Eye movement measuring device, eye movement measuring program, and eye movement measuring method

Abstract

Conventional eyeball movement measuring devices have the problem of not being not capable of responding to movements of a subject. The eyeball movement measuring device according to one embodiment has a parameter outputting means (11) that outputs parameters including at least an illuminance instruction value and an image processing parameter; an illumination controlling means (12) that controls the strength of observation light irradiating an eyeball of a subject according to the illuminance instruction value; and an eyeball movement detecting means (13) that detects a pupil of the subject by applying the image processing parameter to an eyeball image acquired by an imaging means and measures the angle of the eyeball on the basis of the position of the detected pupil. The parameter outputting means (11) changes a value included in the parameters according to the three-dimensional position of the face of the subject extracted from a face image acquired by the imaging means.

Description

[Technical Field]

[0001] The present invention relates to an eye movement measuring device, an eye movement measuring program, and Regarding eye movement measurement methods, in particular, eye movement measurement devices and eye movement measurement programs for measuring the eye movement of subjects and This relates to a method for measuring eye movement. [Background technology]

[0002] In recent years, attempts have been made to measure the eyeballs of a subject without contact and to determine the subject's condition or level of alertness from the eyeball movements derived from the measurement results. Accordingly, a technology for measuring eyeball movements without contact has been disclosed in Patent Document 1.

[0003] The control device described in Patent Document 1 includes an acquisition unit that acquires an input image including an eye region, which is the region of the eye part; an estimation unit that estimates the illuminance of the eye part from the acquired input image; and a determination unit that determines the amount of visible light illumination to irradiate the eye part based on an illuminance-size relationship, which is the relationship between illuminance and pupil size, so that the size of the pupil of the eye part satisfies a size condition. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2021 / 044540 Summary of the Invention

[0005] However, the control device described in Patent Document 1 had a problem in that it was not possible to correctly adjust the observation light illuminating the eyeball when the subject's position or orientation changed, making it impossible to perform measurements with high accuracy.

[0006] An eye movement measuring device according to one embodiment includes a parameter output means for outputting parameters including at least an illuminance command value and an image processing parameter, an illumination control means for controlling the intensity of observation light illuminating the eye of a subject in accordance with the illuminance command value, and an eye movement detection means for applying the image processing parameter to an eye image acquired by an imaging means to detect the pupil of the subject and measure the eye angle based on the detected position of the pupil, and the parameter output means changes the value included in the parameter in accordance with the three-dimensional position of the face of the subject extracted from the facial image acquired by the imaging means.

[0007] Eye movement measurement program according to one embodiment M is An eye movement measurement program executed by a calculation means of an eye movement measurement device that measures the eye movement of a subject, the program performing a parameter output process that outputs parameters including at least an illuminance command value and an image processing parameter, an illumination control process that controls the intensity of observation light illuminating the eye of the subject in accordance with the illuminance command value, and an eye movement detection process that applies the image processing parameters to an eye image acquired by an imaging means to detect the pupil of the subject and measure the eye angle based on the position of the detected pupil, and in the parameter output process, the value included in the parameter is changed in accordance with the three-dimensional position of the face of the subject extracted from the face image acquired by the imaging means.

[0008] An eye movement measuring method according to one embodiment is an eye movement measuring method that acquires eye movement by automatic processing by a calculation means of an eye movement measuring device that measures the eye movement of a subject, and performs a parameter output process that outputs parameters including at least an illuminance command value and an image processing parameter; an illumination control process that controls the intensity of observation light illuminating the eye of the subject in accordance with the illuminance command value; and an eye movement detection process that applies the image processing parameters to an eye image acquired by an imaging means to detect the pupil of the subject and measure the eye angle based on the detected position of the pupil, and in the parameter output process, changes the value included in the parameter in accordance with the three-dimensional position of the face of the subject extracted from the face image acquired by the imaging means.

[0009] According to one embodiment, it is possible to measure eye movement with high accuracy even if the subject moves. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a schematic block diagram of an eye movement measuring device according to a first embodiment. [Figure 2] 1 is a block diagram of an eye movement measuring device according to a first embodiment. [Figure 3] FIG. 2 is a diagram illustrating a face image according to the first embodiment. [Figure 4] FIG. 2 is a diagram illustrating an eyeball image according to the first embodiment. [Figure 5] FIG. 2 is a diagram illustrating an example of a lookup table according to the first embodiment. [Figure 6] 5A to 5C are diagrams illustrating differences in pupil detection images depending on whether or not parameter control is performed according to the first embodiment. [Figure 7] FIG. 2 is a block diagram illustrating a first example of an eye movement classification unit according to the first embodiment. [Figure 8] FIG. 4 is a block diagram illustrating a second example of the eye movement classification unit according to the first embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] For clarity of explanation, the following description and drawings have been omitted and simplified as appropriate. Furthermore, each element shown in the drawings as a functional block performing various processes can be configured in hardware with a CPU (Central Processing Unit), memory, and other circuits, and in software with a program loaded into memory, etc. Therefore, those skilled in the art will understand that these functional blocks can be realized in various forms using only hardware, only software, or a combination thereof, and are not limited to any one of these. In addition, the same elements are designated by the same reference numerals in each drawing, and redundant explanations are omitted as necessary.

[0012] The above-described program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0013] Embodiment 1 Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 shows a schematic block diagram of an eye movement measuring device 1 according to the first embodiment. The eye movement measuring device 1 shown in FIG. 1 is realized by a calculation unit 10. Specifically, the eye movement measuring device 1 can be realized by performing processing of each functional block described below using an eye measurement program executed by the calculation unit 10. Note that the eye movement measuring device 1 can also be configured such that the processing performed within the calculation unit 10 is configured as dedicated hardware.

[0014] As shown in FIG. 1, the eye movement measuring device 1 according to the first embodiment includes a parameter output unit 11, an illumination control unit 12, and an eye movement detection unit 13. The parameter output unit 11 outputs parameters including at least an illuminance command value and an image processing parameter. The illumination control unit 12 controls the intensity of observation light illuminating the subject's eye in accordance with the illuminance command value. The eye movement detection unit 13 applies the image processing parameter to an eye image acquired by an imaging means to detect the subject's pupil and measure the eye angle based on the detected pupil position. In the eye movement measuring device 1 according to the first embodiment, the parameter output unit 11 changes the value included in the parameter in accordance with the three-dimensional position of the subject's face extracted from the face image acquired by the imaging means.

[0015] To detect the eye movement of a subject, it is necessary to irradiate the subject's eye with observation light and determine the differences in the reflected light levels from the pupil, iris, and cornea. However, when the position or orientation of the subject's face changes, the relationship between the reflected light levels from the pupil, iris, and cornea changes. Therefore, in order to maintain a constant level of reflected light from each part of the eye, it is necessary to change the intensity of the irradiated light and the threshold applied to the eye image during pupil detection depending on the position, rotation, and orientation of the subject's face.

[0016] Therefore, in the eye movement measuring device 1 according to the first embodiment, the parameter output unit 11 changes the values ​​included in the parameters according to the three-dimensional position of the subject's face extracted from the face image acquired by the imaging means. Specifically, in the eye movement measuring device 1 according to the first embodiment, the parameter output unit 11 changes an illuminance command value that specifies the intensity of the observation light emitted by the lighting device and an image processing parameter (for example, a binarization threshold) that is used when extracting the pupil from the eye image according to the three-dimensional position of the subject's face extracted from the face image. As a result, the eye movement measuring device 1 according to the first embodiment can stably identify the pupil position even in an environment where the position and orientation of the subject's face change, thereby improving the accuracy of eye movement measurement.

[0017] 1 shows a schematic block diagram of the eye movement measuring device 1, but a specific example of the eye movement measuring device 1 includes a camera as an imaging means, a processing block for extracting the three-dimensional position of the subject from the captured image, and a processing block for performing various processes for controlling the camera. Therefore, to explain FIG. 1 more specifically, FIG. 2 shows a block diagram of the eye movement measuring device 1a according to the first embodiment. Below, the eye movement measuring device 1 will be explained in more detail with reference to the eye movement measuring device 1a.

[0018] The eye movement measuring device 1a shown in Figure 2 includes a calculation unit 10a, a first camera 31, and an eyeball photographing device 32. The eyeball photographing device 32 also includes a second camera 33 and an illumination device 34. In the eye movement measuring device 1a shown in Figure 2, specific devices are used as the sensor and the illumination device, and the information processing section is realized by an eyeball movement measurement program executed by the calculation unit 10a. The eyeball photographing device 32 is connected to the second camera 33 and the illumination device 34 by a mechanism that changes the position and orientation of the second camera 33 and the illumination device 34 in conjunction with each other so as to photograph a single eyeball.

[0019] The first camera 31 captures a facial image including the face of the subject. Here, the facial image captured by the first camera 31 will be described. FIG. 3 shows a diagram for explaining a facial image according to the first embodiment. As shown in FIG. 3, the facial image is an image including the face of the subject. In the following description, the horizontal direction of the facial image is the X direction, the vertical direction is the Y direction, the angle at which the face is looking down is the pitch angle θ, and the tilt direction of the face is the roll angle φ.

[0020] The second camera 33 captures an eyeball image including the eyeball of the subject. Here, the eyeball image captured by the second camera 33 will be described. FIG. 4 is a diagram illustrating an eyeball image according to the first embodiment. As shown in FIG. 4, the first camera 31 captures a wide range including the face of the subject, whereas the second camera 33 captures only the vicinity of the eyeball of the subject. Furthermore, the lighting device 34 irradiates observation light mainly onto the vicinity of the eyeball of the subject. In the following description, the depth direction of the face image is the Z direction, and the lateral direction of the face of the subject is the yaw angle ψ.

[0021] 2, the eye movement measuring device 1a according to the first embodiment includes a parameter output unit 11, an illumination control unit 12, an eye movement detection unit 13, a face detection unit 20, a face direction detection unit 21, an eye position detection unit 22, a three-dimensional position information generation unit 23, and a camera control unit 27. The eye movement detection unit 13 also includes a pupil detection unit 24, an eye movement measurement unit 25, and an eye movement classification unit 26.

[0022] The face detection unit 20 detects a face portion from a face image. The face direction detection unit 21 detects the direction of the face detected by the face detection unit 20. Specifically, the face direction detection unit 21 detects the X direction, Y direction, pitch angle θ, and roll angle φ of the face. The eyeball position detection unit 22 generates eyeball coordinate information indicating the position of the eyeball in the image of the face portion cut out by the face detection unit 20. The eyeball position detection unit 22 outputs the face position information and direction information detected by the face direction detection unit 21 together with the eyeball coordinates generated by the eyeball position detection unit 22 to the three-dimensional position information generation unit 23.

[0023] The pupil detection unit 24 generates coordinate information by extracting only the pupil portion from the eyeball image captured by the second camera. At this time, the pupil detection unit 24 binarizes the eyeball image using the image processing parameters output from the parameter output unit 11 and performs image processing such that only the pupil portion becomes approximately circular. The pupil detection unit 24 then outputs pupil coordinates indicating the pupil position, with the center position of the pupil portion being the pupil position, to the eye movement measurement unit 25 and the camera control unit 27. Here, the camera control unit 27 controls the direction of the second camera 33 based on the pupil coordinates obtained from the pupil detection unit 24. The camera control unit 27 also outputs direction information of the second camera 33 to the three-dimensional position information generation unit 23.

[0024] The three-dimensional position information generation unit 23 extracts three-dimensional position information indicating the three-dimensional position of the subject by combining the information received from the eyeball position detection unit 22 and the direction information of the second camera 33 received from the camera control unit 27. More specifically, the information generated by the eyeball position detection unit 22 and the pupil detection unit 24 lacks information on the subject's Z direction. Therefore, the three-dimensional position information generation unit 23 calculates the position of the subject in the Z direction by applying the principle of binocular parallax to the eyeball coordinates identified by the eyeball position detection unit 22 and the direction information of the second camera 33 received from the camera control unit 27. Then, the three-dimensional position information generation unit 23 generates three-dimensional position information of the subject by adding the Z direction information to the information obtained from the eyeball position detection unit 22 and the camera control unit 27.

[0025] The camera control unit 27 obtains information on the Z direction, which is the distance between the second camera 33 and the subject, and information on the orientation of the subject's face (e.g., roll angle φ, pitch angle θ, yaw angle ψ), from the three-dimensional position information generation unit 23. Then, the camera control unit 27 controls the focus of the second camera 33. As described above, the camera control unit 27 controls the direction of the second camera 33 based on the pupil coordinates obtained from the pupil detection unit 24.

[0026] The parameter output unit 11 obtains three-dimensional position information of the face from the three-dimensional position information generation unit 23 and changes the parameters to be output based on the three-dimensional position information. The three-dimensional position information generation unit 23 may calculate the three-dimensional position of the eyeball from the pupil coordinates of the eyeball position detection unit 22 and the direction information of the second camera. In this case, the parameter output unit 11 may change the parameters according to the three-dimensional position of the eyeball. The parameter output unit 11 may be implemented in a first example using a lookup table or in a second example using a parameter calculation formula. Therefore, the first and second examples of the implementation method of the parameter output unit 11 will be described below. Both the first and second examples are examples in which the parameters are changed based on the three-dimensional position information of the face.

[0027] First, a first example of a lookup table of the parameter output unit 11 will be described. FIG. 5 is a diagram illustrating an example of a lookup table according to the first embodiment. As shown in FIG. 5, when the parameter output unit 11 is realized using a lookup table, a table is created in which a combination of X direction, Y direction, and Z direction, which are face position information, and a roll angle φ, pitch angle θ, and yaw angle ψ, which indicate the face orientation, is associated with a binarization threshold value and an illumination intensity E, which are image processing parameters. Then, the parameter output unit 11 selects one entry of the lookup table that matches the received three-dimensional position information (X direction, Y direction, Z direction, roll angle φ, pitch angle θ, and yaw angle ψ) from the received three-dimensional position information. Then, the parameter output unit 11 outputs the binarization threshold value included in the selected entry as an image processing parameter and outputs the illumination intensity E as an illuminance command value.

[0028] Next, a second example of a parameter calculation formula for the parameter output unit 11 will be described. In the second example, a preset parameter calculation formula is provided, and the parameter output unit 11 applies values ​​included in the received three-dimensional position information to this parameter calculation formula to calculate image processing parameters and an illuminance command value. Examples of the parameter calculation formulas are shown in formulas (1) to (3). Formulas (1) and (2) are formulas for calculating the binarization threshold (θa, θb). Formula (3) is a formula for calculating the illumination intensity E. In formulas (1) to (3), the position (x0, y0, z0), angle (φ0, θ0, ψ0), binarization threshold (θa0, θb0), and illumination intensity E0 are reference values ​​set during system calibration. In each formula, k is a preset weighting coefficient. θa=θa0+ka1(x0-x)+ka2(y0-y)+ka3(z0-z) +ka4(φ0-φ)+ka5(θ0-θ)+ka6(ψ0-ψ)...(1) θb=θb0+kb1(x0-x)+kb2(y0-y)+kb3(z0-z) +kb4(φ0-φ)+kb5(θ0-θ)+kb6(ψ0-ψ)...(2) E=E0+ke1(x0-x)+ke2(y0-y)+ke3(z0-z) +ke4(φ0-φ)+ke5(θ0-θ)+ke6(ψ0-ψ)...(3)

[0029] Next, we will explain the pupil detected using parameters controlled based on the three-dimensional position of the subject. FIG. 6 is a diagram illustrating the difference between pupil detection images with and without parameter control according to the first embodiment. As shown in FIG. 6, when parameter control is not performed by the parameter output unit 11, the white portion indicating the pupil position generated from the image captured by the second camera 33 becomes elliptical. On the other hand, when parameter control is performed by the parameter output unit 11, the white portion indicating the pupil position generated from the image captured by the second camera 33 becomes closer to circular. This change in the pupil image occurs because the illuminance command value is changed in accordance with the movement of the subject, thereby making it possible to keep the reflection level of light reflected from the pupil constant regardless of the movement of the subject's face.

[0030] Next, the eye movement measurement unit 25 and eye movement classification unit 26 of the eye movement detection unit 13 will be described in detail. The eye movement measurement unit 25 receives pupil coordinates from the pupil detection unit 24 and calculates an eye angle indicating the angle of the eyeball based on the received pupil coordinates. The eye movement measurement unit 25 also calculates an eye angle change amount from the calculated eye angle. The eye movement classification unit 26 classifies the type of eye movement derived from time-series data of the eye angle change amount calculated by the eye movement measurement unit 25 and the three-dimensional position information of the subject's face calculated by the three-dimensional position information generation unit 23.

[0031] Here, two methods of realizing the eye movement classification unit 26 are possible: rule-based processing (first example) and neural network processing (second example). Therefore, examples of realizing the eye movement classification unit 26 are shown in Figures 7 and 8, and these two realization methods will be described.

[0032] FIG. 7 is a block diagram illustrating a first example of an eye movement classifier according to the first embodiment. In FIG. 7, the first example of the eye movement classifier is denoted by the reference numeral 26a. The eye movement classifier 26a illustrated in FIG. 7 includes a feature extraction unit 40, a feature classification unit 41, and a result output unit 42. The feature extraction unit 40 calculates, as an eye movement, the difference between the eye angle change amount received from the eye movement measurement unit 25 and the three-dimensional position information obtained from the three-dimensional position information generation unit 23. The feature classification unit 41 classifies the eye movements calculated by the feature extraction unit 40 according to a preset classification rule and assigns a label to each eye movement. The result output unit 42 displays the results indicating the degree to which eye movement is included for each label on a display unit (not shown).

[0033] FIG. 8 is a block diagram illustrating a second example of an eye movement classifier according to the first embodiment. In FIG. 8, the second example of the eye movement classifier is denoted by the reference numeral 26b. The eye movement classifier 26b illustrated in FIG. 8 includes a feature classifier 51 and a result output unit 52. The feature classifier 51 includes a pre-trained neural network. By inputting the eye angle change amount received from the eye movement measurement unit 25 and the three-dimensional position information obtained from the three-dimensional position information generation unit 23 into this neural network, the feature classifier 51 classifies the measured eye movement based on the training results, and outputs the measurement results with labels indicating the type of eye movement based on the classification results. The result output unit 52 displays the results indicating the degree of eye movement included for each label on a display unit (not shown).

[0034] As described above, in the eye movement measuring device 1a according to the first embodiment, the parameter output unit 11 changes the illuminance intensity of the lighting device 34 based on the three-dimensional position of the subject, thereby enabling the shape of the pupil to be detected with high accuracy regardless of the position and orientation of the subject. This allows the eye movement measuring device 1a to improve the accuracy of detecting the pupil position and to improve the accuracy of detecting eye movement regardless of the position and orientation of the subject.

[0035] Furthermore, in the eye movement measuring device 1a, the parameter output unit 11 is realized as a lookup table, so that the parameters to be output can be changed without performing arithmetic processing, thereby improving responsiveness to changes in the subject's posture. Furthermore, if the parameter output unit 11 is realized as a parameter calculation formula, it becomes possible to expand the application conditions of the system while reducing the effort required to create a lookup table.

[0036] Furthermore, in the eye movement measuring device 1a according to the first embodiment, the accuracy of identifying the three-dimensional position of the subject can be improved by using the first camera and the second camera. Furthermore, in the eye movement measuring device 1a, the second camera 33 and the lighting device 34 are moved in conjunction with each other, thereby improving the correlation between the angle of incidence of the observation light on the pupil and the eye image captured by the second camera 33.

[0037] Furthermore, in the eye movement measuring device 1a according to the first embodiment, either rule-based processing or neural network processing can be applied to the eye movement classifying unit 26, which makes it possible to increase the versatility of the system.

[0038] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the invention.

[0039] This application claims priority based on Japanese Patent Application No. 2022-7519, filed January 21, 2022, the disclosure of which is incorporated herein by reference in its entirety. [Explanation of symbols]

[0040] 1, 1a Eye movement measuring device 10, 10a Calculation unit 11 Parameter output section 12 Lighting control unit 13 Eye movement detection unit 20 Face detection unit 21 Face direction detection unit 22 Eye position detection unit 23 3D position information generation section 24 Pupil detection unit 25 Eye Movement Measurement Unit 26 Eye movement classification section 27 Camera control unit 31 First Camera 32 Eye photography device 33 Second Camera 34 Lighting equipment 40 Feature extraction unit 41, 51 Feature classification section 42, 52 Result output section

Claims

1. a parameter output means for outputting parameters including at least an illuminance command value and an image processing parameter; an illumination control means for controlling the intensity of observation light illuminating the subject's eyeball in accordance with the illuminance command value; an eye movement detection means for detecting a pupil of the subject by applying the image processing parameters to an eye image acquired by an image capturing means, and measuring an eye angle based on the detected position of the pupil; the parameter output means changes a value included in the parameter in accordance with a three-dimensional position of the face of the subject extracted from the face image acquired by the photographing means; An eye movement measuring device in which the three-dimensional position of the face includes information on the length, width, and depth of the face in the face image, as well as the roll angle, pitch angle, and yaw angle of the face.

2. 2. The eye movement measuring device according to claim 1, wherein the parameter output means has a lookup table that associates the three-dimensional position of the subject's face with values ​​included in the parameters.

3. 2. The eye movement measuring device according to claim 1, wherein the parameter output means determines the value included in the parameter by applying a value indicating the three-dimensional position of the subject's face to a preset parameter calculation formula.

4. a first camera that captures a facial image including the face of the subject; a second camera configured to capture the eye image including the eye of the subject; a three-dimensional coordinate extraction means for calculating three-dimensional position information indicating a three-dimensional position of the face of the subject from the face image and the eyeball image; a camera control means for controlling the direction in which the second camera takes an image and the focus of the second camera using the three-dimensional position information; 2. The eye movement measuring device according to claim 1, further comprising:

5. 5. The eye movement measuring device according to claim 4, wherein the illumination control means controls the orientation of an illumination device that emits the observation light using the three-dimensional position information.

6. 2. The eye movement measuring device according to claim 1, wherein the eye movement detection means further comprises an eye movement classification means for classifying the type of eye movement derived from time series data of the measured eye angle and the three-dimensional position of the subject's face.

7. 7. The eye movement measuring device according to claim 6, wherein the eye movement classification means classifies the type of eye movement by either neural network processing that uses as input time series data of the eye angle and the three-dimensional position of the face of the subject, or rule-based processing that classifies eye movements calculated from the difference between the time series data of the eye angle and the time series data of the three-dimensional position of the face of the subject in accordance with a preset rule.

8. An eye movement measurement program executed by a calculation means of an eye movement measurement device for measuring eye movement of a subject, a parameter output process for outputting parameters including at least an illuminance command value and an image processing parameter; an illumination control process for controlling the intensity of observation light illuminating the eyeball of the subject in accordance with the illuminance command value; applying the image processing parameters to the eyeball image acquired by the photographing means to detect the pupil of the subject, and performing an eyeball movement detection process to measure the eyeball angle based on the detected pupil position; In the parameter output process, a value included in the parameter is changed in accordance with a three-dimensional position of the face of the subject extracted from the face image acquired by the photographing means; An eye movement measuring program in which the three-dimensional position of the face includes information on the length, width, and depth of the face in the face image, as well as the roll angle, pitch angle, and yaw angle of the face.

9. An eye movement measuring method for acquiring eye movement by automatic processing by a calculation means of an eye movement measuring device for measuring eye movement of a subject, comprising: a parameter output process for outputting parameters including at least an illuminance command value and an image processing parameter; an illumination control process for controlling the intensity of observation light illuminating the eyeball of the subject in accordance with the illuminance command value; applying the image processing parameters to the eyeball image acquired by the photographing means to detect the pupil of the subject, and performing an eyeball movement detection process to measure the eyeball angle based on the detected pupil position; In the parameter output process, a value included in the parameter is changed in accordance with a three-dimensional position of the face of the subject extracted from the face image acquired by the photographing means; The eye movement measuring method, wherein the three-dimensional position of the face includes vertical, horizontal, and depth information of the face in the face image, and roll, pitch, and yaw angles of the face.

Images