KR101094766B1 - Apparatus and mehtod for tracking eye - Google Patents

Abstract

The present invention relates to a gaze position tracking device and method, and more particularly to a gaze position tracking device and method for tracking the gaze position of the user by correcting the face movement according to the distance between the illumination light included in the eye image.
According to an aspect of the present invention, an apparatus for tracking a gaze direction includes a receiver configured to receive an eye image of a user including an illumination reflection light captured by a camera; A detector configured to detect a pupil position from the received eye image using a predetermined method, and detect a coordinate of the illumination reflected light and a center coordinate of the pupil using the detected pupil position; And calculating a face motion correction value of the user using the detected coordinates of the reflected light, and calculating a gaze position of the user using the coordinates of the movement area of the pupil and the coordinates of the monitor stared by the user. Contains wealth.

Description

Gaze position tracking device and method {APPARATUS AND MEHTOD FOR TRACKING EYE}

The present invention relates to a gaze position tracking device and method, and more particularly to a gaze position tracking device and method for tracking the gaze position of the user by correcting the face movement according to the distance between the illumination light included in the eye image.

As digital technology develops today, a technology for analyzing image information and dividing it into specific regions or portions is being developed. Among the analysis techniques, the face recognition technique is a technology that is applied not only to a digital camera but also to a device that performs a security technique, and is being researched and developed in various ways in various ways.

In addition, active research is being conducted on a system for authenticating an individual using biological characteristics such as genetic traits, fingerprints, voices, veins, facial features, and eye irises. Among them, the iris recognition field is expected to be used most in the future due to the advantages of high recognition rate, impossibility of counterfeiting, pattern data with a large amount of data, and no change factor.

The iris (Iris) refers to the area between the pupil and the white area, which is comb-like ligaments, red fibers, cilia-like protrusions, vascular forms, ring-shaped tissues, and corona-shaped ligaments surrounding the pupil. Because of its unique characteristics such as color, spot color, etc., the iris can be used to identify individuals.

In order to reduce the amount of data computation, a preprocessing process for finding the eye position is performed prior to recognizing the iris, which can be done in various ways. Conventionally, in order to find the position of the eye, there is a method of using image information according to the shape of the eye or using reflected noise represented by the pupil.

Here, the reflected noise is a noise component that appears when light is reflected by the pupil and has regular characteristics in size and pattern. In this way, when the position of the eye is found, the iris recognition system is precisely driven so that the subject's eye and the lens of the camera are optically matched, and the iris is precisely photographed to process the iris recognition process.

However, in case of finding the position of the eye by using the shape of the eye, the shape of the eye varies depending on factors such as makeup and artificial eyebrows, or the shape of the eye varies according to the characteristics of the individual, or due to wearing contact lenses or glasses. Since there are many obstacles such as the shape of the eye can be perceived differently, it is technically difficult to detect the image object called the eye uniformly through image processing.

In addition, various noise components, including reflection noise, appear in the image of the eyeball area, and these noise components cover part of the eye so that the shape of the eye cannot be recognized. Sometimes it can't be.

Accordingly, an object of the present invention is to provide a gaze position tracking device and method.

It is also an object of the present invention to provide a gaze position tracking device and method for tracking a gaze position of a user by correcting a face movement according to a distance between illumination lights included in an eye image.

In order to solve the above objects, an apparatus for tracking gaze position according to an exemplary embodiment of the present invention may include: a receiver configured to receive an eye image of a user including illumination reflected light captured by a camera; A detector configured to detect a pupil position from the received eye image using a predetermined method, and detect a coordinate of the illumination reflected light and a center coordinate of the pupil using the detected pupil position; Calculating a distance between the reflected light by using the detected coordinates of the reflected light, and correcting the center coordinates of the pupil by applying a predetermined weight and the distance between the reflected light to the center coordinates of the extracted pupil; A calculator; And a second calculator configured to define a movement area of the pupil using the corrected pupil center coordinates, and calculate a gaze position of the user by using a relationship between a coordinate system between the movement area of the pupil and a monitor stared by the user. do.

In accordance with another aspect of the present invention, a method for tracking a gaze position includes: receiving an eye image of a user including an illumination reflection light captured by a camera; Detecting a pupil position from the received eye image using a predetermined method, and detecting a coordinate of the illumination reflection light and a center coordinate of the pupil using the detected pupil position; Calculating a distance between the illumination reflected light using the detected coordinates of the illumination reflected light, and correcting the center coordinates of the pupil by applying a predetermined weight and the distance between the illumination reflected light to the center coordinates of the extracted pupil; And

Defining a moving area of the pupil using the corrected pupil center coordinates, and calculating a gaze position of the user using a relationship between a coordinate system between the moving area of the pupil and a monitor stared by the user.

The present invention can track a user's gaze position by correcting a face movement according to a distance between illumination lights included in an eye image. In addition, the present invention increases the convenience of the user by tracking the gaze position of the user and utilizing it in various fields.

1 is a view schematically showing the structure of a gaze tracking device according to an embodiment of the present invention;
2 is a diagram illustrating an eye image acquisition camera of a gaze tracking device according to an exemplary embodiment of the present invention;
3 is a view showing a monitor equipped with an infrared LED of the gaze tracking device according to an embodiment of the present invention,
4 is a process of detecting the initial pupil position by the detection unit 102 of the eye tracking apparatus according to an embodiment of the present invention using a circular detection method, and extracts the final pupil position through a binarization process, a labeling process, and a morphology process. Figure,
5 is a view showing an eye image received by the receiver 101 of the eye tracking apparatus according to the embodiment of the present invention;
6 is a view showing the length between the reflected light reflected in the eye image received by the receiver 101 of the gaze tracking device according to an embodiment of the present invention,
7 is a view showing a geometric transformation method for performing calibration according to an embodiment of the present invention;
8 is a view illustrating a gaze tracking system according to an exemplary embodiment of the present invention;
9 is a diagram schematically illustrating a gaze tracking process according to an exemplary embodiment of the present invention.

In describing the present invention, when it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted. Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Let's first look at examples of how eye tracking is used. The gaze tracking method is divided into Skin Electrodes based method, Contact Lens based method, Head Mounted Display attachment based method, and Remote Pan & Tilting device based method. have.

The skin electrode-based method is a method of measuring an electric potential difference between a retina and a cornea by attaching an electrode around a user's eye, and calculating a gaze position based on the measured electric potential difference. The skin electrode-based method can grasp the gaze position of both eyes, has the advantage of low cost and easy to use. However, the skin electrode based method is less accurate because the movement in the horizontal and vertical direction is limited.

The contact lens-based method is a method of calculating a gaze position by attaching a non-slip lens to the cornea and attaching a magnetic field coil or mirror to the cornea. The contact lens based method can accurately calculate the gaze position. However, it is inconvenient to use, the blinking of the eye is not free, and the calculation range is limited.

The head mounted display attachment based method calculates the gaze position using a small camera mounted under the headband or helmet. The head mounted display attachment based method can calculate the gaze position regardless of the user's head movement. However, because the camera is tilted below the user's eye level, the camera is not sensitive to the vertical movement of the eye, so it is applied only to the head mounted display.

The remote pan & tilt device-based method calculates the gaze position by installing a pan & tilt camera and light around the monitor. Remote pan-and-tilt device-based methods have the advantages of accurate and fast gaze position calculations and ease of application, but require more than two expensive stereo camera devices and complex algorithms to track head movements. Requires complex calibration of the liver. Next, the internal structure of the eye tracking apparatus according to the exemplary embodiment of the present invention will be described in more detail with reference to FIG. 1.

1 is a view schematically showing the structure of a gaze tracking device according to an exemplary embodiment of the present invention.

The eye tracking apparatus may be applied to various application fields such as a video player of various types, for example, an Internet Protocol Television (IPTV) system, a TV, a computer, a game machine, and the like. Next, an IPTV system will be described as an example for convenience of explanation.

delete

Here, the user wears glasses equipped with an image photographing device for capturing an eye image, stares at a monitor including two infrared LEDs, and the eye image of the user at predetermined time intervals to detect a user's face movement. It will be described on the assumption that photographing and transmitting to the IPTV system by wire or wireless, such as Bluetooth, infrared.

In addition, the image capturing apparatus for eye image capturing includes not only a camera but also other apparatuses capable of capturing images, which will be described as a camera for convenience of description. The camera is attached to glasses, goggles helmet-type device, or other support that can be fixed to take an image of the user's eyes. In addition, the device for illuminating the light reflected light included in the photographed eye image is composed of a halogen (Halogen), xenon lamp (incandescent lamp), incandescent lamp, etc. as well as the infrared LED to perform the function of illuminating the infrared light to the user's eyes. .

Referring to FIG. 1, the eye tracking apparatus includes a receiver 101, a detector 102, a calculator 103, and a controller 104. The calculator 103 includes a face motion calculator 113 and a gaze position calculator 123. The receiver 101 receives an eye image photographed from a camera at predetermined time intervals.

The eye image includes illumination reflected light illuminated from an infrared light emitting diode (LED). Next, the structure of the camera and the infrared LED will be described in more detail with reference to FIGS. 2 and 3.

2 is an exemplary view of glasses equipped with an eye image acquisition camera 201 according to an embodiment of the present invention, Figure 3 is a monitor of the infrared LED (301, 302) is mounted according to an embodiment of the present invention It is an illustration.

2 and 3, a user wears glasses equipped with an eye image acquisition camera 201 as shown in FIG. 2 and stares at a monitor equipped with infrared LEDs 301 and 302 as shown in FIG. 3. The eye image acquisition camera 201 is installed at a lower right eye of the user to take an eye image.

In this case, the infrared LEDs 301 and 302 mounted on the monitor of FIG. 3 may illuminate infrared rays in a user's eyes, thereby capturing facial motion and capturing an eye image in which a boundary between a pupil and an iris is divided. Then, the infrared cut filter attached to the lens of the camera is removed, and infrared transmission, for example, a visible light cut filter is attached so that only an object irradiated by infrared light can be acquired as an image.

In addition, by attaching a high-learning lens instead of the lens of the camera, it is possible to obtain an eye image including a pupil of a size suitable for eye tracking within a range of the user's field of view. Here, the eye image acquisition camera is attached to glasses, goggles helmet-type device, or other support that can be fixed to capture the user's eye image.

In addition, the device for illuminating the light reflected light included in the photographed eye image is composed of a halogen (Halogen), xenon lamp (incandescent lamp), incandescent lamp, etc. as well as the infrared LED performs a function to illuminate the infrared light to the user's eyes. .

Here, the infrared light is used to correct the gaze position error generated by the movement of the user's face, it is possible to calculate the error according to the movement of the user's face by installing two or more infrared lights on the screen.

The shape of the pupil included in the eye image has an irregular shape in order to simplify the shape of a circle, and can be observed in the form of an ellipse according to the position of the pupil around the camera position. In addition, when the reflected light of the illumination is located at the boundary of the pupil, the center position of the pupil cannot be accurately extracted. Next, the process of determining the pupil position in the eye image received by the detector 102 from the receiver 101 will be described in more detail with reference to FIG. 4.

4 is a process of detecting the initial pupil position by the detection unit 102 of the eye tracking apparatus according to an embodiment of the present invention using a circular detection method, and extracts the final pupil position through a binarization process, a labeling process, and a morphology process. Figure is shown.

Referring to FIG. 4, the detector 102 moves the circular detection template including the inner circle 401a and the outer circle 401b to the pupil area 401c by using a circular detection method (401). The pupil area 402 is determined by detecting a portion where the sum of the gray level differences between the inner circle 402a and the outer circle 401b of the circular detection template is the largest. That is, while changing the radius of the inner circle and the outer circle of the circular detection template and the center position of the circle, the difference between the gray level at the sample position around the center circle based on the center position and the sample position around the outer circle is obtained, and all the sample positions are obtained. By summing the gray level differences in, the center position and radius when the sum of gray level differences is largest is determined as the primary pupil center and radius.

Then, the detector 102 performs local binarization 403 around the pupil area. Here, the binarization method is a method of making a pixel value of an image 0 or 255 in order to obtain information of a desired object, such as a position, a size, and a shape, in an image.

Binarization is divided into global binarization and local binarization. The global binarization method is a method of performing binarization using one threshold for all pixels of an image. The local binarization method divides an image into several zones and performs binarization using different threshold values for each zone.

The detector 102 forms an area of a square shape 403a spaced apart by a predetermined distance from the pupil area, and makes a pixel of an image included in the area 255, for example, a black color 403. The detector 102 performs a morphology operation 404 to obtain the center of gravity of the dark region of the binarized region.

As described above, the detection unit 102 performs a local binarization 403 together with a circular detection algorithm to accurately obtain the center point of the pupil, and performs a morphology calculation to obtain the center of gravity of the dark area among the binarized areas (404). In addition, the dark part of the binarized area may be determined as the pupil area, so that the center of gravity 405 of the dark area may be determined as the substantial center point 406 of the user pupil.

The detector 102 detects an illumination reflection light coordinate and a pupil center coordinate by using the pupil center point. The detector 102 transmits the detected illumination reflected light coordinates to the face motion calculator 113, and transmits the detected pupil center coordinates to the gaze position calculator 123.

The face motion calculator 113 receives the illumination reflection light coordinates from the detection unit 102 and calculates the distance between the illumination reflection light using the received coordinates of the illumination reflection light. Here, the detected pupil center coordinates may be corrected by using distances between the illumination reflection lights calculated using the illumination reflection light of the eye image received at predetermined time intervals.

When the user uses a video player such as an IPTV, a computer, or a game machine, the face motion calculator 113 receives an eye image at predetermined time intervals and does not stare at the fixed position. The detected pupil center coordinates are corrected using the distances between the illumination reflections calculated using the illumination reflections.

More specifically, the face motion calculating unit 113 is closer to the screen of the user when the distance of the illumination formed in the user's pupil is closer to the screen, and when the distance of the illumination formed in the user's pupil is narrower the user's face and the screen The distance from the first gaze position obtained by using the distance is multiplied by a distance between the constant weight and the reflected light to correct the detected pupil center coordinates.

Then, the process of calculating the face motion correction value of the user according to the illumination reflection light distance using the following Equation 1 will be described in more detail.

는 조명 반사광 사이의 길이를 나타낸다. 그리면 여기서, 도 5 및 도 6를 참조하여, 상기 조명 반사광 및 조명 반사광 사이의 길이를 설명하기로 한다.Referring to Equation 1, X and Y represent X and Y axes, w _x represents a weight of the pupil moved to the X axis, and w _y represents a weight of the pupil moved to the X axis. And g _x And g _y represent the actual gaze positions of the pupils on the X and Y axes, respectively. And,

Represents the length between the illumination reflected light. 5 and 6, the length between the illumination reflection light and the illumination reflection light will be described.

5 is a view illustrating an eye image received by the receiver 101 of the gaze tracking device according to an exemplary embodiment of the present invention, and FIG. 6 is a view of the receiver 101 of the gaze tracking apparatus according to an exemplary embodiment of the present invention. FIG. 7 illustrates the lengths between the reflected light and the light included in the eye image.

5 and 6, the receiver 101 receives an eye image of FIG. 5 taken from a camera, and the eye image of FIG. 5 is an illumination reflection light 501 illuminated from an infrared light emitting diode (LED). , 502), including eye images. The detector 102 searches for the final pupil position in the eye image, and detects the illumination reflected light coordinates and the pupil center coordinates using the final pupil position.

를 계산하고, 상기 조명 반사광 거리에 따라 사용자의 얼굴 움직임 보정 값을 계산한다.In addition, the face motion calculator 113 uses the coordinates of the illumination reflection light 501 and 502 to determine the distance 503 between the illumination reflection light, for example.

Calculate the user's face motion correction value according to the illumination reflection light distance.

The face motion calculator 113 transmits the calculated face motion correction value to the gaze position calculator 123. The gaze position calculator 123 calculates an eye gaze position coordinate of the user by using the face motion correction value received from the face motion calculator 113 and the pupil center coordinates received from the detector 102.

That is, the gaze position calculator 123 defines a moving area of the pupil through a user calibration process that gazes at four points on the screen, and uses the geometric transform to determine the relationship between the moving area of the pupil and the screen coordinate system. Calculate the line of sight based on your location.

The transform function is at least one of linear interpolation, geometric or complex ratio transform function. Next, the geometric transformation method for performing calibration according to an embodiment of the present invention will be described in more detail with reference to FIG. 7.

7 is a diagram illustrating a geometric transformation method for performing calibration according to an embodiment of the present invention.

Referring to FIG. 7, the detection unit 102 shows an eye image when a user wearing glasses equipped with an eye image acquisition camera stares at the upper left, upper right, lower right and lower left portions of the monitor of FIG. 3. After receiving sequentially, the detector 102 calculates the pupil center coordinates through the process of FIG. 4, the gaze position calculator 123 uses the geometric transformation function of Equation 2 below. The coordinates of the actual plane S ₂ corresponding to the pupil center coordinates detected at 102 may be calculated.

First, the gaze position calculation unit 123 is a coordinate of the pupil center when a user wearing glasses equipped with an eye image acquisition camera gazes at the upper left, upper right, lower right and lower left of the monitor of FIG. 3, respectively. Define the moving region (S ₁ ) of the user pupil using.

The coordinates of the movement area S ₁ of the user pupil are upper left coordinates (X ₁ , Y ₁ ), upper right coordinates (X ₂ , Y ₂ ), lower left coordinates (X ₄ , Y ₄ ), and lower right coordinates ( X ₃ , Y ₃ ). The gaze position calculator 123 uses coordinates of the movement area S ₁ of the user pupil and coordinates of an actual plane S ₂ corresponding to the coordinates of the movement area S ₁ of each pupil. For example, the upper left coordinates (X ₁ , Y ₁ ) ', the upper right coordinates (X ₂ , Y ₂ )', the lower left coordinates (X ₄ , Y ₄ ) ', and the lower right coordinates (X ₃ , Y ₃ )' Calculate.

Here, the coordinates of the plane S ₂ represent the coordinates of the monitor stared by the user. Then, when a user wearing glasses equipped with an eye image acquisition camera stares at an arbitrary position of the monitor of FIG. 3, referring to Equation 2, a process of calculating a monitor plane position corresponding to the center of the pupil of the user is calculated. It will be described in more detail.

Referring to the <Equation 2>, S ₁ will display the coordinates of the moving region (S ₁₎ of the pupil in a matrix, S ₂ will display the coordinates of the actual plane (S ₂₎ to the matrix. T is a matrix of geometric transformation functions. The gaze position calculating unit 123 calculates the coordinates of the actual plane (S ₂₎ corresponding to the coordinates of the moving region of each pupil by calculating the matrix and geometric transformation function matrix of the coordinates of the moving region (S ₁₎ of the pupil . The gaze position calculator 123 calculates the actual gaze position of the user by using Equation 3 below.

Referring to Equation 3, G is a matrix representing the actual gaze position of the user, and W is a matrix representing the location of the pupil extracted when the user gazes. T is a matrix of geometric transformation functions.

That is, the gaze position calculation unit 123 calculates the monitor plane position corresponding to the center of the user pupil when the user gazes at an arbitrary position of the monitor using Equation 2, and calculates Equation 3 below. To calculate the actual gaze position of the user, eg, the gaze position of the user.

The gaze position calculator 123 calculates the gaze position of the user's final interest using the face motion correction value received from the face motion calculator 113. The calculated final gaze position of interest is transmitted to the controller 104 by wire or wirelessly.

The controller 104 receives a user's final gaze position from the calculator 103 at predetermined time intervals. Although not illustrated in FIG. 1, the controller 104 may include a timer. If it is determined that the user's final gaze position received from the calculator 103 is constant for a predetermined time using a timer, the controller 104 activates a menu or the like that exists at the user's last gaze position.

By applying the gaze tracking device according to the embodiment of the present invention to the IPTV system as described above, even a disabled person who cannot use his or her hand can control a function provided by the IPTV system without the operation of a device such as a remote controller. In addition, an IPTV system can provide a service to a user without including a button and a dial for executing a function such as two-way video conferencing, purchase of a document, and the like on the remote controller.

In addition, by applying the gaze tracking device to a computer, it is possible to execute the software required by the user without the operation of the keyboard, mouse and the like. By applying the gaze tracking device to a game machine or the like, the gaze of the user can be tracked without manipulating the joystick to start and stop the game.

delete

8 is a diagram illustrating a simulation screen of a gaze tracking system according to an exemplary embodiment of the present invention. Next, the eye tracking process according to the exemplary embodiment of the present invention will be described in more detail with reference to FIG. 9.

delete

9 is a diagram schematically illustrating a gaze tracking process according to an exemplary embodiment of the present invention.

Referring to FIG. 9, in operation 900, the eye tracking apparatus receives an eye image photographed from a camera, and detects a pupil position using an illumination reflection light included in the eye image. The gaze tracking device detects an illumination reflection light position and a pupil center coordinate by using the pupil position detected in operation 900 in operation 901.

More specifically, the eye tracking apparatus extracts an initial pupil position using a circular detection method in step 901 and extracts a final pupil position through a binarization process, a labeling process, and a morphology process based on the initial pupil position. Then, the illumination reflected light coordinates and the pupil center coordinates are detected using the final pupil position.

In operation 902, the gaze tracking device calculates a distance between the illumination reflection light using the illumination reflection light, and calculates a face motion correction value of the user using the calculated distance between the illumination reflection light. In operation 903, the gaze tracking device calculates a final gaze position coordinate of the user using the detected pupil center coordinates and the corrected face motion correction value of the user.

In operation 904, the gaze tracking device transmits the coordinates of the final gaze position of the user to the system, and activates a menu when the user gazes at a certain place.

Meanwhile, in the detailed description of the present invention, specific embodiments of an IPTV system, a computer, a game machine, etc. have been described, but various modifications are possible without departing from the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined not only by the scope of the following claims, but also by the equivalents of the claims.

delete

101: receiver
102: detector
103: calculation unit
104: control unit
201: Camera for snow video shooting
301 and 302: Infrared LEDs

Claims (15)

In the eye position tracking device,
A receiver configured to receive an eye image of a user including illumination reflected light captured by a camera;
A detector for detecting a center position of the pupil from the received eye image by using a predetermined method and detecting a coordinate of the illumination reflection light and a center coordinate of the pupil using the detected center position of the pupil;
The distance between the illumination reflection light is calculated using the detected coordinates of the illumination reflection light, and the center coordinates of the pupil is applied by applying the weight between the movement of the pupil and the distance between the illumination reflection light to the detected center coordinates of the pupil. A first calculating unit to correct; And
Define the pupil's movement area coordinates according to user calibration using the corrected pupil's center coordinates, and calculate the gaze position of the user using the relationship between the pupil's movement area coordinates and the coordinate system between the monitor stared by the user. Eye tracking device comprising a second calculation unit.
The method of claim 1,
And a controller for activating a menu corresponding to the gaze position of the user when the calculated gaze position of the user is located at one location for a predetermined time.
delete delete The method of claim 1, wherein the detection unit,
Performing local binarization around the detected pupil area, obtaining a center of gravity of a dark area of the binarized area through a morphology operation, and determining the center of gravity of the obtained dark area as the pupil center position.
The method of claim 1, wherein the second calculation unit,
An eye gaze tracking device, characterized in that a movement area coordinate of the pupil is defined using the center coordinates of the pupil detected when the pupil is located at the upper left, upper right, lower left and lower right.
The method of claim 1, wherein the second calculation unit,
And calculating coordinates of the monitor by mapping the coordinates of the movement area of the pupil to a monitor stared by the user by using at least one of linear interpolation, geometrical, and complex ratio conversion functions. delete In the gaze position tracking method,
Receiving an eye image of a user including illumination reflected light captured by a camera;
Detecting a center position of the pupil from the received eye image using a predetermined method, and detecting a coordinate of the illumination reflection light and a center coordinate of the pupil using the detected center position of the pupil;
The distance between the illumination reflection light is calculated using the detected coordinates of the illumination reflection light, and the center coordinates of the pupil is applied by applying the weight between the movement of the pupil and the distance between the illumination reflection light to the detected center coordinates of the pupil. Correcting;
Define the pupil's movement area coordinates according to user calibration using the corrected pupil's center coordinates, and calculate the gaze position of the user using the relationship between the pupil's movement area coordinates and the coordinate system between the monitor stared by the user. Eye position tracking method characterized in that it comprises a step.
delete delete The method of claim 9,
Detecting the coordinates of the illumination reflected light and the center coordinates of the pupil,
Detecting the pupil area using the sum of the gray level difference between the inner circle and the outer circle of the circular pupil template;
Performing local binarization around the detected pupil region, obtaining a center of gravity of the dark region of the binarized region through a morphology operation, and determining the center of gravity of the obtained dark region as the pupil center position;
Detecting the coordinates of the reflected light and the center coordinates of the pupil using the pupil center position.
delete delete delete

Images