TW201533609A - Method for pupil localization based on a corresponding position of auxiliary light, system and computer product thereof - Google Patents

Abstract

A method for pupil localization based on a corresponding position of auxiliary light, system and computer product thereof are provided. The method comprises: irradiating a eyeball with a plurality of light sources to form a plurality of reflex points on the eyeball; defining a plurality of distance value from the center of the pupil to each of the reflex points; defining a plurality of angle between a base line of the pupil center and each of vector of reflex points, wherein each of the vector of reflex points is from the center of the pupil to each of the reflex points; and transforming the resulting data into a first position on an output unit.

Description

Pupil positioning method based on auxiliary light relative position, its system and its computer program production Product

The invention relates to a pupil positioning method, a system thereof and a computer program thereof A product, especially a pupil positioning method based on the relative position of the auxiliary light, its system, and its computer program product.

Eye tracking technology is commonly used to control computers. It can be used as an aid to communicate with the outside world through a computer or as a tool for psychological research. In addition, eye tracking technology is also widely used in various fields, such as neuroscience, psychology, industrial engineering, human factors engineering, marketing advertising, computer science and so on.

This technique refers to tracking the movement of the eyeball and getting the coordinates of the eye position or Move the trajectory and generate some preset control commands to the computer. Therefore, this technology must first accurately detect the movement of the eyeball, and then another key point must be able to accurately convert the data needed to generate control commands from the computer, such as mapping the eye position to the cursor position on the computer display. Otherwise it will result in a wrong control command.

At present, Eye tracking technology is in contact with the human eye. Divided into contact and non-contact, contact human eye tracking technology can be divided into search coil method and electro-oculogram method. Non-contact human eye tracking technology is mainly based on visual recognition (Vision based), which can be divided into heads. Head-mount or Free-head.

Search for coil method in contact human eye tracking technology (Search The coil) allows the user to wear a soft lens with an induction coil. When the user rotates the eyeball to drive the lens, the induction coil generates an induced electromotive force due to the change of the magnetic flux. The magnitude of the electromotive force represents the angle of deflection of the eyeball, but the disadvantage of this method It is susceptible to the eye condition of the user, such as secretions from the eye, and the soft lens is a two-layer structure that affects the user's vision; as for the electro-oculogram (EOG) method, it is attached around the eye. The plurality of electrodes are used to detect the difference between the voltages of the eyeballs and the left and right angles. The disadvantage is that the skin resistance of the electrodes attached to the electrodes is easily unstable due to keratin secretion, and only Recording the giant turn of the eyeball and not being able to record smaller angle changes.

In the head-mounted human eye tracking technology, the user must wear a Glasses with small cameras, because the relative distance between the eyes and the camera is fixed, so that the judgment is not accurate due to the deviation of the face or the relative distance of the eyes, so the lens must be fixed to the head when the user uses it. By this, the relative position of the small camera and the eye is fixed, which is not only inconvenient or comfortable for the user.

Head-free human eye tracking technology, with foreign screens and doubles Eye trackers of CCD cameras, and more famous in China, are related researches of Lin Yusheng and others. However, the current head-free human eye tracking technology system is known. The use of more complex calculations, and head-free human eye tracking technology must overcome the problem of error caused by the movement of the user's head. In addition, the eye tracker of the dual CCD camera can accurately locate the index, but the cost is very expensive, and two CCD cameras are required. In addition, a light source is used to illuminate the eyeball of the user to form a light spot, and the relative position of the light spot and the pupil is transmitted, and the pre-established database is compared to calculate the gaze point of the user's pupil on the screen. s position.

Regardless of the human eye tracking method used, in general, because each One user's eyes are different, so the first time you use the eye tracker, you need to make corrections; the common correction method is to let the user watch the four corners of the screen or the top, bottom, left and right edges, and the detected eyeball coordinates. In order to correct the points, these correction points are regarded as correct and mapped to the screen, in order to accurately obtain the displacement ratio of the pupil center and the gaze point; however, the correction procedure may cause inconvenience to the user.

In order to satisfy the above needs, the disclosure of the present invention provides the following embodiments.

One aspect of the present invention provides a pupil positioning method based on a relative position of a plurality of light sources to position a user's eyeball to view an output unit, comprising: (a) illuminating a plurality of light sources on the eyeball Forming a plurality of reflective spots on the eyeball; (b) obtaining an eye image including the pupil of the eyeball and the plurality of the reflective points by using a photographing unit; (c) positioning the eye image according to an operation unit a pupil center point and a plurality of positions of the reflection point; (d) defining a plurality of spot vectors by the distance from the pupil center point to the plurality of the reflection points a group; and (e) converting the first group to a first location on the output unit.

Further, wherein the plurality of the light sources used in the step (a) are disposed on Two light sources at the end of the diagonal of the output unit, the two light sources illuminate the eyeball to form corresponding two reflective points.

Further, wherein the plurality of the light sources used in the step (a) are The four apex positions of the output unit or the four side lengths of the output unit are arranged such that the four light sources illuminate the eyeball to form corresponding four reflective points.

Further, wherein the photographing unit of the step (b) is through the search Find the center points of the two nostrils in the facial image; calculate the spacing between the center points of the two nostrils and determine the coordinates of the points together; calculate a coordinate point coordinate according to the spacing and the coordinates of the starting point; according to the coordinates of the reference point A rectangular frame is defined, and the eye image is taken out from the open face image along the rectangular frame.

Further, wherein step (d) comprises a horizontal axis according to the pupil or The vertical axis is used as the reference line segment, and an angle value is defined in conjunction with the spot vector.

Further, wherein the operation unit and the storage list in the step (e) The element is connected, and the storage unit includes a plurality of angle-distance distribution maps equal to the number of the plurality of light sources, thereby converting the first group into the plurality of angle-distance distribution maps to be converted into the first position.

Further, wherein the plurality of angle-distance profiles are transmitted through a training module in the computing unit, the output unit is pre-divided into a plurality of groups of regions, and only one of the regions is displayed at a time. The training module performs the following steps: When a group of areas is displayed for the user to watch, the image analysis module is controlled to perform positioning and control of the vector processing module to obtain distance-angle data of each group of regions.

Further, wherein the step (c) is transmitted through one of the operation units The image analysis module executes, and the step (d) is performed by a vector processing module in the operation unit, and the step (e) is performed by a coordinate conversion module in the operation unit.

Another aspect of the present invention provides a relative position of a plurality of light sources The basic pupil positioning system comprises: a plurality of light sources, the emitted light beam illuminates a user's eye to form a corresponding plurality of reflective points; a photographing unit captures the user's eye image; and an arithmetic unit, Positioning a pupil center point and a plurality of the reflection points on the eye image; wherein the operation unit defines a plurality of spot vectors according to the distance from the pupil center point to the plurality of the reflection points, and converts the plurality of spots The spot vector is the first position on an output unit.

Further, wherein the computing unit is based on an image analysis module The horizontal axis or the vertical axis of the center point of the pupil is positioned as a reference line segment, and a plurality of angle values are defined by a plurality of the spot vectors.

Further, the pupil positioning system further includes the operation list The element is connected to one of the storage units, and the storage unit includes a plurality of angle-distance distribution maps equal to the number of the plurality of light sources.

Further, the pupil positioning system further comprises an output unit, the phase Adjacent to the photographing unit, and the output unit displays an index corresponding to the pupil gaze position.

Further, wherein the plurality of the light sources are disposed in the output unit pair An end point of the corner line for emitting light onto the eye to form two corresponding reflecting points.

Further, wherein the plurality of the light sources are disposed on the output list The four apex positions of the element or the four peripheral side midpoints of the output unit are used to emit light onto the eye to form corresponding four reflective points.

Another aspect of the present invention provides a non-transient state for positioning a pupil A non-transitory computer program product, when the computer is loaded into the computer program product and executed, the pupil positioning method based on the relative position of the plurality of light sources according to the present invention can be completed.

In summary, the pupil positioning method based on the relative position of the auxiliary light, The system and its computer program products can use the relative positional relationship between the pupil and the plurality of reflective points to calculate the position of the pupil. Therefore, the embodiment of the invention can accurately detect the position of the pupil, thereby achieving accurate eye tracking, and achieving multiple applications. Moreover, in some embodiments of the present invention, the effect of no correction can be achieved by using a database.

5‧‧‧ punctuation

6‧‧‧ original image

10‧‧‧瞳孔定位系统

40‧‧‧Users

41‧‧‧ pupil center point

42a‧‧‧Reflecting point

42b‧‧‧Reflecting point

42c‧‧‧reflection point

42d‧‧‧Reflecting point

42e‧‧‧Reflecting point

42f‧‧‧reflection point

43a‧‧‧ spot vector

43b‧‧‧ spot vector

43c‧‧‧ spot vector

43d‧‧‧ spot vector

43e‧‧‧ spot vector

43f‧‧‧ spot vector

61‧‧‧Face images

62‧‧‧ Nose center point

100‧‧‧Multiple lighting units

200‧‧‧ arithmetic unit

202‧‧‧ training module

204‧‧‧Image Analysis Module

206‧‧‧Vector Processing Module

208‧‧‧Coordinate conversion module

210‧‧‧Eye Search Module

212‧‧‧Eye Status Judgment Module

300‧‧‧Photographic unit

400‧‧‧ storage unit

401‧‧‧Eye images

420‧‧‧ eyeballs

450‧‧‧ eye white

500‧‧‧Output unit

501‧‧‧ indicators

a~g‧‧‧step

D‧‧‧ spacing

BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 is a block diagram showing an embodiment of a pupil positioning system based on the relative position of two auxiliary lights of the present invention.

Figure 2 is a schematic illustration of the embodiment of Figure 1.

FIG. 3 is a flow chart of obtaining an eye image by the arithmetic unit through the image captured by the photographing unit.

Fig. 4 is a view showing an image taken by a photographing unit in the embodiment of the pupil positioning system based on the relative position of the two auxiliary lights of the present invention.

Figure 5a shows a schematic view of the eye image taken from the image, and Figure 5b shows a schematic diagram of the vector module calculating the eye parameters.

Figure 6 is a diagram showing the angle-distance distribution coordinates of an embodiment of the present invention.

Figure 7 shows a schematic diagram of an embodiment of a pupil positioning system based on the relative position of four auxiliary lights.

Fig. 8a is a schematic view showing an eye image taken out by an embodiment of a pupil positioning system based on the relative position of the four auxiliary lights of the present invention, and Fig. 8b is a schematic view showing the calculation of eye parameters by the vector module.

The foregoing and other objects, features, and advantages of the invention are set forth in the <RTIgt; Before the present invention is described in detail, it is noted that in the following description, similar elements are denoted by the same reference numerals.

Referring to FIG. 1 and FIG. 2 together, FIG. 1 is a block diagram showing a pupil positioning system 10 based on the relative positions of a plurality of light sources in an embodiment of the present invention, which can be used to The line of sight is switched to the position of the indicator on the screen, and Fig. 2 is a schematic view of the embodiment of Fig. 1. As shown in FIG. 1 and FIG. 2, the pupil positioning system 10 can include a plurality of lighting units 100, an arithmetic unit 200, a photographing unit 300, a storage unit 400, and an output unit 500. Transport The calculation unit 200 includes a training module 202, an image analysis module 204, a vector processing module 206, and a standard conversion module 208. In addition, the calculation unit 200 further includes an eye search module 210 and an eye state determination module. 212.

The plurality of illumination units 100 can be an infrared source, a visible light source, Or any one that can project the light source on the eyeball of the user, and the light source reflects the light source, thereby causing a reflective point on the eyeball of the user. Preferably, the illumination unit 100 can be an infrared light source, thereby avoiding the use of the light source. The operation is uncomfortable. The embodiment of the plurality of lighting units 100 herein will be exemplified by two lighting units 100 and four lighting units 100 and will be described in detail later.

In this embodiment, the operation unit 200 and the storage unit 400 can be Together, they constitute a computer or processor, such as a personal computer, workstation, host computer, or other type of computer or processor, and are not limited in scope. In the embodiment, the computing unit 200 is coupled to the storage unit 400.

The photographing unit 300 is used to photograph the face of the user to generate a plurality of sheets The continuous image; the photographing unit 300 may be any camera having a charge coupled device (CCD) lens, a complementary metal oxide semiconductor transistor (CMOS) lens, or an infrared lens, or may be The image capturing device for obtaining depth information is, for example, a depth camera or a stereo camera; the photographing unit 300 may be a lens having a rotatably adjustable direction and an angle to adjust the lens to look up to the user's face. status. For example, the lens is oriented toward the user's face at an angle of 30 degrees of elevation. Thereby, the nose in each image captured by the photographing unit 300 The holes are clearly displayed, which means that the nostril recognition of each facial image will be greatly enhanced to facilitate the execution of the nostril search program described later. In addition, the photographing unit 300 can further have an illumination component, and the built-in detector of the photographing unit 300 can perform fill light when determining that the light is insufficient to ensure the sharpness of the captured facial image. In other embodiments, the photographing unit 300 is connected through a physical line such as a universal serial bus (USB), or through a wired network, or wireless, such as Bluetooth or Wireless Fidelity (WiFi). The transmission interface transmits signals to the arithmetic unit 200 and the storage unit 400. The embodiment of the present invention is not limited to the type of the photographing unit 300.

The storage unit 400 can be any type of fixed or movable random A random access memory (RAM), a read-only memory (ROM), a flash memory or the like or a combination of the above elements. The storage unit 400 can also be constructed from one or more accessible non-volatile memory components. Specifically, it can be a hard disk, a memory card, or an integrated circuit or a firmware. In one or more embodiments, the storage unit 400 can be used to record images and statistical information including the pupils and feature points obtained by the photographing unit 300.

The output unit 500 can be a display screen, a screen, a speaker, or any The instructions can be converted into devices that are typically bio-receivable for processing information. In the preferred embodiment, the output unit 500 is a screen to match the indicator of the display to the pupil's gaze position.

2 auxiliary position relative position based pupil positioning system

Please continue to refer to "Figure 2", as can be seen from Figure 2, the lighting unit 100 It is disposed at the diagonal end of the output unit 500. When the user 40 eyes gaze at the output unit 500, the two illumination units 100 located at the ends of the diagonal line emit light to the user's eyes, forming two reflective spots on the eyeball, and the photographing unit 300 is used for photographing. The user's face is used to generate multiple continuous images, and the pupil of the eyeball and the eye images of the two reflective points are obtained.

Further, the photographing unit 300 is coupled to the arithmetic unit 200, and further The way to get an eye image. Referring to FIG. 3 together, a flowchart for obtaining an eye image by the operation unit 200 through the image captured by the imaging unit 300, and FIG. 4, is a schematic diagram of the image captured by the imaging unit 300. When the computing unit 300 activates the eye search module 210, the eye search module 210 performs the following steps a through g.

In step a, the original image 6 is received. In step b, the face image 61 is taken out from the original image 6. In step c, the two nostril center points 62 in the facial image 61 are found. In step d, the distance D between the center points of the two nostrils is calculated and the starting point coordinates A(x ₁ , y ₁ ) are determined. In step e, the reference point coordinates B(x ₂ , y ₂ ) are calculated according to the spacing D and the starting point coordinates A(x ₁ , y ₁ ). In step f, a rectangular frame R _{1 is} defined according to the reference point coordinate B(x ₂ , y ₂ ). Step g, ₁ eye image taken from the face image along the rectangular frame R 401; _{wherein, x 2 = x 1 + k} 1 × D, y 2 = y 1 + k 2 × D, k 1 = 1.6 ~ 1.8, and k ₂ = 1.6~1.8. The acquired eye image 401 is as shown in "Fig. 5a".

Further, the eye state determination module 212 in the operation unit 200 The step of determining the state of the eye may be performed to search for a certain part of the eye in the eye image 401, such as the upper and lower eyelids or the pupil, and generate an eye state data according to the detection result of the part, for example, “0” Representing the eyes, closing the eyes with "1" Wait. In the present invention, if the eye state data is generated by the degree of curvature of the upper eyelid, the upper eyelid may be an arc extending in the horizontal direction in the eye-opening state; but in the closed eye state, the upper eyelid is substantially a straight line extending in the horizontal direction. Therefore, the focal length of the parabola can be calculated using the graph obtained along the upper eyelid, and the different focal lengths represent the upper eyelids of different degrees of curvature, and correspondingly the eye state is obtained.

Then, the eye image 401 is obtained and the state thereof can be further determined. Thereafter, the pupil center point at the center of the eyeball 420 (here, the iris in the human eye configuration, which is the non-white area of the eye, such as black, blue, or brown, and the eyeball 420, hereinafter referred to as the eyeball 420) may be utilized. The relative positional relationship between the 41 and the two reflecting points 42a and 42b is calculated by vector processing and coordinate conversion to calculate the position of the pupil.

In detail, the image analysis module 204 in the computing unit 200 is first The eye image 401 performs a binarization process (also referred to as grayscale segmentation) to adjust a portion of the image whose grayscale is greater than the preset grayscale value to black; and the portion of the image whose grayscale is smaller than the preset grayscale value. It is adjusted to white, whereby the pupil center point 41 is clearly found by the eyeball 420; similarly, the two light reflecting points 42a, 42b can be found by adjusting the preset gray value.

Next, the vector processing module 206 in the computing unit 200 respectively According to the pupil center point 41 and the two reflecting points 42a, 42b, two distance values and two angles are calculated. In detail, referring to FIG. 5b, the vector processing module 206 defines the first distance value and the second distance from the pupil center point 41 to the reflection point 42a or the distance from the pupil center point 41 to the reflection point 42b. Distance value and by the 瞳 The hole center point 41 defines a reference line (in this embodiment, a vertical axis) that defines two angles θ1 and θ2 in cooperation with the two spot vectors 43a and 43b, wherein the spot vectors 43a and 43b are respectively from the pupil center point 41 to The vectors of the reflection points 42a, 42b, in turn, constitute a first group comprising the two distance values (the first distance value and the second distance value) and the two angle angles (θ1 and θ2).

It should be noted that, when the invention defines that the angle value θ is a negative number, The following formula converts it to an angle between 0 and 180 degrees: if Angle<0 then Angle=180+Angle. In addition, when calculating the distance value, the error correction problem in the case where the user's head moves back and forth relative to the photographing unit 300 can be further considered; since the user's head is closer to the photographing unit 300, the second in the eye image 20 The distance between the reflecting points 42a, 42b is large, and as the user's head is away from the photographing unit 300, the distance between the two reflecting points 42a, 42b becomes small. To eliminate this error, the length of the vector detected separately for the pupil center 41 and the reflection points 42a, 42b can be divided by a normalization factor.

Finally, using the coordinate conversion module 208 in the computing unit 200, The first group obtained by the vector processing module 206 is converted to the first position on the output unit 500 by the coordinate system conversion method. In this embodiment, the coordinate conversion module 108 can perform an affine transformation method to include two distance values (a first distance value and a second distance value) and the two angle angles (θ1 and θ2). The first group performs coordinate conversion. The manner of coordinate conversion can be performed by taking the first group into the angle-distance distribution map in the storage unit 400. Hereinafter, the manner of establishing the angle-distance distribution map by the training module 202 will be described in detail.

For example, the training module 202 in the pupil positioning system 10 each time A first target area is displayed on the output unit 200 to divide the output unit 202 into 4×4 total 16-cell target areas for viewing by the user 40, and then the second target area is displayed for the user to view. Up to the 16th target area is displayed; as described above, the image analysis module 204 can obtain the eye images 401 of the 16 users 4 by the 16 times of gaze, so the vector processing module 206 can obtain the pupil center point 41 to The first training distance value defined by the distance of the reflection point 42a to the sixteenth training distance value, and the first angle angle of the spot vector to the sixteenth angle angle, thereby obtaining the first angle-distance distribution map (eg In the same manner, the vector processing module 206 can obtain the first training distance value defined by the distance from the pupil center point 41 to the reflection point 42b to the sixteenth training distance value, and the first of the spot vector. The angle of the angle is angled to the sixteenth angle, and a second angle-distance map (not shown) is obtained.

Thus, coordinate conversion module 208 can use, for example, but not limited to, grouping Corresponding method or interpolation corresponding method, each time the user has different gaze points to the output unit 500, the vector processing module 206 can be used to obtain two distance values (the first distance value and the second distance value) and the two The angles of the angles (θ1 and θ2) are brought into the preset first angle-distance distribution map and the second angle-distance distribution map to obtain corresponding coordinate points 5 for obtaining corresponding positions on the output unit 500.

Furthermore, since two of the output units 500 are used in this embodiment The illumination unit 100 on the diagonal line, therefore, referring to FIG. 5a again, the two reflection points 42a, 42b on the eye image can be utilized to reflect the two reflections by the coordinate conversion module 208. The positions of the points 42a and 42b are converted to positions corresponding to the illumination unit 100 on the diagonal of the output unit 500, and then the pupil center point 41 is further determined by the coordinate conversion module 28 to correspond to the first position on the output unit 500.

4 auxiliary position relative position based pupil positioning system

Please refer to FIG. 7 , which is a schematic diagram of a pupil positioning system based on the relative positions of four auxiliary lights. As can be seen from the figure, the illumination unit 100 is disposed at a midpoint position of the four sides of the output unit 500. When the user 40 looks at the output unit 500, the four illumination units 100 located at the midpoint of the four peripheral sides of the output unit 500 The light source is irradiated to the user's eyes to form four reflective spots on the eyeball, and the photographing unit 300 is used to photograph the user's face to generate a plurality of continuous images, and obtain the pupil of the eyeball and the eyes of the four reflective points. Partial image.

The operation mode of the operation unit 200 for acquiring the eye image is as described in the previous embodiment, and the details of the acquired eye image are as shown in FIG. 8a. Next, the vector processing module 206 calculates four distance values according to the pupil center point 41 and the four reflection points 42c, 42d, 42e, and 42f, respectively, in the manner described in the previous embodiment, such as "Fig. 8b", and four The spot vectors 43c, 43d, 43e, and 43f cooperate with the vertical axis of the pupil center point 41 as a reference line, and obtain four angles of angle (θ3, θ4, θ5, and θ6), thereby composing one including the four distance values and four One of the angled angles of the second group.

Finally, the second group obtained by the vector processing module 206 is converted into the second position on the output unit 500 by using the coordinate conversion module 208 in the computing unit 200. The conversion method is as described in the previous embodiment, and details are not described herein again. It should be noted that since this embodiment uses four auxiliary lights to do For the light source, the reflection on the user's eyes will produce four reflective points. Therefore, it can be known that the pupil positioning system 10 can utilize the training module 202, such as the training method of the above embodiment, according to the position of the pupil and the four reflective points respectively. The four angle-distance distribution maps are obtained. Therefore, in the embodiment, the second group can compare the database information formed by the four angle-distance distribution maps, and can be more accurately positioned.

Furthermore, since four are used in the output unit 500 in this embodiment The illumination unit 100 at the midpoint of the four side lengths, therefore, the pupil center point 41 and the four reflections can be utilized by the coordinate conversion module 208 by using the four reflection points 42c, 42d, 42e and 42f on the eye image. The positions of the points 42c, 42d, 42e, and 42f are converted to correspond to the second position on the output unit 500. According to the reference positions of the four reflective points 42c-42f, the positioning accuracy of the pupil center point 41 corresponding to the second position on the output unit 500 can be effectively improved, and the correction procedure when the user first uses can be omitted.

Thereby, using the pupil positioning method proposed by the embodiment of the present invention, Its systems and computer program products provide precise pupil positioning and fast and accurate eye tracking for a wide range of applications. For example, the pupil positioning of the embodiment of the present invention can be applied to a security product. In the case of an input keyboard composed of English or numeric characters in the access control system, when the user looks at the keyboard, the user's pupil is positioned through the embodiment of the present invention, and the user is matched with the deep drawing device. The depth value or other method can be used to further calculate the gaze direction of the user, and the corresponding key of the keyboard is used to know the character to be input by the user. Thereby, the user can operate the lock such as an eye movement lock in the access control system by simply looking at the character to be input in the keyboard.

In summary, the pupil positioning method, the system thereof and the computer program product of the present invention can calculate the position of the pupil by using the relative positional relationship between the pupil and the plurality of reflective points. Therefore, the embodiment of the invention can accurately detect the position of the pupil, thereby achieving accurate eye tracking, and achieving multiple applications. Moreover, in some embodiments of the present invention, the effect of no correction can be achieved by using a database.

The above is only the preferred embodiment of the present invention, and the scope of the invention is not limited thereto, that is, the simple equivalent changes and modifications made by the scope of the invention and the description of the invention are All remain within the scope of the invention patent.

10‧‧‧瞳孔定位系统

40‧‧‧Users

100‧‧‧Multiple lighting units

200‧‧‧ arithmetic unit

202‧‧‧ training module

204‧‧‧Image Analysis Module

206‧‧‧Vector Processing Module

208‧‧‧Coordinate conversion module

210‧‧‧Eye Search Module

212‧‧‧Eye Status Judgment Module

300‧‧‧Photographic unit

500‧‧‧Output unit

501‧‧‧ indicators

Claims (15)

A pupil positioning method based on the relative positions of a plurality of light sources to position a user's eyeball to look at an output unit position, comprising: (a) illuminating a plurality of light sources on the eyeball for the eyeball Forming a plurality of reflective points on the upper surface; (b) obtaining an eye image including the pupil of the eyeball and the plurality of the reflective points by using a photographing unit; (c) positioning the pupil center point and the plural in the eye image according to an operation unit a position of the reflection point; (d) defining a first group of the plurality of spot vectors from the distance from the center point of the pupil to the plurality of reflection points; and (e) converting the first group into the A first position on the output unit. The pupil positioning method of claim 1, wherein the plurality of the light sources used in the step (a) are disposed at two ends of the diagonal end of the output unit, and the two light sources illuminate the eyeball. In order to form corresponding two reflective spots. The method for positioning a pupil according to claim 1, wherein the plurality of the light sources used in the step (a) are disposed at four vertex positions of the output unit or at a midpoint of four sides of the output unit, so that the four The light source illuminates the eyeball to form corresponding four reflective spots. The pupil positioning method according to any one of claims 1 to 3, wherein the photographing unit of the step (b) finds two by searching for a facial image a nodal center point; calculate a spacing between the center points of the two nostrils and determine a coordinate point; calculate a coordinate point coordinate according to the spacing and the starting point coordinate; define a rectangular frame according to the reference point coordinate, and The eye image is taken out from the open face image along the rectangular frame. The pupil positioning method according to any one of claims 1 to 3, wherein the step (d) comprises, according to the horizontal axis or the vertical axis of the pupil, a reference line segment, and an angle value is defined in accordance with the spot vector. The method for locating a pupil according to any one of claims 1 to 3, wherein the arithmetic unit in the step (e) is connected to a storage unit, and the storage unit includes a plurality of angle-distances equal to the number of the plurality of light sources. a distribution map by which the first group is brought into the plurality of angle-distance distribution maps to be converted into the first position. The pupil positioning method of claim 6, wherein the plurality of the angle-distance distribution maps are pre-divided into a plurality of groups of regions through one of the training modules of the computing unit, and only one of the regions is displayed at a time. The training module performs the following steps: each time a group of regions is displayed for viewing by the user, the image analysis module is controlled to perform positioning and control of the vector processing module to obtain distance-angle data of each group of regions. . The method for locating a pupil according to claim 7, wherein the step (c) is performed by an image analysis module of the operation unit, and the step (d) is performed by a vector processing module of the operation unit, and the Step (e) is transmitted through a coordinate in the arithmetic unit The conversion module is executed. A pupil positioning system based on the relative positions of a plurality of light sources, comprising: a plurality of light sources, the emitted light beam illuminating a user's eye to form a corresponding plurality of reflective spots; and a photographing unit for capturing the user's eye And an operation unit for positioning a pupil center point and a plurality of the reflection points on the eye image; wherein the operation unit defines a plurality of spots according to the distance from the pupil center point to the plurality of the reflection points a vector, and converting a plurality of the spot vectors to a first position on an output unit. The pupil positioning system of claim 8, wherein the operation unit is configured to define a plurality of angle values according to a plurality of the spot vectors according to a horizontal axis or a vertical axis of the pupil center point positioned by the image analysis module. The pupil positioning system of claim 8, further comprising a storage unit connected to the computing unit, and the storage unit includes a plurality of angle-distance distribution maps equal to the number of the plurality of light sources. The pupil positioning system of claim 9 or 10 further includes an output unit adjacent to the photographing unit, and the output unit displays an index corresponding to the pupil gaze position. The pupil positioning system of claim 11, wherein the plurality of light sources are disposed at diagonal ends of the output unit for emitting light onto the eye to form corresponding two reflective points. The pupil positioning system of claim 11, wherein the plurality of the light sources are disposed at four corner positions of the output unit or at a midpoint of four peripheral sides of the output unit for emitting light onto the eye, so that Form corresponding four reflection points. A non-transitory computer program product for locating a pupil, the method of any one of claims 1 to 8 being completed after the computer is loaded into the computer program product and executed.