, which can be any electronic device with data storage and processing capabilities. For example, the computer device can be the server 104 in Figure 1, the terminal device 102 in Figure 1, or another device other than the terminal 102 and the server 104.

[0039] With the continuous improvement of social information security awareness, iris recognition has a wider application prospect in practical application scenarios such as payment and identity authentication. In one embodiment, taking the terminal as a VR device as an example, the target object wears the VR device, and the VR device can collect the target object's eye image and upload the eye image to the server. The server predicts the key points of the target object's eye image to obtain multiple iris boundary key points and multiple eyelid boundary key points. According to the iris contour shape conditions, the server performs contour fitting on each iris boundary key point to obtain a predicted iris area, determines the eyelid boundary formed by each eyelid boundary key point, and performs iris occlusion analysis on the target object based on the relative position relationship between the predicted iris area and the area formed by the eyelid boundary to obtain an iris occlusion analysis result. When the iris occlusion analysis result shows that the occlusion ratio exceeds the maximum tolerable iris occlusion ratio threshold, the iris occlusion analysis result is sent to the VR device, so that the VR device sends a prompt message to the target object to open his eyes so that the eye image can be re-collected for analysis. When the iris occlusion analysis result shows that the occlusion ratio is less than or equal to the maximum tolerable iris occlusion ratio threshold, the server extracts iris features in the predicted iris area, performs iris recognition processing on the target object based on the iris features, and obtains an iris recognition result.

[0040] In another embodiment, the iris occlusion analysis method can also be applied to traffic scenarios, educational scenarios, and the like. For example, while a driver is driving in a traffic scenario, the iris occlusion analysis method can be used to analyze the driver's iris occlusion. The results of the iris occlusion analysis can be used to determine whether the driver is driving fatigued. If this is detected, a prompt message can be sent to the driver in a timely manner. For another example, during a class in an educational scenario, the iris occlusion analysis method can be used to analyze the student's iris occlusion. The results of the iris occlusion analysis can be used to determine whether the student is dozing off in class. If this is detected, a prompt message can be sent to the student in a timely manner.

[0041] In some embodiments, a VR device integrates an algorithm for performing iris occlusion analysis and has the computing power to perform iris occlusion analysis. After acquiring an eye image of a target subject, the VR device performs key point prediction on the target subject's eye image to obtain multiple iris boundary key points and multiple eyelid boundary key points. Based on iris contour shape conditions, the device performs contour fitting on each iris boundary key point to obtain a predicted iris region. The device then determines the eyelid boundary formed by each eyelid boundary key point. Based on the relative positional relationship between the predicted iris region and the region formed by the eyelid boundary, the device performs iris occlusion analysis on the target subject to obtain an iris occlusion analysis result. If the iris occlusion analysis result indicates that the occlusion ratio exceeds a maximum tolerable iris occlusion ratio threshold, the device sends a prompt message to the target subject to open their eyes so that the eye image can be recaptured for analysis. If the iris occlusion analysis result indicates that the occlusion ratio is less than or equal to the maximum tolerable iris occlusion ratio threshold, the server extracts iris features from the predicted iris region and, based on the iris features, performs iris recognition processing on the target subject to obtain an iris recognition result.

[0042] In one embodiment, as shown in FIG2 , an iris occlusion analysis method is provided. This method is described using a computer device as an example. The computer device may be the server shown in FIG1 , or a terminal with data processing capabilities, or may be implemented through interaction between the server and the terminal. The method includes the following steps:

[0043] Step 202 : performing key point prediction on the eye image of the target object to obtain a plurality of iris boundary key points and a plurality of eyelid boundary key points.

[0044] The target object is an object that requires iris occlusion analysis, such as an object whose learning or driving status is identified by the degree of iris occlusion, or an object whose identity is verified by iris recognition. An eye image refers to an image whose image content is the eye of the target object. The eye image can be a pre-stored image, or an image captured in real time by an image acquisition device for the target object. The eye image of the target object can be a single eye image directly acquired or captured, or an eye image captured from a certain video frame in a video or animated image. For example, if a computer device has an image acquisition function, the computer device can acquire an image of the target object to obtain an eye image. The computer device can also capture a video of the target object and extract the eye image of the target object from a sequence of video frames.

[0045] Keypoint prediction is the process of predicting the locations of keypoints within a specific image component. For example, if the specific components of an eye image include the iris and eyelid, keypoint prediction for the eye image involves predicting the keypoints at the iris and eyelid boundaries.

[0046] In some embodiments, key point prediction can be achieved by executing a key point prediction algorithm. For example, key point prediction can be achieved using a deep network. The specific prediction process can be to extract features using CNN (Convolutional Neural Networks), and then use a fully connected layer to directly regress the coordinates of the key points. For example, the key point prediction algorithm can be implemented by DeepPose human pose estimation network (Human Pose Estimation via Deep Neural Networks), or by MTCNN network (Multi-task Cascaded Convolutional Networks), or by a heat map prediction method. The principle of heat map prediction is to extract the point in the channel where the pixel response is greater than the threshold and the response is the largest. The coordinates of the point are the coordinates of the key point. In one embodiment, taking the regression-based pose estimation algorithm DeepPose as an example, the DeepPose algorithm can be used to predict key points of the eye image of the target object to obtain multiple iris boundary key points and multiple eyelid boundary key points.

[0047] Furthermore, the prediction process for iris boundary keypoints and eyelid boundary keypoints can be implemented using a neural network model that implements a keypoint prediction algorithm. The neural network model can be trained using sample eye images with keypoint annotations. The types of keypoints predicted by the keypoint prediction algorithm can be determined based on the categories corresponding to the samples with keypoint annotations.

[0048] Iris boundary keypoints are keypoints used to represent the boundaries of the iris region in the eye. The iris is the annular area between the black pupil and the white sclera on the surface of the human eye. Specifically, iris boundary keypoints include keypoints for the iris outer boundary and keypoints for the pupil boundary. The iris outer boundary is the boundary between the iris and the white sclera, while the pupil boundary is the boundary between the iris and the black pupil.

[0049] Eyelid boundary keypoints are keypoints used to represent the eyelid boundary. The eyelids include the upper eyelid and the lower eyelid, and the eyelid boundary keypoints can include upper eyelid boundary keypoints and lower eyelid boundary keypoints. The number of upper eyelid boundary keypoints and lower eyelid boundary keypoints can be the same or different.

[0050] During keypoint prediction for an eye image, multiple iris boundary keypoints and multiple eyelid boundary keypoints need to be predicted. Specifically, the number of iris boundary keypoints and multiple eyelid boundary keypoints can be pre-set. For example, the number of iris boundary keypoints can be set to X, and the number of eyelid boundary keypoints can be set to Y.

[0051] In a specific application, since the pupil itself is a circular area, and in the iris recognition scenario, the pupil will be guided to become smaller through environmental adjustments, and the imaging distortion is not large at small angles, the number of key points of the pupil boundary can be more than 3, for example, the number of key points of the pupil boundary is set to 4. However, the iris area is larger than the pupil and is more easily occluded by the eyelids. Therefore, the number of key points of the iris outer boundary can be greater than the number of key points of the pupil boundary. For example, the number of key points of the iris outer boundary can be set to 8. Since the upper part of the eyelid boundary has a larger curvature than the lower part, the number of key points of the upper eyelid boundary can be greater than the number of key points of the lower eyelid boundary.

[0052] In an application embodiment, as shown in Figure 3, the number of pupil boundary key points is 4, the number of iris outer boundary key points is 8, and the number of eyelid boundary key points is 6, where the eyelid boundary key points include 2 corner of the eye key points, 1 lower eyelid boundary key point and 3 upper eyelid boundary key points.

[0053] Step 204: According to the iris contour shape condition, contour fitting is performed on each iris boundary key point to obtain a predicted iris area.

[0054] The iris outline shape condition is used to define the boundary contour of the fitted iris region. The iris outline shape condition may include an iris outer boundary shape condition and an iris inner boundary shape condition. The iris inner boundary shape condition is the pupil boundary shape condition. The iris outer boundary shape condition and the pupil boundary shape condition may be defined as the same boundary shape or different boundary shapes.

[0055] Contour fitting is the process of fitting an iris contour line that meets the iris's shape requirements based on the distribution of key points on the iris's boundary. Different contour fitting algorithms can be used to adapt to different iris shape requirements. For example, a circular contour line can be obtained using a circular fitting algorithm, while an ellipse contour line can be obtained using an ellipse fitting algorithm.

[0056] The iris contour shape condition can be determined based on the actual eye image acquisition angle and acquisition scene. For eye images acquired at a normal viewing angle, the iris contour shape condition can be set to a circular contour. For eye images acquired at multiple angles, the iris outer boundary shape condition in the iris contour shape condition can be set to an elliptical contour, and the pupil boundary shape condition in the iris contour shape condition can be set to a circular contour. It should be noted that the predicted iris area is the theoretically complete iris area for the iris. In the eye image, the predicted iris area includes the iris area displayed in the eye image and the iris area blocked by the eyelid.

[0057] In one embodiment, after acquiring an eye image of a target object, a computer device performs key point prediction on the eye image based on a key point prediction algorithm, predicts multiple iris boundary key points, and marks or records the coordinate positions of the multiple iris boundary key points in the eye image. For the multiple iris boundary key points, the computer device first obtains a preset iris contour shape condition, performs contour fitting on each iris boundary key point according to the iris contour shape condition, and determines a predicted iris area based on the fitting result.

[0058] Step 206: Determine the eyelid boundary formed by each eyelid boundary key point.

[0059] Eyelid boundary keypoints are keypoints in the eye image that represent the edge of the eye. The eyelid boundary is determined by each eyelid boundary keypoint. The eyelid boundary can be obtained by curve fitting the eyelid boundary keypoints or by connecting the keypoints directly based on their coordinates.

[0060] Specifically, eyelid boundary keypoints can be divided into canthus keypoints and middle eyelid keypoints. When determining the eyelid boundary, the middle eyelid keypoints can be fitted with the canthus keypoints as endpoints to obtain the eyelid boundary. The middle eyelid keypoints can specifically include upper eyelid boundary keypoints and lower eyelid boundary keypoints. When determining the eyelid boundary, the upper eyelid boundary keypoints and lower eyelid boundary keypoints can be fitted with the canthus keypoints as endpoints to obtain the upper eyelid boundary and the lower eyelid boundary, respectively. The eyelid boundary is then constructed based on the upper eyelid boundary and the lower eyelid boundary.

[0061] In one embodiment, after acquiring the eye image of the target object, the computer device predicts key points of the eye image based on a key point prediction algorithm. While predicting multiple iris boundary key points, the computer device can also predict multiple eyelid boundary key points, and mark the multiple eyelid boundary key points in the eye image or record their coordinate positions. For the multiple eyelid boundary key points, the computer device processes each eyelid boundary key point by connecting key points or fitting key points, and obtains the eyelid boundary composed of each eyelid boundary key point.

[0062] In one application embodiment, as shown in FIG4 , the predicted key points include 4 pupil boundary key points, 8 iris outer boundary key points, and 6 eyelid boundary key points. The eyelid boundary key points include 2 eye corner key points, 1 lower eyelid boundary key point, and 3 upper eyelid boundary key points. The computer device fits a circular pupil boundary using the 4 pupil boundary key points, and fits an elliptical iris outer boundary using the 8 iris outer boundary key points. Based on the fitted iris outer boundary and the fitted pupil boundary, the predicted iris region is determined. Furthermore, the computer device obtains the upper eyelid boundary by connecting the 2 eye corner key points and the 3 upper eyelid boundary key points, and obtains the lower eyelid boundary by connecting the 2 eye corner key points and the 1 lower eyelid boundary key point, and then determines the eyelid boundary based on the upper eyelid boundary and the lower eyelid boundary.

[0063] Step 208 : Based on the relative positional relationship between the predicted iris area and the area formed by the eyelid boundary, an iris occlusion analysis is performed on the target object to obtain an iris occlusion analysis result.

[0064] The area formed by the eyelid boundary is the internal area formed by the eyelid boundary, and overlaps with the predicted iris area in at least a portion. The relative positional relationship between the predicted iris area and the area formed by the eyelid boundary specifically includes that the area formed by the eyelid boundary includes the entire predicted iris area, and that the area formed by the eyelid boundary includes a portion of the predicted iris area. For example, as shown in FIG5 , when the target object is collecting an eye image, the eye is in a fully open state, and the area formed by the eyelid boundary includes the predicted iris area. For another example, as shown in FIG6 , when the target object is collecting an eye image, the eye is in a half-open state, and the area formed by the eyelid boundary includes a portion of the predicted iris area, and the rest of the predicted iris area is covered by the eyelid.

[0065] Iris occlusion analysis refers to the analysis of the degree of iris obstruction by the eyelids. The degree of iris occlusion can be analyzed by setting an occlusion ratio threshold, or by determining whether the eyelids obstruct the pupil area. The specific iris occlusion analysis method can be determined by the actual scenario's requirements for iris occlusion analysis. For example, when determining a student's learning status or a driver's driving status, analysis can be performed by calculating an occlusion ratio threshold; during user identity verification, analysis can be performed by determining whether the eyelids obstruct the pupil area.

[0066] The iris occlusion analysis result may include the degree of iris occlusion by the eyelid, and may also include whether the eyelid occludes the pupil. In some embodiments, the computer device may determine the iris occlusion ratio by the eyelid based on the relative positional relationship between the predicted iris area and the area formed by the eyelid boundary. The computer device then compares the iris occlusion ratio with a set occlusion ratio threshold to determine the degree of iris occlusion by the eyelid, thereby obtaining the iris occlusion analysis result. The iris occlusion ratio by the eyelid can provide a more accurate occlusion analysis result, which is suitable for scenarios requiring high occlusion accuracy.

[0067] In some other embodiments, the computer device can also determine whether the eyelid blocks the pupil based on the relative position relationship between the predicted iris area and the area formed by the eyelid boundary. If the eyelid blocks the pupil, it indicates that the degree of occlusion of the iris by the eyelid is high. If the eyelid does not block the pupil, it indicates that the degree of occlusion of the iris by the eyelid is low. The method of judging whether the eyelid blocks the pupil is simpler and the judgment result can be obtained quickly. It can be applied to scenarios that require high speed in judging the degree of occlusion.

[0068] Furthermore, the purpose of iris occlusion analysis in this application is to obtain iris information of the target subject for identity recognition. The target subject's eye image includes iris information. To protect the target subject's iris information and the identity recognition results obtained based on this iris information, data encryption can be used during data transmission between the device that captures the target subject's eye image and the device that performs iris recognition.

[0069] When the iris occlusion analysis process is implemented by a server, the data sent by the terminal to the server can be an encrypted eye image. The eye image encryption can be achieved through image segmentation and reassembly, key encryption, and other methods. Image segmentation and reassembly refers to the process of segmenting and reassembling the eye image into multiple image blocks according to certain rules and then reassembling them. During the transmission of the eye image, the segmented and reassembled image is transmitted. After the server obtains the segmented and reassembled image, it can perform the reverse image segmentation and reassembly process based on the terminal, restoring the multiple image blocks to the eye image, and then perform subsequent processing. This prevents the leakage of iris information contained in the target subject's eye image during transmission. Furthermore, after the server performs identity recognition on the iris information in the eye image, if the application scenario requires feedback of specific identity information to the terminal, the identity information can be encrypted using a key during transmission. This can, to a certain extent, prevent the leakage of the identity information corresponding to the eye image and reduce the threat posed to the target subject's identity information security.

[0070] When the iris occlusion analysis process is completed by the terminal, the terminal can encrypt the iris information when the iris occlusion analysis result represents that the eye image can be used for iris recognition, and send the extracted iris information to the server for identity recognition. The encryption method can be data block reorganization and key encryption.

[0071] The above-mentioned iris occlusion analysis method can directly predict multiple iris boundary key points and multiple eyelid boundary key points by performing key point prediction on the eye image of the target object, and can quickly predict the key points in the eye image, and then can determine the predicted iris area and eyelid boundary based on the key points, wherein the predicted iris area is not only the iris displayed in the eye image, but is obtained by contour fitting of each iris boundary key point according to the iris contour shape condition, and can quickly and easily determine the predicted iris area, and the eyelid boundary is composed of eyelid boundary key points, which can accurately express the eyelid position in the eye image, so that the target object can be subjected to iris occlusion analysis based on the relative position relationship between the predicted iris area and the area composed of the eyelid boundary, and the iris occlusion analysis result can be obtained quickly and accurately.

[0072] In one embodiment, key point prediction is performed on an eye image of a target object to obtain a plurality of iris boundary key points and a plurality of eyelid boundary key points, including:

[0073] Perform preliminary key point recognition on the target object's eye image to determine the initial key points; determine the eye area in the eye image according to the distribution of the initial key points in the eye image; use the area ratio of the eye area reaching a set ratio threshold as the cropping condition to crop the eye image to obtain the target image; predict key points of the target image based on the key point prediction algorithm to obtain multiple iris boundary key points and multiple eyelid boundary key points.

[0074] The eye image of the target object can be an eye image containing the target object's eyes, captured at a preset size. The preset size can be an acquisition parameter set by the image acquisition device. Using the same acquisition parameters for different objects in different scenes results in images of the same size. However, the acquisition distance between the target object and the image acquisition device may vary with the acquisition scene, and individual differences between different target objects may also result in different acquisition distances. Therefore, the keypoint prediction algorithm employs an iterative approach to image processing to predict keypoints. In the first stage of the keypoint prediction algorithm, an image of a specific size is input, subjected to a series of convolution operations, and then processed through two fully-connected layers to obtain the final predicted keypoint coordinates (xi, yi). Due to the uncertain size of the input object, an input image of a specific size can result in an overly large image, resulting in errors in the final keypoint prediction due to scaling. In the second stage of the keypoint prediction algorithm, the principles of the first stage are reused, and the area surrounding the predicted keypoint locations is cropped and enlarged for further, more accurate prediction, thereby improving the final prediction accuracy.

[0075] Specifically, in the first stage, the key point prediction algorithm used is the DeepPose algorithm. Its core idea is to transform the key point detection algorithm into a purely mathematical prediction problem. By manually annotating a large number of sample images of eye key points in various states and learning the sample images through DNN (Deep Neural Networks), a more general end-to-end key point prediction can be achieved.

[0076] In one specific application, a computer device acquires an eye image of a target subject captured by an image acquisition device, where the eye image includes the target subject's eye region. The eye image acquisition process includes the computer device sending an acquisition instruction to the image acquisition device, thereby acquiring the eye image, which includes the target subject's eye and is captured by the image acquisition device at a preset size.

[0077] In other embodiments, the eye image acquisition process may also involve the image acquisition device proactively triggering eye image acquisition of the target subject upon detecting that specific conditions are met, and then transmitting the acquired eye image to the computer device. The image acquisition device may be a device that communicates with the computer device via a network, or may be a device built into the computer device.

[0078] In some embodiments, taking VR scenes as an example, the image acquisition device can be an infrared image acquisition device, which uses an infrared sensor to capture infrared light imaging. Since the iris has a relatively special absorption characteristic for infrared, and at the same time avoids interference from VR color imaging in VR scenes, using infrared images to collect iris information has better anti-interference and recognition effects.

[0079] After acquiring an eye image of a preset size, the computer device first performs preliminary key point identification on the target object's eye image based on a key point prediction algorithm to determine the initial key points. The computer device then determines the eye region within the eye image based on the distribution data of the initial key points within the eye image. The computer device then crops the eye image, using the eye region's area ratio reaching a set threshold as the cropping condition, to obtain a target image whose key point distribution meets the preset distribution condition. After obtaining the target image, the computer device can perform key point prediction on the target image based on the key point prediction algorithm to obtain multiple iris boundary key points and multiple eyelid boundary key points.

[0080] As shown in FIG7 , the eye image is cropped according to the distribution of the initial key points in the eye image to obtain a target image in which the key point distribution meets the distribution conditions. This effect can be achieved through multiple cropping, where each cropping is performed according to a set ratio, and the key points of the cropped image are re-predicted until the area ratio of the eye region in the cropped image reaches a set ratio threshold. The image is used as the target image to predict the iris boundary key points and the eyelid boundary key points.

[0081] In this embodiment, by looping key point prediction and image cropping through a key point prediction algorithm, the key point prediction results can be optimized so that the predicted iris boundary key points and eyelid boundary key points have higher accuracy.

[0082] In some embodiments, the key point prediction process is implemented using a key point prediction model. The key point prediction model training process includes: obtaining sample images of the eye in different occlusion states, the sample images being annotated with iris boundary key points and eyelid boundary key points, wherein the distribution of the annotated iris boundary key points in the sample images conforms to iris contour shape conditions; the annotated eyelid boundary key points are used to characterize the eyelid boundary in the sample images; and training an initial deep neural network model based on the sample images until a model training stop condition is met, thereby obtaining a key point prediction model for predicting key points in eye images.

[0083] Among them, the key point prediction model can be obtained by training the initial deep neural network model with sample images carrying key point annotations. The annotation method of the key points in the sample image will affect the prediction effect of the trained key point prediction model. Therefore, when annotating the sample image, it is necessary to ensure that the distribution of the annotated iris boundary key points in the sample image meets the iris contour shape conditions, and the annotated eyelid boundary key points are located on the eyelid boundary, so that the annotated eyelid boundary key points can accurately represent the eyelid boundary in the sample image. Among them, the annotation method of the key points in the sample image can be implemented separately based on the type of key points. For example, the iris boundary key points can be selected on the iris contour with a specific shape in the sample image, and the eyelid boundary key points can be directly selected on the eyelid boundary in the sample image.

[0084] The initial deep neural network model can be a DNN network model, wherein the structure of the DNN network model is shown in Figure 8, including multiple convolutional layers and two fully connected layers. After the fully connected layer processes and obtains the predicted target points, the current image is further cropped based on the predicted target points to obtain a new image and the DNN network model re-performs the target point prediction process until a target image with a key point distribution that meets the distribution conditions is obtained. The DNN network model then performs the final key point prediction process and outputs the prediction results. During the training process, the DNN network model adopts supervised training based on annotated key points, and uses the key point prediction model obtained through training to perform key point prediction processing on the eye image of the target object.

[0085] In this embodiment, by using a deep neural network model as the model architecture and using sample images labeled with various key points as training samples, the trained key point prediction model can have accurate and efficient key point recognition and prediction capabilities, thereby improving the prediction efficiency of key points in eye images.

[0086] In some embodiments, the eyelid boundary includes an upper eyelid boundary and a lower eyelid boundary; the eyelid boundary key points include a corner of the eye key point located at the intersection of the upper eyelid boundary and the lower eyelid boundary, an upper eyelid key point located on the upper eyelid boundary, and a lower eyelid key point located on the lower eyelid boundary; the number of upper eyelid key points is greater than the number of lower eyelid key points.

[0087] The upper eyelid boundary refers to the boundary line representing the upper eyelid boundary of the target object in the eye image, and the lower eyelid boundary refers to the boundary line representing the lower eyelid boundary of the target object in the eye image. The intersection of the upper and lower eyelids is the canthus, and the key points marked at the canthus are called canthus keypoints. The key points marked on the upper eyelid boundary are called upper eyelid keypoints, and the key points marked on the lower eyelid boundary are called lower eyelid keypoints. Since the curvature of the upper eyelid boundary is generally greater than that of the lower eyelid boundary, when marking eyelid boundary keypoints, the number of marked upper eyelid keypoints can be greater than the number of marked lower eyelid keypoints.

[0088] In this embodiment, by limiting the position and number of key points on the eyelid boundary and marking the key points on the eyelid boundary, the marked key points in the sample image can more accurately characterize the specific position of the eyelid, thereby enabling the key point prediction model trained based on the sample image marked with key points to more accurately predict the key points.

[0089] In some embodiments, after performing keypoint prediction on the target subject's eye image and obtaining eyelid boundary keypoints, the eyelid boundary in the eye image needs to be determined based on the eyelid boundary keypoints. Previously, we described how the eyelid boundary can be determined using curve fitting and keypoint connection. The following describes how to determine the eyelid boundary using the keypoint connection method.

[0090] Specifically, determining the eyelid boundary formed by each eyelid boundary key point includes:

[0091] From each eyelid boundary key point, identify the canthus key point, upper eyelid key point and lower eyelid key point; with the canthus key point as the endpoint, connect each upper eyelid key point through the first connecting line to obtain the upper eyelid boundary; with the canthus key point as the endpoint, connect each lower eyelid key point through the second connecting line to obtain the lower eyelid boundary; based on the upper eyelid boundary and the lower eyelid boundary, determine the eyelid boundary.

[0092] Among them, the eyelid boundary key points can be divided into three categories according to their positional relationship, namely, canthus key points, upper eyelid key points and lower eyelid key points. Among them, the canthus key points represent the position of the canthus in the eye image and are the endpoints of the upper eyelid boundary and the lower eyelid boundary. Therefore, the computer device can use the canthus key point as the endpoint and connect the upper eyelid key points through a first line to obtain the upper eyelid boundary; use the canthus key point as the endpoint and connect the lower eyelid key points through a second line to obtain the lower eyelid boundary, so that the eyelid boundary can be determined based on the upper eyelid boundary and the lower eyelid boundary.

[0093] In other embodiments, the eyelid boundary formed by the eyelid boundary key points may be determined by sequentially connecting the eyelid boundary key points in a clockwise direction or a counterclockwise direction to form a convex polygon, and the convex polygon is the eyelid boundary.

[0094] In this embodiment, the eyelid boundary is determined by connecting key points. This method is simple and can quickly determine the position of the eyelid boundary, thereby improving data processing speed.

[0095] In some embodiments, key point prediction is performed on the eye image of the target object to obtain multiple iris boundary key points and multiple eyelid boundary key points, including: key point prediction is performed on the eye image of the target object based on a key point prediction algorithm to obtain multiple pupil boundary key points, multiple iris outer boundary key points and multiple eyelid boundary key points.

[0096] Furthermore, according to the iris contour shape condition, contour fitting is performed on each iris boundary key point to obtain the predicted iris area, including:

[0097] Based on the distribution of each iris outer boundary key point, according to the iris outer contour shape condition, the iris outer contour is fitted for each iris outer boundary key point to obtain the predicted iris outer boundary; based on the distribution of each pupil boundary key point, according to the pupil contour shape condition, the pupil contour is fitted for each pupil boundary key point to obtain the predicted pupil boundary; the predicted iris outer boundary and the predicted pupil boundary are used as the iris area boundaries to determine the predicted iris area.

[0098] The iris is the annular area between the black pupil and the white sclera on the surface of the human eye. Iris boundary keypoints can be divided into two categories based on their position: pupil boundary keypoints and iris outer boundary keypoints. Pupil boundary keypoints are keypoints located on the boundary line between the pupil and iris, while iris outer boundary keypoints are keypoints located on the boundary line between the iris and sclera.

[0099] During the process of contour fitting for each iris boundary key point, the computer device can separately perform contour fitting for the pupil boundary key point and the iris outer boundary key point. The contour fitting for the pupil boundary key point and the iris outer boundary key point can be performed synchronously or asynchronously, depending on the allocation of data processing resources.

[0100] Specifically, during the iris outer contour fitting process, the computer device performs iris outer contour fitting on each iris outer boundary key point based on the distribution of each iris outer boundary key point and in accordance with the iris outer contour shape condition, thereby obtaining a predicted iris outer boundary. During the pupil contour fitting process, the computer device performs pupil contour fitting on each pupil boundary key point based on the distribution of each pupil boundary key point and in accordance with the pupil contour shape condition, thereby obtaining a predicted pupil boundary. After obtaining the predicted iris outer boundary and the predicted pupil boundary, the computer device may, based on the positional relationship between the predicted iris outer boundary and the predicted pupil boundary, use the predicted iris outer boundary and the predicted pupil boundary as the iris region boundary, and determine the region between the predicted iris outer boundary and the predicted pupil boundary as the predicted iris region.

[0101] In this embodiment, by performing contour fitting on the pupil boundary key points and the iris outer boundary key points respectively, the predicted iris outer boundary and the predicted pupil boundary are obtained, so that the iris boundary key points at different positions can be used to achieve different iris boundary predictions, thereby improving the position accuracy of the predicted iris area.

[0102] The iris outer contour shape condition and the pupil contour shape condition may vary depending on the shooting angle of the eye image and the environment in which the image is taken. In some embodiments, the iris outer contour shape condition is an elliptical contour, and the pupil contour shape condition is a circular contour. Furthermore, determining the predicted iris region using the predicted iris outer boundary and the predicted pupil boundary as the iris region boundaries includes:

[0103] An elliptical area formed by the outer boundary of the predicted iris and a circular area formed by the outer boundary of the predicted iris are determined respectively; and an area in the elliptical area that does not overlap with the circular area is determined as the predicted iris area.

[0104] In actual applications, to avoid obstructing the target subject's line of sight, the target subject's eye image can be captured from a side angle or other angle. In this case, due to angular distortion, the iris in the target subject's eye image appears elliptical. Therefore, the iris outer boundary shape condition in the iris outline shape condition can be set to an elliptical outline, and the pupil boundary shape condition in the iris outline shape condition can be set to a circular outline.

[0105] During the iris outer contour fitting process, the computer device fits the iris outer contour to each iris outer boundary key point according to an elliptical contour based on the distribution of each iris outer boundary key point, thereby obtaining an elliptical predicted iris outer boundary. During the pupil contour fitting process, the computer device fits the pupil contour to each pupil boundary key point according to a circular contour based on the distribution of each pupil boundary key point, thereby obtaining a circular predicted pupil boundary. After obtaining the elliptical area formed by the predicted iris outer boundary and the circular area formed by the predicted pupil boundary, the computer device may determine the area within the elliptical area that does not overlap with the circular area as the predicted iris area.

[0106] In this embodiment, by considering the impact of angular distortion on the iris' outer boundary, the iris outer boundary shape condition in the iris outline shape condition can be set to an elliptical contour. This allows for better contour fitting of key points on the iris' outer boundary, improving the accuracy of the predicted iris outer boundary's description of the pupil's outer boundary. Furthermore, considering that the pupil area is relatively small and thus less affected by distortion, to simplify the pupil fitting process, the pupil boundary shape condition in the iris outline shape condition can be set to a circular contour, effectively increasing the pupil boundary fitting speed.

[0107] In some embodiments, an iris occlusion analysis is performed on the target object based on the relative positional relationship between the predicted iris region and the region formed by the eyelid boundary to obtain an iris occlusion analysis result, including:

[0108] For each pixel point in the predicted iris area, the target pixel points in the area formed by the eyelid boundary are screened out according to the coordinates of each pixel point; the iris occlusion ratio of the target object is determined based on the ratio of the number of target pixels to the total number of pixels in the predicted iris area; iris occlusion analysis is performed based on the iris occlusion ratio and the maximum tolerance ratio threshold of iris occlusion to obtain the iris occlusion analysis result.

[0109] To ensure the accuracy of the iris occlusion analysis results, the computer device uses a target pixel ratio calculation method. Specifically, the iris occlusion ratio of the target object is essentially the ratio of the target pixels within the eyelid boundary within the predicted iris region to the total number of pixels within the predicted iris region. A greater ratio of target pixels to the total number of pixels within the predicted iris region indicates less iris occlusion, while a smaller ratio of target pixels to the total number of pixels within the predicted iris region indicates more iris occlusion.

[0110] The maximum tolerance ratio threshold for iris occlusion refers to a threshold set to determine if the degree of iris occlusion affects subsequent processing. For example, when an eye image is captured and iris occlusion analysis is performed on a target object wearing a VR device, an iris occlusion analysis result is obtained. If the iris occlusion analysis result indicates that the occlusion ratio exceeds the maximum tolerance ratio threshold, the iris occlusion analysis result is sent to the VR device, causing the VR device to issue a prompt message to the target object to open their eyes so that eye images can be recaptured for analysis. For another example, when the iris occlusion analysis result indicates that the occlusion ratio is less than or equal to the maximum tolerance ratio threshold, the server extracts iris features from the predicted iris area and, based on the iris features, performs iris recognition processing on the target object to obtain an iris recognition result.

[0111] Furthermore, in some embodiments, if the iris occlusion analysis result indicates that the iris occlusion ratio is less than or equal to a maximum tolerable iris occlusion ratio threshold, iris features are extracted from the predicted iris area; based on the iris features, iris recognition processing is performed on the target object to obtain a recognition result. In other embodiments, if the iris occlusion analysis result indicates that the iris occlusion ratio is greater than the maximum tolerable iris occlusion ratio threshold, a reminder message is generated for the target object.

[0112] Specifically, when the iris occlusion analysis result shows that the iris occlusion ratio is greater than the maximum tolerance ratio threshold, a reminder message is generated for the target object, including:

[0113] When the iris occlusion analysis result shows that the iris occlusion ratio is greater than the maximum tolerance ratio threshold, the reminder message type is determined based on the current scene of the target object; and a reminder message is generated for the target object according to the reminder message type.

[0114] For example, the iris occlusion analysis method can be applied to traffic scenarios, educational scenarios, and the like. For example, while a driver is driving in a traffic scenario, the iris occlusion analysis method can be used to analyze the driver's iris occlusion. The results of the iris occlusion analysis can be used to determine whether the driver is driving fatigued. If the driver is found to be driving fatigued, a prompt message can be sent to the driver in a timely manner.

[0115] For another example, during a class in an educational scenario, the iris occlusion analysis method is used to perform iris occlusion analysis on students, and the results of the iris occlusion analysis are used to determine whether the students are dozing off in class. If a student is found to be dozing off, a prompt message is sent to the student in a timely manner.

[0116] In some embodiments, an iris occlusion analysis method is further provided, as shown in FIG9 , and the method includes:

[0117] Step 902 : Acquire sample images of eyes in different occlusion states, wherein the sample images are marked with iris outer boundary key points, pupil boundary key points, and eyelid boundary key points.

[0118] Step 904 : Train the initial deep neural network model based on the sample image until the model training stop condition is met, thereby obtaining a key point prediction model for predicting key points of the eye image.

[0119] The sample image is a sample data that carries eye key point annotations and is used for key point prediction model. The annotation method of the key points in the sample image will affect the prediction effect of the trained key point prediction model. Therefore, when annotating the sample image, it is necessary to ensure that the distribution of the annotated iris boundary key points in the sample image meets the iris contour shape conditions, and the annotated eyelid boundary key points are located on the eyelid boundary, so that the annotated eyelid boundary key points can accurately represent the eyelid boundary in the sample image. The annotation method of the key points in the sample image can be implemented separately based on the type of key points. For example, the iris boundary key points can be selected on the iris contour with a specific shape in the sample image, and the eyelid boundary key points can be directly selected on the eyelid boundary in the sample image.

[0120] The initial deep neural network model can be a DNN network model, wherein the DNN network model includes multiple convolutional layers and two fully connected layers. After the fully connected layer processes to obtain the predicted target points, the current image is further cropped based on the predicted target points to obtain a new image and the DNN network model re-performs target point prediction processing until a target image with a key point distribution that meets the distribution conditions is obtained. The DNN network model then performs a final key point prediction process and outputs a prediction result. During the training process, the DNN network model uses supervised training based on annotated key points, and uses the key point prediction model obtained through training to perform key point prediction processing on the eye image of the target object.

[0121] Step 906: Acquire an eye image including the eyes of the target object captured according to a preset size.

[0122] The acquisition of the eye image includes the computer device sending an acquisition instruction to the image acquisition device, and acquiring the eye image containing the target object's eye captured by the image acquisition device according to a preset size. In other embodiments, the acquisition of the eye image can also be that the image acquisition device actively triggers the acquisition of the eye image of the target object when detecting that a specific condition is met, and sends the acquired eye image to the computer device. The image acquisition device can be a device that communicates with the computer device through a network, or it can be a device that comes with the computer device. In some embodiments, such as in a VR scene, the image acquisition device can be an infrared image acquisition device, which uses an infrared sensor to capture pan-infrared light imaging. Since the iris has a relatively special absorption characteristic for infrared, and in a VR scene, it avoids interference from VR color imaging, and the use of infrared images to acquire iris information has better anti-interference and recognition effects.

[0123] Step 908 : Preliminary key point recognition is performed on the eye image of the target object based on the key point prediction algorithm used by the key point prediction model to determine initial key points.

[0124] Step 910: Determine the eye region in the eye image according to the distribution of the initial key points in the eye image; and crop the eye image based on the fact that the area ratio of the eye region reaches a set ratio threshold as a cropping condition to obtain a target image.

[0125] Step 912: perform key point prediction on the eye image of the target object to obtain a plurality of pupil boundary key points, a plurality of iris outer boundary key points, and a plurality of eyelid boundary key points.

[0126] Step 914 : Based on the distribution of each iris outer boundary key point, perform iris outer contour fitting on each iris outer boundary key point according to the ellipse contour to obtain a predicted iris outer boundary.

[0127] Step 916 : Based on the distribution of each pupil boundary key point, pupil contour fitting is performed on each pupil boundary key point according to a circular contour to obtain a predicted pupil boundary.

[0128] Step 918: Determine the elliptical area and the circular area formed by the outer boundary of the predicted iris, and determine the area in the elliptical area that does not overlap with the circular area as the predicted iris area.

[0129] Step 920: Identify the eye corner key points, upper eyelid key points, and lower eyelid key points from each eyelid boundary key point.

[0130] Step 922: With the canthus key point as the endpoint, connect the upper eyelid key points through a first line to obtain the upper eyelid boundary; with the canthus key point as the endpoint, connect the lower eyelid key points through a second line to obtain the lower eyelid boundary.

[0131] Step 924 : Determine the eyelid boundary based on the upper eyelid boundary and the lower eyelid boundary.

[0132] Step 926 : For each pixel point in the predicted iris area, target pixel points within the area formed by the eyelid boundary are screened out according to the coordinates of each pixel point.

[0133] Step 928 : Determine the iris occlusion ratio of the target object based on the ratio of the number of target pixels to the total number of pixels in the predicted iris area.

[0134] Step 930: Perform iris occlusion analysis based on the iris occlusion ratio and the maximum tolerance ratio threshold of iris occlusion to obtain an iris occlusion analysis result.

[0135] Step 932: If the iris occlusion analysis result shows that the iris occlusion ratio is less than or equal to the maximum tolerance ratio threshold, extract iris features in the predicted iris area, and perform iris recognition processing on the target object based on the iris features to obtain a recognition result.

[0136] Step 934 : When the iris occlusion analysis result shows that the iris occlusion ratio is greater than the maximum tolerance ratio threshold, the reminder message type is determined based on the current scene of the target object, and a reminder message is generated for the target object according to the reminder message type.

[0137] This application also provides an application scenario for VR iris recognition, which applies the above-mentioned iris occlusion analysis method. Specifically, the application of the iris occlusion analysis method in this application scenario is as follows:

[0138] In the iris recognition scenario, due to differences in the size of users' eyes, there will be different degrees of eyelid occlusion, etc. Based on this, it is necessary to provide a relevant processing method to determine the occlusion of the iris by the eyelid, so as to ensure the iris recognition effect. The existing algorithm for determining iris occlusion is mainly to perform semantic segmentation on the eyelid and iris, and then determine the iris occlusion. Since this type of method is based on semantic segmentation, it has very high requirements on the accuracy and speed of the segmentation algorithm. In the VR recognition scenario, the speed is poor and real-time processing cannot be achieved. At the same time, after semantic segmentation, only the content area of ​​the iris and eyelid can be obtained, and the proportion of the iris that is occluded cannot be determined. Due to the difference in camera imaging distance, although the size of the iris area is obtained, the proportion of occlusion cannot be evaluated. At the same time, iris recognition in VR scenarios will lead to insufficient semantic segmentation accuracy due to interference factors such as eyelid shadows and eyelashes.

[0139] In this application, after a user puts on a VR device, the iris recognition camera continuously captures photos of the user's eyes. Using an algorithm, it determines the extent of iris occlusion and provides corresponding prompts. If the occlusion ratio is significant, the user is prompted to open their glasses or the displayed content is adjusted to guide the user to open their glasses wider. Specifically, the computer device can use the DeepPose algorithm to predict the eyelid boundary key points and iris boundary key points, and then determine the iris occlusion ratio based on the relationship between the eyelid key points and the position of the pupil and iris.

[0140] Specifically, this plan consists of three parts:

[0141] 1. Key point calculation based on DeepPose's pupil boundary key points, iris outer boundary key points, and eyelid boundary key points;

[0142] 2. Based on the pupil boundary key points, iris outer boundary key points, and eyelid boundary key points, the iris area formed by the pupil boundary and iris outer boundary is determined, and the iris occlusion ratio is accurately calculated based on the eyelid boundary;

[0143] 3. The optimal logic determines whether the occlusion ratio meets the requirements and gives corresponding prompts.

[0144] Furthermore, calculating iris occlusion requires knowing the position of the iris itself and the eyelids. This allows for accurate calculation of the occlusion ratio and degree, and for assessing whether subsequent iris recognition algorithms support this degree of occlusion. DeepPose can be used to predict key points in the iris region, and based on these predicted key points, the predicted iris region can be obtained.

[0145] The DeepPose algorithm's philosophy is to disregard the anthropomorphic nature of complex poses and instead transform keypoint detection into a purely mathematical prediction problem. By manually labeling a large amount of eye keypoint data in various poses and then using a Deep Neural Network (DNN) convolutional neural network to learn from this sample data, a more general end-to-end eye keypoint detection algorithm is achieved.

[0146] In the first stage of eye key point detection, the DNN convolutional neural network can perform a series of convolutions on the input image of a set size, and finally obtain the coordinates (xi, yi) of the predicted key points through two fully connected layers. At the same time, the optimization idea of ​​the DeepPose algorithm is that since the input target size is uncertain and the network itself only receives input images of a fixed size, it will cause errors in the final target key point prediction due to scaling of overly large images. In the second stage of eye key point detection, the DeepPose algorithm continues to reuse the ideas of the first stage, but only crops and enlarges the area around the estimated key point position and continues to make further more accurate predictions, thereby improving the final prediction accuracy. The DeepPose algorithm is a DNN network fitting of nonlinear regression problems, and returns the network prediction results end-to-end.

[0147] In one embodiment, taking the analysis of the eye image of the right eye of the target object as an example, after the eye image is predicted by DeepPose, 19 key points of the eye area are returned, including 4 estimated key points for the eyelid key points, 8 estimated key points for the points around the iris, and 7 estimated key points for the points around the pupil. Specifically, since the pupil itself is a circular area, and in the iris recognition scenario, the pupil will be guided to become smaller through environmental adjustment, and the imaging distortion is not large at small angles, only 4 key points are used for the pupil key points. The iris area is larger than the pupil, and the upper right is more easily blocked by the eyelid, so 8 key points are used for alignment in the iris area. Similarly, since the upper part of the eyelid area has a larger curve than the lower part, 7 key points are used for alignment in the upper part.

[0148] Based on the iris boundary key points, since the pupil and iris regions are circular, distortions such as angles can transform them into ellipses. However, given the small size of the pupil, distortions are not significant. Furthermore, too many registration points can lead to high errors. Therefore, we use four points to define a circular mark for the pupil region. For the iris edge, eight points are used with the fitEllipse function in OpenCV (a cross-platform computer vision library) to perform ellipse matching to obtain the iris region's location information. Due to its irregular shape, the eyelid boundary can be calibrated using a simple line-connecting method.

[0149] Specifically, the computer device fits a circular pupil boundary using four pupil boundary keypoints and an elliptical iris boundary using eight iris boundary keypoints. Based on the fitted iris boundary and the fitted pupil boundary, the computer device determines the predicted iris region. Furthermore, the computer device connects two eye corner keypoints with three upper eyelid boundary keypoints to obtain the upper eyelid boundary, and connects two eye corner keypoints with one lower eyelid boundary keypoint to obtain the lower eyelid boundary. The computer device then determines the eyelid boundary based on the upper and lower eyelid boundaries.

[0150] The iris area can be determined by the known pupil boundary and iris outer boundary. The computer device can accurately determine the iris occlusion ratio by judging whether each pixel in the iris area is within the area formed by the upper eyelid boundary and the lower eyelid boundary.

[0151] The iris recognition algorithm determines the iris occlusion ratio. If the occlusion ratio is greater than the maximum ratio tolerated by the iris recognition algorithm, the user is prompted to open their eyes. Otherwise, if the iris recognition algorithm meets the requirements, the algorithm will be used to perform the next iris recognition process.

[0152] In this embodiment, because this solution primarily relies on the DeepPose algorithm to estimate iris key points, the algorithm is relatively fast. For iris recognition scenarios in VR, it can accurately determine iris occlusion while maintaining recognition speed, overcoming the problems of traditional semantic segmentation-based algorithms, such as slow speed and inability to accurately calculate occlusion ratios.

[0153] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0154] Based on the same inventive concept, embodiments of the present application also provide an iris occlusion analysis device for implementing the aforementioned iris occlusion analysis method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more of the following embodiments of the iris occlusion analysis device can be found in the above-described limitations of the iris occlusion analysis method and will not be further elaborated here.

[0155] In one embodiment, as shown in FIG10 , an iris occlusion analysis device is provided, comprising: a key point prediction module 1002 , a contour fitting module 1004 , a boundary determination module 1006 , and an occlusion analysis module 1008 , wherein:

[0156] A key point prediction module 1002 is used to predict key points of the eye image of the target object to obtain multiple iris boundary key points and multiple eyelid boundary key points;

[0157] The contour fitting module 1004 is used to perform contour fitting on each of the iris boundary key points according to the iris contour shape condition to obtain a predicted iris area;

[0158] A boundary determination module 1006 is used to determine the eyelid boundary formed by the eyelid boundary key points;

[0159] The occlusion analysis module 1008 is configured to perform iris occlusion analysis on the target object based on the relative positional relationship between the predicted iris region and the region formed by the eyelid boundary, and obtain an iris occlusion analysis result.

[0160] In some embodiments, the key point prediction module is further used to determine initial key points based on preliminary key point identification of the eye image of the target object; determine the eye area in the eye image according to the distribution of the initial key points in the eye image; crop the eye image based on the area ratio of the eye area reaching a set ratio threshold as the cropping condition to obtain a target image; and predict key points of the target image based on the key point prediction algorithm to obtain multiple iris boundary key points and multiple eyelid boundary key points.

[0161] In some embodiments, the key point prediction process is implemented by a key point prediction model; the training process of the key point prediction model includes:

[0162] Sample images of the eyes in different occlusion states are obtained, wherein the sample images are marked with iris boundary key points and eyelid boundary key points, and the distribution of the marked iris boundary key points in the sample images conforms to the iris contour shape conditions; the marked eyelid boundary key points are used to characterize the eyelid boundary in the sample images; an initial deep neural network model is trained based on the sample images until the model training stopping conditions are met, thereby obtaining a key point prediction model for key point prediction of the eye images.

[0163] In some embodiments, the eyelid boundary includes an upper eyelid boundary and a lower eyelid boundary; the eyelid boundary key points include a corner of the eye key point located at the intersection of the upper eyelid boundary and the lower eyelid boundary, an upper eyelid key point located on the upper eyelid boundary, and a lower eyelid key point located on the lower eyelid boundary; the number of the upper eyelid key points is greater than the number of the lower eyelid key points.

[0164] In some embodiments, the boundary determination module is further used to identify the canthus key point, the upper eyelid key point and the lower eyelid key point from each of the eyelid boundary key points; using the canthus key point as the endpoint, connecting each of the upper eyelid key points through a first line to obtain the upper eyelid boundary; using the canthus key point as the endpoint, connecting each of the lower eyelid key points through a second line to obtain the lower eyelid boundary; and determining the eyelid boundary based on the upper eyelid boundary and the lower eyelid boundary.

[0165] In some embodiments, the key point prediction module is further used to perform key point prediction on the eye image of the target object to obtain a plurality of pupil boundary key points, a plurality of iris outer boundary key points, and a plurality of eyelid boundary key points;

[0166] The contour fitting module is further used to perform iris outer contour fitting on each of the iris outer boundary key points based on the distribution of each of the iris outer boundary key points and in accordance with the iris outer contour shape condition to obtain a predicted iris outer boundary; perform pupil contour fitting on each of the pupil boundary key points based on the distribution of each of the pupil boundary key points and in accordance with the pupil contour shape condition to obtain a predicted pupil boundary; and determine a predicted iris area using the predicted iris outer boundary and the predicted pupil boundary as iris area boundaries.

[0167] In some embodiments, the iris outer contour shape condition is an elliptical contour; the pupil contour shape condition is a circular contour;

[0168] The contour fitting module is further configured to respectively determine an elliptical area formed by the outer boundary of the predicted iris and a circular area formed by the outer boundary of the predicted iris; and determine an area within the elliptical area that does not overlap with the circular area as the predicted iris area.

[0169] In some embodiments, the occlusion analysis module is further used to screen out target pixel points within the area formed by the eyelid boundary for each pixel point within the predicted iris area according to the coordinates of each pixel point; determine the iris occlusion ratio of the target object based on the ratio of the number of target pixel points to the total number of pixels within the predicted iris area; perform iris occlusion analysis based on the iris occlusion ratio and the maximum tolerance ratio threshold of iris occlusion to obtain an iris occlusion analysis result.

[0170] In some embodiments, the device further includes an iris recognition module for extracting iris features in the predicted iris area when the iris occlusion analysis result indicates that the iris occlusion ratio is less than or equal to a maximum tolerance ratio threshold of iris occlusion; and performing iris recognition processing on the target object based on the iris features to obtain a recognition result.

[0171] In some embodiments, the apparatus further includes a message generating module configured to generate a reminder message for the target object when the iris occlusion analysis result indicates that the iris occlusion ratio is greater than a maximum tolerance ratio threshold of iris occlusion.

[0172] In some embodiments, the message generation module is further used to determine the reminder message type based on the current scene of the target object when the iris occlusion analysis result is that the iris occlusion ratio is greater than the maximum tolerance ratio threshold of the iris occlusion; and generate a reminder message for the target object according to the reminder message type.

[0173] The above-mentioned iris occlusion analysis device can directly predict multiple iris boundary key points and multiple eyelid boundary key points by performing key point prediction on the eye image of the target object, and can quickly predict the key points in the eye image, and then can determine the predicted iris area and eyelid boundary based on the key points, wherein the predicted iris area is not only the iris displayed in the eye image, but is obtained by contour fitting of each iris boundary key point according to the iris contour shape condition, and can quickly and conveniently determine the predicted iris area, and the eyelid boundary is composed of eyelid boundary key points, which can accurately express the eyelid position in the eye image, so that the target object can be subjected to iris occlusion analysis based on the relative position relationship between the predicted iris area and the area composed of the eyelid boundary, and the iris occlusion analysis result can be quickly and accurately obtained.

[0174] Each module in the aforementioned iris occlusion analysis device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0175] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in Figure 11. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data. The I / O interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements an iris occlusion analysis method.

[0176] In one embodiment, a computer device is provided, which may be a terminal. Its internal structure diagram may be as shown in Figure 12. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. The wireless communication may be achieved via Wi-Fi, a mobile cellular network, NFC (near field communication), or other technologies. When executed by the processor, the computer program implements an iris occlusion analysis method. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse, etc.

[0177] Those skilled in the art will understand that the structures shown in Figures 11 and 12 are merely block diagrams of partial structures related to the solution of the present application, and do not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figures, or combine certain components, or have a different component arrangement.

[0178] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0179] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0180] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0181] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0182] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0183] 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.

[0184] 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 application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. An iris occlusion analysis method, characterized in that: Executed by a computer device, the method includes: Predict key points of the target object's eye image to obtain multiple iris boundary key points and multiple eyelid boundary key points; According to the iris contour shape condition, contour fitting is performed on each of the iris boundary key points to obtain a predicted iris area; Determine the eyelid boundary formed by the eyelid boundary key points; and Based on the relative positional relationship between the predicted iris region and the region formed by the eyelid boundary, an iris occlusion analysis is performed on the target object to obtain an iris occlusion analysis result.

2. The method according to claim 1, characterized in that The step of performing key point prediction on the eye image of the target object to obtain a plurality of iris boundary key points and a plurality of eyelid boundary key points includes: Perform preliminary key point recognition on the target object's eye image based on the key point prediction algorithm to determine the initial key points; Determining an eye region in the eye image according to the distribution of the initial key points in the eye image; Taking the area ratio of the eye region reaching a set ratio threshold as a cropping condition, cropping the eye image to obtain a target image; and Key point prediction is performed on the target image based on the key point prediction algorithm to obtain a plurality of iris boundary key points and a plurality of eyelid boundary key points.

3. The method according to claim 1 or 2, characterized in that: The key point prediction process is implemented by a key point prediction model; the training process of the key point prediction model includes: Acquire sample images of eyes in different occlusion states, wherein the sample images are annotated with iris boundary key points and eyelid boundary key points, and distribution of the annotated iris boundary key points in the sample images meets the iris contour shape condition; the annotated eyelid boundary key points are used to characterize the eyelid boundary in the sample images; and The initial deep neural network model is trained based on the sample image until the model training stop condition is met, thereby obtaining a key point prediction model for predicting key points of the eye image.

4. The method according to claim 1, 2 or 3, characterized in that: The eyelid boundary includes an upper eyelid boundary and a lower eyelid boundary; The eyelid boundary key points include a corner of the eye key point located at the intersection of the upper eyelid boundary and the lower eyelid boundary, an upper eyelid key point located on the upper eyelid boundary, and a lower eyelid key point located on the lower eyelid boundary; The number of the upper eyelid key points is greater than the number of the lower eyelid key points.

5. The method according to any one of claims 1 to 4, characterized in that The step of determining the eyelid boundary formed by the eyelid boundary key points comprises: From each of the eyelid boundary key points, identify the eye corner key point, the upper eyelid key point and the lower eyelid key point; Taking the eye corner key point as an endpoint, connecting the upper eyelid key points through a first connecting line to obtain an upper eyelid boundary; Taking the eye corner key point as an endpoint, connecting the lower eyelid key points through a second connecting line to obtain a lower eyelid boundary; and An eyelid boundary is determined based on the upper eyelid boundary and the lower eyelid boundary.

6. The method according to any one of claims 1 to 5, characterized in that The step of performing key point prediction on the eye image of the target object to obtain a plurality of iris boundary key points and a plurality of eyelid boundary key points includes: Based on the key point prediction algorithm, key points of the eye image of the target object are predicted to obtain multiple pupil boundary key points, multiple iris outer boundary key points and multiple eyelid boundary key points; According to the iris contour shape condition, contour fitting is performed on each of the iris boundary key points to obtain a predicted iris area, including: Based on the distribution of each of the iris outer boundary key points, according to the iris outer contour shape condition, the iris outer contour is fitted to each of the iris outer boundary key points to obtain a predicted iris outer boundary; and Based on the distribution of each pupil boundary key point and in accordance with the pupil contour shape condition, pupil contour fitting is performed on each pupil boundary key point to obtain a predicted pupil boundary; The predicted iris outer boundary and the predicted pupil boundary are used as iris region boundaries to determine a predicted iris region.

7. The method according to claim 6, characterized in that The shape condition of the iris outer contour is an elliptical contour; the shape condition of the pupil contour is a circular contour; The step of determining the predicted iris region by taking the predicted iris outer boundary and the predicted pupil boundary as iris region boundaries comprises: respectively determining an elliptical area formed by the outer boundary of the predicted iris and a circular area formed by the outer boundary of the predicted iris; and An area in the elliptical area that does not overlap with the circular area is determined as a predicted iris area.

8. The method according to any one of claims 1 to 7, characterized in that The step of performing iris occlusion analysis on the target object based on the relative position relationship between the predicted iris area and the area formed by the eyelid boundary to obtain an iris occlusion analysis result includes: For each pixel point in the predicted iris area, according to the coordinates of each pixel point, a target pixel point in the area formed by the eyelid boundary is screened out; Determining an iris occlusion ratio of the target object based on a ratio of the number of target pixels to the total number of pixels in the predicted iris region; and An iris occlusion analysis is performed based on the iris occlusion ratio and a maximum tolerance ratio threshold of the iris occlusion to obtain an iris occlusion analysis result.

9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: When the iris occlusion analysis result is that the iris occlusion ratio is less than or equal to the maximum tolerance ratio threshold of the iris occlusion, extracting the iris features in the predicted iris area; and Based on the iris features, iris recognition processing is performed on the target object to obtain an iris recognition result.

10. The method according to any one of claims 1 to 8, characterized in that The method further comprises: When the iris occlusion analysis result is that the iris occlusion ratio is greater than the maximum tolerable ratio threshold of iris occlusion, a reminder message for the target object is generated.

11. The method according to claim 10, characterized in that When the iris occlusion analysis result is that the iris occlusion ratio is greater than the maximum tolerance ratio threshold of the iris occlusion, generating a reminder message for the target object includes: When the iris occlusion analysis result is that the iris occlusion ratio is greater than the maximum tolerance ratio threshold of the iris occlusion, determining the type of reminder message based on the current scene of the target object; and Generate a reminder message for the target object according to the reminder message type.

12. An iris occlusion analysis device, characterized in that: The device comprises: A key point prediction module is used to predict key points of the eye image of the target object to obtain multiple iris boundary key points and multiple eyelid boundary key points; A contour fitting module, used to perform contour fitting on each of the iris boundary key points according to the iris contour shape conditions to obtain a predicted iris area; A boundary determination module, used to determine the eyelid boundary formed by each of the eyelid boundary key points; and The occlusion analysis module is used to perform iris occlusion analysis on the target object based on the relative position relationship between the predicted iris area and the area formed by the eyelid boundary to obtain an iris occlusion analysis result.

13. The device according to claim 12, characterized in that The key point prediction module is further used to determine initial key points based on preliminary key point recognition of the eye image of the target object; and determine the eye area in the eye image according to the distribution of the initial key points in the eye image; The eye image is cropped based on the cropping condition that the area ratio of the eye region reaches a set ratio threshold to obtain a target image; key point prediction is performed on the target image based on the key point prediction algorithm to obtain multiple iris boundary key points and multiple eyelid boundary key points.

14. The device according to claim 12 or 13, characterized in that The key point prediction process is implemented by a key point prediction model; the training process of the key point prediction model includes: Sample images of eyes in different occlusion states are obtained, wherein the sample images are marked with iris boundary key points and eyelid boundary key points, and the distribution of the marked iris boundary key points in the sample images meets the iris contour shape conditions; the marked eyelid boundary key points are used to characterize the eyelid boundary in the sample images; an initial deep neural network model is trained based on the sample images until the model training stop conditions are met, so as to obtain a key point prediction model for key point prediction of eye images.

15. The device according to any one of claims 12 to 14, characterized in that The eyelid boundary includes an upper eyelid boundary and a lower eyelid boundary; the eyelid boundary key points include an eye corner key point located at the intersection of the upper eyelid boundary and the lower eyelid boundary, an upper eyelid key point located on the upper eyelid boundary, and a lower eyelid key point located on the lower eyelid boundary; the number of the upper eyelid key points is greater than the number of the lower eyelid key points.

16. The device according to any one of claims 12 to 15, characterized in that The boundary determination module is also used to identify the eye corner key point, the upper eyelid key point and the lower eyelid key point from each of the eyelid boundary key points; using the eye corner key point as the endpoint, connecting each of the upper eyelid key points through a first line to obtain the upper eyelid boundary; using the eye corner key point as the endpoint, connecting each of the lower eyelid key points through a second line to obtain the lower eyelid boundary; and determining the eyelid boundary based on the upper eyelid boundary and the lower eyelid boundary.

17. The device according to any one of claims 12 to 16, characterized in that The key point prediction module is further used to perform key point prediction on the eye image of the target object to obtain a plurality of pupil boundary key points, a plurality of iris outer boundary key points and a plurality of eyelid boundary key points; The contour fitting module is further used to perform iris outer contour fitting on each of the iris outer boundary key points based on the distribution of each of the iris outer boundary key points and according to the iris outer contour shape condition to obtain a predicted iris outer boundary; Based on the distribution of each pupil boundary key point and in accordance with the pupil contour shape condition, pupil contour fitting is performed on each pupil boundary key point to obtain a predicted pupil boundary; the predicted iris outer boundary and the predicted pupil boundary are used as iris area boundaries to determine a predicted iris area.

18. The device according to claim 17, characterized in that The shape condition of the iris outer contour is an elliptical contour; the shape condition of the pupil contour is a circular contour; The contour fitting module is further used to respectively determine the elliptical area formed by the outer boundary of the predicted iris and the circular area formed by the outer boundary of the predicted iris; and determine the area in the elliptical area that does not overlap with the circular area as the predicted iris area.

19. The device according to any one of claims 12 to 18, characterized in that The occlusion analysis module is further used to screen out target pixel points in the area formed by the eyelid boundary for each pixel point in the predicted iris area according to the coordinates of each pixel point; and determine the iris occlusion ratio of the target object based on the ratio of the number of target pixel points to the total number of pixel points in the predicted iris area; An iris occlusion analysis is performed based on the iris occlusion ratio and a maximum tolerance ratio threshold of the iris occlusion to obtain an iris occlusion analysis result.

20. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 11 are implemented.

Images