WO2021012370A1

WO2021012370A1 - Pupil radius detection method and apparatus, computer device and storage medium

Info

Publication number: WO2021012370A1
Application number: PCT/CN2019/106604
Authority: WO
Inventors: 满康瑞
Original assignee: 深圳壹账通智能科技有限公司; 壹帐通金融科技有限公司（新加坡）
Priority date: 2019-07-25
Filing date: 2019-09-19
Publication date: 2021-01-28
Also published as: CN110555875A; SG11202004539QA

Abstract

A pupil radius detection method, comprising: obtaining an image to be measured of the pupil radius, and extracting a region-of-interest image in said image of the pupil radius (S202); performing pixel processing on the region-of-interest image to obtain a pupil region image (S204); extracting a plurality of pupil contours from the pupil region image by means of a boundary tracking algorithm (S206); obtaining the center of the region-of-interest image, a minimum bounding circle set of the plurality of pupil contours and the circle center of each minimum bounding circle in the minimum bounding circle set (S208); and obtaining the distance between the center and each circle center, screening the circle center closest to the center, taking the minimum surrounding circle corresponding to the closest circle center as a target circle, and taking the radius of the target circle as the pupil radius (S210).

Description

Method, device, computer equipment and storage medium for detecting pupil radius

Cross references to related applications

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on July 25, 2019, the application number is 2019106767537, and the application title is "Pupillary Radius Detection Method, Device, Computer Equipment, and Storage Medium". The reference is incorporated in this application.

Technical field

This application relates to a method, device, computer equipment and storage medium for detecting pupil radius.

Background technique

With the development of science and technology, gaze tracking has become more and more widely used in medical, human-computer interaction, aviation and military, face-to-face audits and other fields. Take the loan review face-to-face review as an example. At this stage, in the communication process, the response of the subject under the face-to-face review can be automatically obtained through line-of-sight tracking, thereby assisting in making judgments on their overall qualifications.

Pupil radius detection, as an important part of the gaze tracking technology, plays an important role in the gaze tracking system. The traditional pupil radius detection method considers the geometric characteristics of the pupil, regards the pupil as a circle or an ellipse, and performs fitting by the least square method. However, the inventor realizes that this leads to low accuracy of the obtained pupil radius.

Summary of the invention

According to various embodiments disclosed in the present application, a method, device, computer device, and storage medium for detecting pupil radius are provided.

A method for detecting pupil radius includes:

Acquiring a pupil radius to-be-measured image, and extracting a region of interest image in the pupil-radius-to-be-measured image;

Performing pixel processing on the image of the region of interest to obtain an image of the pupil region;

Extracting multiple pupil contours from the pupil area image through a boundary tracking algorithm;

Acquiring the center of the region of interest image, the smallest enclosing circle set of the multiple pupil contours, and the center of each smallest enclosing circle in the smallest enclosing circle set; and

The distance between the center and the center of each circle is obtained, the center of the circle closest to the center is selected, the smallest enclosing circle corresponding to the nearest circle center is taken as the target circle, and the radius of the target circle is taken as the pupil radius.

A detection device for pupil radius includes:

An image extraction module for acquiring a pupil radius to-be-measured image, and extracting an image of a region of interest in the pupil-radius-to-be-measured image;

A pupil image acquisition module, configured to perform pixel processing on the image of the region of interest to obtain an image of the pupil region;

A pupil contour acquisition module, configured to extract multiple pupil contours from the pupil area image through a boundary tracking algorithm;

A center circle acquisition module, configured to acquire the center of the region of interest image, the smallest enclosing circle set of the multiple pupil contours, and the center of each smallest enclosing circle in the smallest enclosing circle set; and

The pupil radius acquiring module is used to acquire the distance between the center and the center of each circle, select the center of the circle closest to the center, and use the smallest enclosing circle corresponding to the nearest center as the target circle, and use the radius of the target circle as Pupil radius.

A computer device, including a memory and one or more processors, the memory stores computer readable instructions, when the computer readable instructions are executed by the processor, the one or more processors execute The following steps:

One or more non-volatile computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the following steps:

The details of one or more embodiments of the application are set forth in the following drawings and description. Other features and advantages of this application will become apparent from the description, drawings and claims.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

Fig. 1 is an application scene diagram of a pupil radius detection method according to one or more embodiments.

Fig. 2 is a schematic flowchart of a method for detecting pupil radius according to one or more embodiments.

Fig. 3 is a schematic flowchart of the steps of obtaining the minimum enclosing circle set according to one or more embodiments.

Fig. 4 is a schematic flowchart of the steps of obtaining the smallest enclosing circle according to one or more embodiments.

Fig. 5 is a block diagram of an apparatus for detecting pupil radius according to one or more embodiments.

Figure 6 is a block diagram of a computer device according to one or more embodiments.

Detailed ways

In order to make the technical solutions and advantages of the present application clearer, the following further describes the present application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the application, and not used to limit the application.

The pupil radius detection method provided in this application can be applied to the application environment as shown in FIG. 1. The target object wears an HMD102 (Head-mounted Display) with eye tracking function. The eye tracking HMD102 has a built-in eye tracking camera to adjust the wearing position. At the beginning, the eye tracking camera collects the pupil radius to-be-measured image of the target object, and transmits the pupil-radius-to-be-measured image to the control terminal 104 in real time. The control terminal 104 analyzes and processes the pupil radius to-be-measured image, extracts the image of the area of interest from the pupil-radius image to be measured, and then performs pixel processing on the image of interest to obtain the pupil area image, which is extracted from the pupil area image by the boundary tracking algorithm For multiple pupil contours, the center of the minimum enclosing circle of the multiple pupil contours and the distance between the center of the region of interest image and the center of each circle are obtained, and the radius of the minimum enclosing circle corresponding to the center of the center with the closest distance is taken as the pupil radius. The control terminal 104 may be, but is not limited to, various personal computers, notebook computers, smart phones, and tablet computers.

In one of the embodiments, as shown in FIG. 2, a method for detecting pupil radius is provided. Taking the method applied to the control terminal in FIG. 1 as an example for description, the method includes the following steps:

Step 202: Obtain a pupil radius to-be-measured image, and extract a region of interest image in the pupil-radius-to-be-measured image.

The pupil radius to be measured image is collected by the eye tracking camera and sent to the control terminal. The eye tracking camera is an IR-sensitive camera with IR (Infrared Radiation) bandpass filtering function. The camera only allows infrared light to enter the camera and provides infrared illumination. Infrared lighting devices are usually infrared light-emitting diodes, which are used to illuminate the area around the eyes. The pupil is generally located in the central area of the eye image, therefore, the area of interest is specifically an image corresponding to the central area of the eye image output by the eye tracking camera.

Step 204: Perform pixel processing on the image of the region of interest to obtain an image of the pupil region.

In the image captured by IR illumination and IR bandpass filter, the area of the pupil position is most likely to be the darkest area, and the image corresponding to the darkest area is not convenient for subsequent processing. Therefore, the darkest area is converted into the brightest area through bitwise non-processing, and the brightest area is easier to perform subsequent processing than the darkest area.

Performing pixel processing on the image of the region of interest to obtain the image of the pupil region includes: obtaining the pixel values of the image of the region of interest, performing bitwise non-processing on each pixel value, and obtaining the pixel values of the processed image of the region of interest; Among the pixel values of the processed image of the region of interest, the pixel values lower than the preset threshold are set to zero to obtain the pupil region image. By comparing the pixel value of the processed image of the region of interest with a preset threshold, the pupil region and the non-pupil region are divided. When the pixel value corresponding to a certain area image is lower than the preset threshold, it means that the area is a non-pupil area. Setting the pixel value corresponding to the non-pupil region in the region of interest to zero can remove the non-pupil region from the region of interest so that only the pupil region remains in the region of interest.

Step 206: Extract multiple pupil contours from the pupil area image through the boundary tracking algorithm.

In digital binary image processing, boundary tracking extracts a series of coordinate points or chain codes of the boundary contour. The boundary refers to the boundary between a 1-pixel connected domain and a 0-pixel connected domain. For example, to convert a binary image into a boundary description, the information that needs to be extracted is the enclosing relationship between the outer boundary and the hole boundary. There is a one-to-one correspondence between the outer boundary and the 1-connected domain, and between the hole boundary and the 0-connected domain, so that the topology of a given binary image can be determined.

The boundary tracking algorithm can distinguish the enclosing relationship between binary image boundaries. The outer boundary and the hole boundary have a one-to-one correspondence with the connected domain with a pixel value of 1 and the hole with a pixel value of 0, respectively. Through the binary image representation method, some features can be extracted without reconstructing the image. The boundary tracking algorithm can also only track the outermost contour, that is, there is no hole boundary surrounding it outside the outer boundary, which can be used for area counting and topology analysis of binary images.

Step 208: Obtain the center of the image of the region of interest, the smallest enclosing circle set of multiple pupil contours, and the center of each smallest enclosing circle in the smallest enclosing circle set.

The region of interest may specifically be the central region of the eye image. When the central region is a geometric region, the center of the image of the region of interest is the geometric center of the geometric region. Obtaining the center and radius of the smallest enclosing circle, including: obtaining four pixels to determine the smallest enclosing circle, choosing two from the four pixels at will to obtain two sets of different pixel combinations, through two sets of different pixel combinations , Get two straight lines; get the vertical averages of the two straight lines respectively, get the center of the smallest enclosing circle by getting the intersection of the two vertical averages; get the smallest by getting the distance between the center of the circle and any point of the four pixels The radius of the enclosing circle.

Step 210: Obtain the distance between the center and the center of each circle, filter the center of the circle closest to the center, use the smallest enclosing circle corresponding to the nearest circle center as the target circle, and use the radius of the target circle as the pupil radius.

The distance between the center and the center of the circle can be obtained by obtaining the pixel points corresponding to the center and the center of the circle, and then by the distance formula between the two points.

The pupil radius detection method mentioned above extracts the image of the area of interest from the image to be measured with the pupil radius, and then performs pixel processing on the image of interest to obtain the pupil area image, and extracts multiple pupil contours from the pupil area image through the boundary tracking algorithm to obtain multiple The center of the smallest enclosing circle of the pupil contour, and the distance between the center of the image of the region of interest and the center of each circle, the radius of the smallest enclosing circle corresponding to the center of the center is the pupil radius, and the center of the circle is the closest to the center of the region of interest. The way the smallest enclosing circle locates the pupil, the obtained pupil positioning is more accurate, and the accuracy of the obtained pupil radius can be improved.

In one of the embodiments, after extracting the multiple pupil contours from the pupil area image by the boundary tracking algorithm, the method further includes: obtaining the pixel point set of each pupil contour in the multiple pupil contours; The angles are sorted from small to large, and the pixels with the same polar angle are sorted according to the distance from the bottom left pixel in the pixel point set from small to large; the sorted pixels are stored through the structure array, and the sorted pixels are traversed , Remove the non-vertex pixels to obtain the vertex pixel point set; judge the corner of each vertex pixel in the vertex pixel point set, remove the vertex pixels that are not cornered in the preset direction, and obtain the convex hull processed pupil contour ; Obtaining the minimum enclosing circle set of multiple pupil contours includes: obtaining the minimum enclosing circle set of the pupil contour after convex hull processing. Find the pixel at the bottom left among the pixels that make up the pupil outline, and sort the pixels that make up the pupil outline. Sort the polar angles from small to large, and the pixels with the same polar angle are sorted from small to large according to the distance to the bottom left pixel. The outermost pixels of the convex hull are stored in the structure array, and the pixels that are not the vertices of the convex hull are removed through the while loop, because when the convex hull is traversed counterclockwise, each vertex should be turned to the left. Therefore, it can be found in the while loop that when a vertex is not turned to the left, the vertex is removed. The direction of the turning angle can be judged to the left or right according to the cross product. Convex hull processing helps to eliminate the distortion caused by the reflection of infrared LEDs in the image.

In one of the embodiments, as shown in FIG. 3, obtaining the minimum enclosing circle set of multiple pupil contours includes: step 302, obtaining the minimum enclosing circle and the radius of the minimum enclosing circle respectively corresponding to the multiple pupil contours; step 304, The smallest enclosing circle whose radius is greater than the preset value in the smallest enclosing circle is removed, and the smallest enclosing circle set of the pupil contour is obtained. By excluding the smallest enclosing circle whose radius exceeds the preset value, the possibility that the radius is too large to belong to the pupil can be reduced. The preset value range can be calculated by the resolution of the image, by detecting several possible circles, for example, the iris or the shell of the eye tracking device against the face.

In one of the embodiments, as shown in FIG. 4, obtaining the minimum enclosing circle corresponding to multiple pupil contours respectively includes: step 402, obtaining the leftmost, rightmost, and uppermost sides of each pupil contour in the multiple pupil contours respectively And the four pixels at the bottom, obtain the smallest circle surrounding the four pixels according to the four pixels; step 404, traverse all the pixels of the pupil contour, when there is no pixel located outside the boundary of the smallest circle When the pixel points of, the smallest circle is the smallest enclosing circle of the pupil contour.

In one of the embodiments, the method for detecting the pupil radius further includes: when there are pixel points outside the boundary of the smallest circle among all the pixels, obtaining the smallest enclosing circle whose smallest circle is not the pupil contour; from outside the boundary of the smallest circle Among the pixels in, filter the pixels farthest from the center of the smallest circle, and arrange and combine the filtered pixels with any three of the leftmost, rightmost, uppermost and lowermost four pixels; obtain the permutation and combination For the last four pixels, the candidate minimum circle surrounding the four pixels is obtained according to the four pixels after permutation and combination; when the pixels that are not selected in the permutation and combination are not outside the boundary of the candidate minimum circle, traverse the pupil contour For other pixels, when there is no pixel located outside the boundary of the candidate minimum circle among other pixels, the candidate minimum circle is obtained as the minimum enclosing circle of the pupil contour.

The minimum enclosing circle of the pupil contour can be obtained by the following steps: (1) Traverse all the pixels of the pupil contour, find the four pixels on the leftmost, rightmost, uppermost, and lowermost sides, and find the leftmost and rightmost enclosing pixels , The smallest circle of the four pixels at the top and bottom, including the center and radius of the smallest circle. (2) Then traverse all the pixels of the pupil contour to determine whether there are some pixels outside the boundary of the minimum circle. If there are no pixels outside the boundary of the smallest circle, then the smallest circle is the smallest enclosing circle of the pupil contour. If there are some points outside the boundary of the smallest circle, then the smallest circle is not the smallest enclosing circle of the pupil contour. (3) When the minimum circle obtained is not the minimum enclosing circle of the pupil contour, the pixel point farthest from the center of the minimum circle among the points outside the boundary of the minimum circle is selected, and the pixel point farthest from the center of the minimum circle is selected. Arrange and combine any three points among the four points on the leftmost, right, top, and bottom of the pupil contour found before, and determine the smallest circle surrounding the four points according to the four points after rearrangement and combination. That is, the smallest circle 1 surrounding the farthest point, the leftmost point, the rightmost point, and the uppermost point is obtained, the smallest circle 2 surrounding the farthest point, the leftmost point, the rightmost point, and the lowermost point is obtained. The smallest circle 3 for the left point, the uppermost point, and the uppermost point, and the smallest circle 4 surrounding the farthest point, the rightmost point, the uppermost point, and the lowermost point. (4) When the lowest point is not outside the boundary of the minimum circle 1, traverse all points of the pupil contour to determine whether there are some points outside the boundary of the minimum circle 1. If there are no points outside the boundary of the smallest circle 1, then the smallest circle 1 is the smallest enclosing circle of the pupil contour. If there are some points outside the boundary of the smallest circle, then the smallest circle 1 is not the smallest enclosing circle of the candidate pupil contour. (5) When the smallest circle 1 is not the smallest enclosing circle of the pupil contour, the point that is farthest from the center of the smallest circle 1 among the points outside the boundary of the smallest circle 1 is selected, and the point farthest from the center of the smallest circle 1 is Determine any three points among the four points of the minimum circle 1, and repeat steps (3) and (4) until all points of the pupil contour are traversed, and there are no points outside the boundary of the obtained minimum circle. The minimum circle obtained is the minimum enclosing circle of the pupil contour.

In one of the embodiments, taking the loan face-to-face review as an example, the control terminal can pre-store the historical pupil radius data of the face-to-face subject when answering a specific question, for example, use the average value of the historical pupil radius data as the face-to-face subject Reference value of pupil radius. During the actual loan interview process, the interview subject wears an HMD with eye tracking function. The eye tracking HMD has a built-in eye tracking camera. At the beginning of the interview, the eye tracking camera collects the real-time pupil radius of the interview subject to be measured And transmit the real-time pupil radius to-be-measured image to the control terminal in real time. The control terminal analyzes and processes the real-time pupil radius to-be-measured image, extracts the image of the area of interest from the real-time pupil-radius image to be measured, and then performs pixel processing on the image of interest to obtain the pupil area image, which is obtained from the pupil area image through the boundary tracking algorithm Extract multiple pupil contours, obtain the center of the minimum enclosing circle of multiple pupil contours, and the distance between the center of the region of interest image and the center of each circle, and use the radius of the smallest enclosing circle corresponding to the center of the center with the closest distance as the real-time pupil radius. Then the real-time pupil radius is compared with the benchmark value of the pupil radius of the face-to-face interview subject, and the lie detection result of the face-to-face subject when answering questions is obtained. For example, when the real-time pupil radius when answering a specific question is greater than the corresponding pupil radius reference value, it is determined that the interview subject is lying when answering the question.

It should be understood that although the various steps in the flowcharts of FIGS. 2-4 are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless specifically stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least some of the steps in Figures 2-4 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. These sub-steps or stages The execution order of is not necessarily performed sequentially, but may be performed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

In one of the embodiments, as shown in FIG. 5, a device for detecting pupil radius is provided, including: an image extraction module 502, a pupil image acquisition module 504, a pupil contour acquisition module 506, a central circle acquisition module 508, and a pupil radius Obtain the module 510. The image extraction module is used to obtain the pupil radius to be measured, and extract the image of the region of interest in the pupil radius to be measured; the pupil image acquisition module is used to perform pixel processing on the image of the region of interest to obtain the pupil area image; the pupil contour acquisition module, It is used to extract multiple pupil contours from the pupil area image through the boundary tracking algorithm; the center circle center acquisition module is used to obtain the center of the region of interest image, the minimum enclosing circle set of multiple pupil contours, and each minimum encircle in the minimum enclosing circle set The center of the circle; the pupil radius obtaining module is used to obtain the distance between the center and the center of each circle, filter the center of the circle closest to the center, and use the smallest enclosing circle corresponding to the nearest circle center as the target circle, and the radius of the target circle as the pupil radius.

In one of the embodiments, the pupil image acquisition module is also used to acquire the pixel values of the image of the region of interest, perform bitwise non-processing on the pixel values, and acquire the pixel values of the processed image of the region of interest; Among the pixel values of the image of the region of interest, the pixel values lower than the preset threshold are set to zero to obtain an image of the pupil area.

In one of the embodiments, the pupil image acquisition module further includes a convex hull processing module for acquiring the pixel point set of each pupil contour in the plurality of pupil contours; the pixel points in the pixel point set are from small to large according to the polar angle. Sort, sort the pixels with the same polar angle according to the distance from the bottom leftmost pixel in the pixel point set from small to large; store the sorted pixels through the structure array, traverse the sorted pixels, and go Except for the pixels of the vertex, the vertex pixel point set is obtained; the corner of each vertex pixel in the vertex pixel point set is judged, and the vertex pixels that are not cornered in the preset direction are removed to obtain the convex hull processed pupil contour; The circle center acquisition module is used to acquire the minimum enclosing circle set of the pupil contour after convex hull processing.

In one of the embodiments, the central circle acquisition module is also used to acquire the minimum enclosing circle and the radius of the minimum enclosing circle respectively corresponding to multiple pupil contours; remove the smallest enclosing circle whose radius is greater than the preset value in the minimum enclosing circle to obtain the pupil contour The smallest enclosing circle set.

In one of the embodiments, the center circle acquisition module is also used to separately acquire the leftmost, rightmost, uppermost, and lowermost four pixels of each pupil contour in the plurality of pupil contours, and obtain the encircling according to the four pixels. The smallest circle of the four pixels; traverse all the pixels of the pupil contour, and when there is no pixel outside the boundary of the smallest circle among all the pixels, the smallest circle is the smallest enclosing circle of the pupil contour.

In one of the embodiments, the central circle acquisition module is also used to obtain the smallest enclosing circle whose smallest circle is not the pupil contour when there are pixels outside the boundary of the smallest circle among all the pixels; Among the pixels, filter the pixels farthest from the center of the smallest circle, and arrange and combine the filtered pixels with any three of the leftmost, rightmost, uppermost and lowermost four pixels; after obtaining the permutation and combination According to the four pixel points after permutation and combination, the candidate minimum circle surrounding the four pixels is obtained; when the pixel points not selected in the permutation and combination are not outside the boundary of the candidate minimum circle, traverse other pupil contours For pixel points, when there is no pixel point outside the boundary of the candidate minimum circle among other pixels, the candidate minimum circle is obtained as the minimum enclosing circle of the pupil contour.

In one of the embodiments, the detection device for pupil radius further includes a center radius module, which is used to obtain four pixels that determine the minimum enclosing circle, and select two of the four pixels at will to obtain two sets of different pixel point combinations , Through the combination of two sets of different pixels, two straight lines are obtained; the vertical average line of the two straight lines is obtained separately, and the center of the smallest enclosing circle is obtained by obtaining the intersection of the two vertical average lines; by obtaining the center and four The distance of any point in the pixel is the radius of the smallest enclosing circle.

For the specific definition of the pupil radius detection device, please refer to the above definition of the pupil radius detection method, which will not be repeated here. Each module in the above-mentioned pupil radius detection device can be implemented in whole or in part by software, hardware, and a combination thereof. The foregoing modules may be embedded in the form of hardware or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the foregoing modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 6. The computer equipment includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide calculation 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, computer readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile storage medium. The database of the computer equipment is used to store data such as the center of the smallest enclosing circle and the radius of the smallest enclosing circle. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer readable instructions are executed by the processor to realize a pupil radius detection method.

Those skilled in the art can understand that the structure shown in FIG. 6 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.

A computer device, including a memory and one or more processors, in which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the steps of the pupil radius detection method provided in any embodiment of the present application are implemented .

One or more non-volatile computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors implement any one of the embodiments of the present application. Provide the steps of the pupil radius detection method.

A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing relevant hardware through computer-readable instructions, which can be stored in a non-volatile computer. In a readable storage medium, when the computer-readable instructions are executed, they may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction between the combinations of these technical features, they should It is considered as the range described in this specification.

The above-mentioned embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can be made, and these all fall within the protection scope of this application. Therefore, the scope of protection of the patent of this application shall be subject to the appended claims.

Claims

A method for detecting pupil radius, including:

Acquiring a pupil radius to-be-measured image, and extracting a region of interest image in the pupil-radius-to-be-measured image;

Performing pixel processing on the image of the region of interest to obtain an image of the pupil region;

Extracting multiple pupil contours from the pupil area image through a boundary tracking algorithm;

Acquiring the center of the region of interest image, the smallest enclosing circle set of the multiple pupil contours, and the center of each smallest enclosing circle in the smallest enclosing circle set; and

The distance between the center and the center of each circle is obtained, the center of the circle closest to the center is selected, the smallest enclosing circle corresponding to the nearest circle center is taken as the target circle, and the radius of the target circle is taken as the pupil radius.
The method according to claim 1, wherein the performing pixel processing on the image of the region of interest to obtain an image of the pupil region comprises:

Acquiring each pixel value of the image of the region of interest, performing bitwise non-processing on each pixel value, and acquiring each pixel value of the processed region of interest image; and

The pixel values that are lower than the preset threshold among the pixel values of the processed image of the region of interest are set to zero to obtain an image of the pupil region.
The method according to claim 1, wherein, after extracting a plurality of pupil contours from the pupil region image through a boundary tracking algorithm, the method further comprises:

Acquiring a pixel point set of each pupil contour in the plurality of pupil contours;

Sort the pixels in the pixel point set according to the polar angle from small to large, and sort the pixels with the same polar angle according to the distance to the bottom leftmost pixel in the pixel point set from small to large;

Store the sorted pixels through the structure array, traverse the sorted pixels, remove non-vertex pixels, and obtain a vertex pixel point set; and

Perform a corner judgment on each vertex pixel in the vertex pixel point set, remove vertex pixels that are not cornered in a preset direction, and obtain a pupil contour after convex hull processing;

The acquiring the minimum enclosing circle set of the multiple pupil contours includes:

Obtain the minimum enclosing circle set of the pupil contour after the convex hull processing.
The method according to claim 1, wherein the obtaining the minimum enclosing circle set of the multiple pupil contours comprises:

Acquiring the minimum enclosing circle and the radius of the minimum enclosing circle respectively corresponding to the multiple pupil contours; and

The smallest enclosing circle whose radius is greater than the preset value in the smallest enclosing circle is removed to obtain the smallest enclosing circle set of the pupil contour.
The method according to claim 4, wherein the obtaining the minimum enclosing circles corresponding to the multiple pupil contours respectively comprises:

Obtaining the leftmost, rightmost, uppermost and lowermost four pixel points of each pupil contour in the plurality of pupil contours respectively, and obtaining the smallest circle surrounding the four pixels according to the four pixel points; and

Traverse all the pixels of the pupil contour, and when there is no pixel located outside the boundary of the minimum circle among all the pixels, the minimum circle is obtained as the minimum enclosing circle of the pupil contour.
The method according to claim 5, further comprising:

When there is a pixel point outside the boundary of the minimum circle among all the pixels, obtaining the minimum circle that is not the minimum enclosing circle of the pupil contour;

From the pixels located outside the boundary of the smallest circle, filter the pixels farthest from the center of the smallest circle, and compare the filtered pixels with the four pixels of the leftmost, rightmost, uppermost and lowermost edges Any three of the points are permuted and combined;

Obtaining four pixel points after permutation and combination, and obtaining the candidate smallest circle surrounding the four pixels according to the four pixel points after permutation and combination; and

When the pixel points that are not selected into the permutation and combination are not outside the boundary of the candidate minimum circle, traverse other pixels of the pupil contour, when there is no pixel outside the boundary of the candidate minimum circle In the case of pixel points, the candidate minimum circle is obtained as the minimum enclosing circle of the pupil contour.
The method according to claim 1, further comprising:

Obtain four pixel points that determine the minimum enclosing circle, randomly select two from the four pixels to obtain two sets of different pixel point combinations, and obtain two straight lines through the two sets of different pixel point combinations;

Obtaining the vertical average lines of the two straight lines respectively, and obtaining the center of the smallest enclosing circle by obtaining the intersection of the two vertical average lines; and

The radius of the minimum enclosing circle is obtained by calculating the distance between the center of the circle and any one of the four pixel points.
A detection device for pupil radius, including:

An image extraction module for acquiring a pupil radius to-be-measured image, and extracting an image of a region of interest in the pupil-radius-to-be-measured image;

A pupil image acquisition module, configured to perform pixel processing on the image of the region of interest to obtain an image of the pupil region;

A pupil contour acquisition module, configured to extract multiple pupil contours from the pupil area image through a boundary tracking algorithm;

A center circle acquisition module, configured to acquire the center of the region of interest image, the smallest enclosing circle set of the multiple pupil contours, and the center of each smallest enclosing circle in the smallest enclosing circle set; and

The pupil radius acquiring module is used to acquire the distance between the center and the center of each circle, select the center of the circle closest to the center, and use the smallest enclosing circle corresponding to the nearest center as the target circle, and use the radius of the target circle as Pupil radius.
The device according to claim 8, wherein the pupil image acquisition module is further configured to acquire each pixel value of the image of the region of interest, perform bitwise non-processing on each pixel value, and acquire the processed Each pixel value of the image of the region of interest; and

The pixel values that are lower than the preset threshold among the pixel values of the processed image of the region of interest are set to zero to obtain an image of the pupil region.
A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the one or more Each processor performs the following steps:

Acquiring a pupil radius to-be-measured image, and extracting a region of interest image in the pupil-radius-to-be-measured image;

Performing pixel processing on the image of the region of interest to obtain an image of the pupil region;

Extracting multiple pupil contours from the pupil area image through a boundary tracking algorithm;

Acquiring the center of the region of interest image, the smallest enclosing circle set of the multiple pupil contours, and the center of each smallest enclosing circle in the smallest enclosing circle set; and

The distance between the center and the center of each circle is obtained, the center of the circle closest to the center is selected, the smallest enclosing circle corresponding to the nearest circle center is taken as the target circle, and the radius of the target circle is taken as the pupil radius.
The computer device according to claim 10, wherein the processor further executes the following steps when executing the computer-readable instruction:

Acquiring each pixel value of the image of the region of interest, performing bitwise non-processing on each pixel value, and acquiring each pixel value of the processed region of interest image; and

The pixel values that are lower than the preset threshold among the pixel values of the processed image of the region of interest are set to zero to obtain an image of the pupil region.
The computer device according to claim 10, wherein the processor further executes the following steps when executing the computer-readable instruction:

Acquiring a pixel point set of each pupil contour in the plurality of pupil contours;

Sort the pixels in the pixel point set according to the polar angle from small to large, and sort the pixels with the same polar angle according to the distance to the bottom leftmost pixel in the pixel point set from small to large;

Store the sorted pixels through a structure array, traverse the sorted pixels, remove non-vertex pixels, and obtain a vertex pixel point set;

Perform a corner judgment on each vertex pixel in the vertex pixel point set, remove vertex pixels that are not cornered in a preset direction, and obtain a pupil contour after convex hull processing; and

Obtain the minimum enclosing circle set of the pupil contour after the convex hull processing.
The computer device according to claim 10, wherein the processor further executes the following steps when executing the computer-readable instruction:

Acquiring the minimum enclosing circle and the radius of the minimum enclosing circle respectively corresponding to the multiple pupil contours; and

The smallest enclosing circle whose radius is greater than the preset value in the smallest enclosing circle is removed to obtain the smallest enclosing circle set of the pupil contour.
The computer device according to claim 13, wherein the processor further executes the following steps when executing the computer-readable instruction:

Obtaining the leftmost, rightmost, uppermost and lowermost four pixel points of each pupil contour in the plurality of pupil contours respectively, and obtaining the smallest circle surrounding the four pixels according to the four pixel points; and

Traverse all the pixels of the pupil contour, and when there is no pixel located outside the boundary of the minimum circle among all the pixels, the minimum circle is obtained as the minimum enclosing circle of the pupil contour.
The computer device according to claim 14, wherein the processor further executes the following steps when executing the computer-readable instruction:

When there is a pixel point outside the boundary of the minimum circle among all the pixels, obtaining the minimum circle that is not the minimum enclosing circle of the pupil contour;

From the pixels located outside the boundary of the smallest circle, filter the pixels farthest from the center of the smallest circle, and compare the filtered pixels with the four pixels of the leftmost, rightmost, uppermost and lowermost edges Any three of the points are permuted and combined;

Obtaining four pixel points after permutation and combination, and obtaining the candidate smallest circle surrounding the four pixels according to the four pixel points after permutation and combination; and

When the pixel points that are not selected into the permutation and combination are not outside the boundary of the candidate minimum circle, traverse other pixels of the pupil contour, when there is no pixel outside the boundary of the candidate minimum circle In the case of pixel points, the candidate minimum circle is obtained as the minimum enclosing circle of the pupil contour.
One or more non-volatile computer-readable storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the following steps:

Acquiring a pupil radius to-be-measured image, and extracting a region of interest image in the pupil-radius-to-be-measured image;

Performing pixel processing on the image of the region of interest to obtain an image of the pupil region;

Extracting multiple pupil contours from the pupil area image through a boundary tracking algorithm;

Acquiring the center of the region of interest image, the smallest enclosing circle set of the multiple pupil contours, and the center of each smallest enclosing circle in the smallest enclosing circle set; and

The distance between the center and the center of each circle is obtained, the center of the circle closest to the center is selected, the smallest enclosing circle corresponding to the nearest circle center is taken as the target circle, and the radius of the target circle is taken as the pupil radius.
The storage medium according to claim 16, wherein the following steps are further executed when the computer-readable instructions are executed by the processor:

Acquiring each pixel value of the image of the region of interest, performing bitwise non-processing on each pixel value, and acquiring each pixel value of the processed region of interest image; and

The pixel values that are lower than the preset threshold among the pixel values of the processed image of the region of interest are set to zero to obtain an image of the pupil region.
The storage medium according to claim 16, wherein the following steps are further executed when the computer-readable instructions are executed by the processor:

Acquiring a pixel point set of each pupil contour in the plurality of pupil contours;

Sort the pixels in the pixel point set according to the polar angle from small to large, and sort the pixels with the same polar angle according to the distance to the bottom leftmost pixel in the pixel point set from small to large;

Store the sorted pixels through a structure array, traverse the sorted pixels, remove non-vertex pixels, and obtain a vertex pixel point set;

Perform a corner judgment on each vertex pixel in the vertex pixel point set, remove vertex pixels that are not cornered in a preset direction, and obtain a pupil contour after convex hull processing; and

Obtain the minimum enclosing circle set of the pupil contour after the convex hull processing.
The storage medium according to claim 16, wherein the following steps are further executed when the computer-readable instructions are executed by the processor:

Acquiring the minimum enclosing circle and the radius of the minimum enclosing circle respectively corresponding to the multiple pupil contours; and

The smallest enclosing circle whose radius is greater than the preset value in the smallest enclosing circle is removed to obtain the smallest enclosing circle set of the pupil contour.
The storage medium according to claim 19, wherein the following steps are further executed when the computer-readable instructions are executed by the processor:

Obtaining the leftmost, rightmost, uppermost and lowermost four pixel points of each pupil contour in the plurality of pupil contours respectively, and obtaining the smallest circle surrounding the four pixels according to the four pixel points; and

Traverse all the pixels of the pupil contour, and when there is no pixel located outside the boundary of the minimum circle among all the pixels, the minimum circle is obtained as the minimum enclosing circle of the pupil contour.