TWI673034B - Methods and system for detecting blepharoptosis - Google Patents

Abstract

An eyelid sagging detection method and system are used to solve the problems that the conventional artificial eyelid sagging detection method takes a lot of time and the measurement results are inconsistent by different doctors and cause errors in measurement results. The method and system include: shooting an eye image with a photographing unit to generate an eye image; performing image processing on the eye image with a processing unit to generate an edge image; and executing the eye image and the edge image with the processing unit. Image processing to obtain a plurality of characteristic variables; the processing unit calculates a characteristic parameter group based on the plurality of characteristic variables; and uses the processing unit to compare the characteristic parameter group with a preset eyelid droop information to infer the eyelid Severity of sagging and function of eye lift.

Description

Eyelid droop detection method and system

The present invention relates to a detection method and system, in particular to a method for detecting eyelid droop, which can be derived through machine vision technology and used to determine the severity of eyelid droop and whether eye muscle function is normal or not based on the data. And system.

Eyelid ptosis can be divided into congenital eyelid ptosis and acquired eyelid ptosis. One of the causes of congenital eyelid ptosis is that the patient's eyelid dysplasia is caused at birth and one of the causes of acquired ptosis It is caused by the tension of the eye-lifting muscles, which prevents the upper eyelid from opening to a normal height. In addition, after the pupil of the eyelid covers the pupil, in addition to the visual field is affected, the patient is likely to unconsciously raise the eyebrows or raise the chin by opening the upper eyelid, and it will also cause forehead wrinkles, shoulder and neck pain, and back pain Or cause symptoms such as eye fatigue.

Known surgical methods to treat eyelid droop depend on the degree of eyelid droop, and / or the state of eyelift function. Therefore, before deciding on the appropriate surgical method, the doctor will manually measure the patient's eyelid static or eyelid dynamics with a ruler. Position to obtain the distance from the center of the pupil to the intersection of the upper edge of the upper eyelid (MRD1), the distance from the center of the pupil to the intersection of the lower edge of the upper eyelid (MRD2), the severity of sagging (Ptosis Severity), and the levator function Based on the relevant data, the physician then analyzed the severity of eyelid droop based on the data. Furthermore, when the physician decides the appropriate surgical method according to the severity of eyelid droop, and after performing the operation in this surgical method, the physician will manually measure the data with a ruler to evaluate the surgical efficacy.

However, the above-mentioned conventional eyelid droop detection method takes a lot of time to measure such as the distance from the center of the pupil to the intersection of the upper edge of the upper eyelid (MRD1), the distance from the center of the pupil to the intersection of the upper edge of the lower eyelid (MRD2), and the severity of the sagging (Ptosis Severity, Levator Function, and other related data, and the measurements of different doctors are also inconsistent, which easily causes errors in the measurement results.

In view of this, the conventional eyelid droop detection method still needs to be improved.

In order to solve the above problems, the present invention aims to provide a method for detecting eyelid droop, which can derive relevant data for judging eyelid droop through machine vision technology, and infer the severity of eyelid droop and normal eye muscle function based on the data.

A secondary object of the present invention is to provide an eyelid droop detection system capable of deriving relevant data for eyelid droop through image processing and machine vision, and automatically detecting whether eye muscle function is normal and detecting severe eyelid droop based on the data. Degrees.

The method for detecting drooping eyelids of the present invention includes: photographing and generating an eye image, the eye image includes a pupil head-up image, a pupil force upward image, and a pupil force downward image; performing image processing on the eye image To generate an edge image; perform image calculations on the eye image and the edge image to obtain a plurality of feature variables; calculate according to the plurality of feature variables to obtain a feature parameter group; and the feature parameter group and a preset eyelid Comparison of sagging information, to infer the severity of eyelid droop and the function of eye muscles.

The eyelid droop detection system of the present invention includes: a photographing unit for photographing and generating an eye image, the eye image includes a pupil head-up image, a pupil force upward image, and a pupil force downward image; a storage A unit for storing a preset eyelid sagging information; and a process A unit coupled to the photographing unit and the storage unit, the processing unit performs image processing on the eye image to generate an edge image, and the processing unit performs image operations on the eye image and the edge image to obtain a plurality of feature variables The processing unit calculates and obtains a characteristic parameter group according to the plurality of characteristic variables, and compares the characteristic parameter group with the preset eyelid sagging information to infer the severity of the eyelid sagging and the function of the eye-lifting muscle.

According to this, the eyelid droop detection method and system of the present invention can obtain the patient's eye information by using image processing technology and machine vision, and use the eye information to derive relevant data for judging eyelid droop, and to automate according to the data Detect the function of eyelift and detect the severity of eyelid droop. In this way, the system can achieve convenient operation, greatly shorten the measurement time and improve the measurement consistency, and simultaneously detect the severity of eyelid droop and the function of lifting eye muscles.

The plurality of characteristic variables include an eye contour area, a scleral area, an iris area, a pupil area, a pupil center point, an upper eyelid lower edge curve, an upper eyelid upper edge curve, and an upper eyelid lower edge intersection. The position coordinates of the point where the upper edge of the eyelid meets. Thus, the eyelid droop detection method of the present invention has the functions of providing relatively complete static measurement parameters and dynamic measurement parameters to simultaneously detect the severity of eyelid droop and the function of raising eye muscles.

The plurality of characteristic variables further include position coordinates of a left edge point and a right edge point. In this way, the method for detecting drooping eyelids of the present invention uses the above parameters to assist in determining the severity of drooping eyelids and the function of lifting the function of the eye muscles.

The characteristic parameter system includes a height difference between an iris diameter and a palpebral fissure height, and a maximum moving distance when the pupil is forced upward and downward. Thus, the eyelid droop detection method of the present invention has the effect of simultaneously detecting the severity of eyelid droop and the function of raising eye muscles.

The feature parameter group further includes a first distance between the pupil center point and the intersection point of the upper edge of the lower eyelid, and a second distance between the pupil center point and the intersection point of the upper edge of the lower eyelid. The height of the palpebral fissure between the intersection of the lower edge of the upper eyelid and the intersection of the upper edge of the lower eyelid, the width of a palpebral fissure between the left edge of the eye corner and the right edge of the eye corner, and the calculation is derived based on the iris area. The surface area of an eyeball. In this way, the eyelid droop detection method of the present invention has the function of assisting in judging the severity of eyelid droop and the function of raising eye muscles by using the above parameters.

A virtual digital eye is formed according to the plurality of characteristic variables, and the virtual digital eye is overlapped with the eye image to analyze whether the virtual digital eye has a great deviation from the eye image. In this way, the eyelid droop detection method of the present invention has the effect of improving detection accuracy.

The plurality of characteristic variables include an eye contour area, a scleral area, an iris area, a pupil area, a pupil center point, an upper eyelid lower edge curve, an upper eyelid upper edge curve, and an upper eyelid lower edge intersection. The position coordinates of the point where the upper edge of the eyelid meets. In this way, the eyelid droop detection system of the present invention has the functions of providing complete static measurement parameters and dynamic measurement parameters, and simultaneously detecting the severity of eyelid droop and the function of lifting eye muscles.

The plurality of characteristic variables further include position coordinates of a left edge point and a right edge point. In this way, the eyelid droop detection system of the present invention assists in judging the severity of eyelid droop and the function of lifting the eye muscles by using the above parameters.

The characteristic parameter system includes a height difference between an iris diameter and a palpebral fissure height, and a maximum moving distance when the pupil is forced upward and downward. In this way, the eyelid droop detection system of the present invention has the function of simultaneously detecting the severity of eyelid droop and the function of raising eye muscles.

The feature parameter group further includes a first distance between the pupil center point and the intersection point of the upper edge of the upper eyelid, a second distance between the pupil center point and the intersection point of the upper edge of the lower eyelid, and the upper point. The height of the palpebral fissure between the intersection of the lower edge of the eyelid and the upper edge of the lower eyelid, the width of a palpebral fissure between the left edge of the eye corner and the right edge of the eye corner, and calculated based on the derivation of the iris area One glance at the sphere surface area. In this way, the eyelid droop detection system of the present invention has the function of assisting in judging the severity of eyelid droop and the function of raising eye muscles by using the above parameters.

Wherein, the processing unit forms a virtual digital eye according to the plurality of characteristic variables, and the processing unit overlaps the virtual digital eye with the eye image to analyze whether the virtual digital eye has a maximum distance between the eye image and the eye image. Deviations occur. In this way, the eyelid droop detection method of the present invention has the effect of improving detection accuracy.

〔this invention〕

S1‧‧‧Image capture steps

S2‧‧‧Image processing steps

S3‧‧‧Feature Extraction Steps

S4‧‧‧Feature calculation steps

S5‧‧‧ Feature analysis steps

S6‧‧‧ Feature Overlap Step

1‧‧‧Photography Unit

2‧‧‧Storage unit

3‧‧‧ processing unit

LF‧‧‧Maximum moving distance

A‧‧‧eye contour area

A1‧‧‧‧Scleral area

A2‧‧‧Iris area

A3‧‧‧ pupil area

C1‧‧‧Curve of lower edge of upper eyelid

C2‧‧‧ Curve of upper edge of lower eyelid

P1‧‧‧ pupil center

P2‧‧‧Intersection of lower edge of upper eyelid

P3‧‧‧Intersection of upper edge of lower eyelid

P4‧‧‧Left edge of eye corner

P5‧‧‧Right edge of eye corner

P6‧‧‧ first position coordinates

P7‧‧‧Second position coordinates

MRD1‧‧‧First distance

MRD2‧‧‧Second Distance

PFH‧‧‧height

PFW‧‧‧ Eyelid width

PS‧‧‧ height difference

[FIG. 1] A processing flowchart of a preferred embodiment of the present invention.

[Fig. 2] A schematic diagram of an eye image of a pupil head-up image according to a preferred embodiment of the present invention.

[Figure 3] A schematic diagram of an eye image with a pupil forced upward and a downward forced image according to a preferred embodiment of the present invention.

[FIG. 4] A system architecture diagram of a preferred embodiment of the present invention.

In order to make the above and other objects, features, and advantages of the present invention more comprehensible, the following describes the preferred embodiments of the present invention in detail with the accompanying drawings as follows: Please refer to FIG. 1, It is a preferred embodiment of the eyelid droop detection method of the present invention, and includes an image capture step S1, an image processing step S2, a feature extraction step S3, a feature calculation step S4, and a feature analysis step S5.

Please refer to FIG. 2 to FIG. 3 together. The image capturing step S1 is capable of shooting and generating an eye image, and the eye image is a color image. Preferably, the eye image system may include a pupil head-up image, a pupil force upward image, and a pupil force downward image. in particular, The image capturing step S1 is capable of capturing and generating a facial image, and selecting a Region of Interest (ROI) as the eye image from the facial image. The position coordinates of the starting pixel of the rectangle formed by the region of interest and the length and width values of the rectangle can be set so as to cover the eye parts including the upper eyelid, lower eyelid, sclera, iris, and pupil. Those with ordinary knowledge in related fields can understand it, so I won't go into details here.

The image processing step S2 is capable of performing image processing on the eye image to generate an edge image. Specifically, a gray-scale process is performed on the eye image to segment the foreground and background of the eye image to generate a gray-scale image. Furthermore, the image processing step S2 retains the part of interest in the eye image, simplifies subsequent image processing procedures, and improves overall computing performance. The image processing step S2 is capable of performing binarization processing on the grayscale image. To generate a binarized image, such as but not limited to, the binarized threshold can be distinguished as a fixed threshold or an adaptive threshold (such as: Otsu, bimodal method, P-parameter method, or superimposed Generation law). Furthermore, the image processing step S2 is capable of performing edge detection processing on the binarized image, so that the edge image is generated, so as to further greatly reduce the amount of data of the eye image, and to remove potentially irrelevant information, and The important structural attributes of the eye image are retained. For example, but not limited to, the edge detection system can use edge detection algorithms such as Sobel, Prewitt or Canny.

The feature extraction step S3 is capable of performing image calculations on the eye image and the edge image to obtain a plurality of feature variables for analyzing the severity of eyelid droop and the function of lifting the eye muscles. The plurality of feature variables may be Contains an eye contour area A, a scleral area A1, an iris area A2, a pupil area A3, a pupil center point P1, an upper eyelid lower edge curve C1, an lower eyelid upper edge curve C2, and an upper eyelid lower edge intersection Position coordinates of the intersection point P2 and the upper edge of the lower eyelid P3. Preferably, the plurality of characteristic variables may further include position coordinates of a left edge point P4 and a right edge point P5 of the eye corner.

Specifically, the feature extraction step S3 can perform a symmetric change on the eye image. Symmetry Transform to get an eye area. Performing a symmetric transformation on each pixel point of the eye image to generate a plurality of symmetric transformation results, and using the position coordinates of a maximum pixel point in the plurality of symmetric transformation results as an initial point for generating the eye contour area A. The eye contour area A may include eye features such as the scleral area A1, the iris area A2, the pupil area A3, the upper eyelid and the lower eyelid. Furthermore, because the sclera has relatively low color saturation compared to eye features such as the pupil, iris, upper eyelid, and lower eyelid. Therefore, the feature extraction step S3 can convert the eye image from the RGB color space to the HSV color space to generate an HSV image. An S-channel image is obtained from the HSV image, and pixels with saturation less than a threshold in the S-channel image form the scleral region A1. The setting of the threshold value can be understood by those having ordinary knowledge in the related field of the present invention, and details are not described herein.

On the other hand, the feature extraction step S3 can perform a Symmetry Transform on the edge image to obtain a plurality of candidate pupil regions. In this embodiment, the symmetric transformation can be a fast radial symmetric transformation (Fast Radial Symmetry Transform (FRST). The feature extraction step S3 calculates and obtains two projection points of each edge point of the edge image in the gradient direction, and respectively forms a gradient projection image (Orientation Projection Image) and a gradient amplitude image ( Magnitude Projection Image) to obtain a plurality of radial symmetric transformation results, that is, to obtain the plurality of candidate pupil areas. A pupil black value ratio is calculated for each of the plurality of candidate pupil areas, and the candidate pupil area having the largest ratio among the plurality of pupil black values is used as the pupil area A3. The pupil black value ratio is a ratio occupied by black pixels among all pixels in each candidate pupil area. Furthermore, the system can also obtain the position coordinates of the pupil center point P1 by positioning in the pupil area A3.

The feature extraction step S3 can obtain the upper edge eyelid lower edge curve C1 and the lower eyelid upper edge curve C2 in the eye contour area A. Specifically, a gradient direction (Gradient Orientation) is used to calculate each pixel point on the boundary of the scleral area A1 with respect to the eye contour area. The tangent slope of A, the boundary between each pixel point on the boundary of the scleral area A1 and the tangent slope of the eye contour area A is zero, which is expressed as an eyelid curve. According to the position coordinates of the eyelid curve, the eyelid curve is divided into the upper eyelid lower edge curve C1 and the lower eyelid upper edge curve C2. Furthermore, it is also possible to extend a vertical line from the pupil center point P1 in a direction perpendicular to the plane formed by the pupil's head-up direction, and make the vertical lines intersect at the lower edge curve C1 and the upper edge of the lower eyelid, respectively. The curve C2 is used to obtain the position coordinates of the upper edge intersection point P2 and the lower edge intersection point P3 respectively.

Preferably, the feature extraction step S3 can also obtain the position coordinates of the left corner point P4 and the right corner point P5 of the eye corner in the eye contour area A. Specifically, the corners of the upper eyelid lower edge curve C1 and the lower eyelid upper edge curve C2 are calculated at a corner distance, and the positions of the left edge point P4 and the right edge point P5 of the eye corner are obtained respectively. coordinate.

Please refer to Figs. 2 to 3, the feature calculation step S4 can be calculated according to the plurality of feature variables to obtain a feature parameter group. For example, the characteristic parameter system includes a height difference PS (Ptosis Severity) between an iris diameter and a palpebral fissure height (PFH), and a maximum movement when the pupil is forced upwards and downwards Distance LF. Preferably, the characteristic parameter group may further include a first distance MRD1 between the pupil center point P1 and the upper eyelid intersection point P2, and the pupil center point P1 to the lower eyelid upper edge intersection point P3. A second distance MRD2, a palpebral fissure height PFH between the upper edge lower edge intersection point P2 to the lower eyelid upper edge intersection point P3, a left edge point P4 to the right edge edge point P5 of the eyelid The palpebral fissure width (PFW) and the ocular surface area (OSA) of one eye calculated from the iris area A2.

The feature analysis step S5 is capable of inferring the severity of the eyelid droop and the function of the eye-lifting muscles by comparing the characteristic parameter set with a preset eyelid droop information. For example, the iris diameter is 11 mm calculated from the iris area A2, and the height of the palpebral fissure PFH between the intersection point P2 of the upper edge of the upper eyelid and the intersection point P3 of the upper edge of the lower eyelid is 8 mm. , The height difference between the diameter of the iris and the height of the eyelid PFH is 3 mm, that is, the severity of eyelid droop is mild. The preset eyelid sagging information can be shown in Table 1 below:

The eyelid droop detection method of the present invention may further include a feature overlapping step S6. The feature overlapping step S6 is to form a virtual digital eye according to the plurality of feature variables. The virtual digital eye and the eye image are overlapped to form a virtual digital eye. Analyze whether the virtual digital eye has a great deviation from the eye image. Specifically, the feature overlapping step S6 can set a weight value for the scleral area A1, the pupil area A3, and the eyelid curve, respectively. The formula for calculating the weight value of the scleral area A1 can be shown in the following formula (1) _{: D color = α Σ △ P} sclera - β Σ △ P skin (1) wherein, P _sclera line represents a pixel point on the sclera; P _skin lines indicates a pixel on the skin; [alpha] line represents the control P _sclera of weights, β Is the weight that controls P _skin , and α + β = 1.

The calculation formula of the weight value of the pupil area A3 can be shown in the following formula (2): Among them, eye _total represents all pixels of the pupil; eye _black represents pupil black pixels.

The calculation formula of the weight value of the eyelid curve can be shown in the following formula (3): Among them, Ω indicates the boundary of the eye contour area A; | Ω | indicates the boundary length of the eye contour area A; θ _{( x, y )} indicates the gradient direction in the ( x, y ) coordinate system; m _{( x , y )} is the slope of the tangent to the contour area A of the eye.

Preferably, the feature overlapping step S6 can also set another weight value for the left corner point P4 and the right corner point P5 of the eye corner, and a formula for calculating the weight value of the left corner point P4 and the right corner point P5 of the eye corner. It can be shown by the following formulas (4) ~ (5): D _cor = | H | -k . trace ( H ) ² (4)

Among them, w ( x, y ) is a weighted value centered on the x, y coordinates; G _x is a derivative in the x-axis direction; G _y is a derivative in the y-axis direction; k is a Harris algorithm parameter.

The above weight value is used as an input variable of a weight value formula, and a plurality of virtual digital eyes with different weights are calculated and obtained. Among the plurality of virtual digital eyes, a person having the highest weight is selected to replace the original formed by the plurality of characteristic variables. Virtual digital eyes. The formula for calculating the weight value can be shown in the following formula (6): Among them, D _θ represents the weight value of the eyelid curve; D _color represents the weight value of the scleral area A1; D _sym represents the weight value of the pupil area A3; D _cor represents the weight value of the corner point of the eye; σ _i represents The optimal parameter values obtained through repeated experiments; d _i represents the respective parameter values of D _θ , D _color , D _sym and D _cor ; μ _i represents the average weight of D _θ , D _color , D _sym and D _cor .

Please refer to FIG. 4, which is a preferred embodiment of the eyelid droop detection system of the present invention, which includes a photographing unit 1, a storage unit 2, and a processing unit 3. The processing unit 3 is coupled to the photographing unit 1. And the storage unit 2.

The photographing unit 1 can be used for shooting and generating a face image, preferably shooting and generating an eye image. The eye image system can include a pupil head-up image, a pupil forced upward image, and a pupil forced downward image. . For example, without limitation, the photographing unit 1 may be a charge coupled device CCD color camera or a complementary metal oxide semiconductor CMOS color camera.

The storage unit 2 may be any storage medium used to store electronic data, such as a hard disk or a memory, but is not limited thereto. The storage unit 2 can be used to store preset eyelid sagging information. The preset eyelid sagging information can be as shown in Table 1 above.

The processing unit 3 is coupled to the photographing unit 1 and the storage unit 2. The processing unit 3 may be a circuit unit having functions such as data processing, signal generation, and control, such as a microprocessor, a microcontroller, A digital signal processor, a logic circuit or a special application integrated circuit (ASIC). In this embodiment, the processing unit 3 may be a microprocessor, but it is not limited thereto. The processing unit 3 can perform image processing on the eye image to generate an edge image. Specifically, the image processing system may include performing image processing procedures such as grayscale, binarization, and edge detection on the eye image to generate the edge image. Wherein, when the photographing unit 1 generates a facial image, the processing unit 3 can set a region of interest in the facial image as the eye image. The position coordinates of the starting pixel of the rectangle formed by the region of interest and the length and width values of the rectangle can be set so as to cover the eye parts including the upper eyelid, lower eyelid, sclera, iris, and pupil. Those with ordinary knowledge in the related field can understand it, and will not repeat it here.

The processing unit 3 can perform image calculations on the eye image and the edge image to obtain a plurality of characteristic variables for analyzing the severity of eyelid droop and the function of lifting the eye muscle. The plurality of characteristic variables may include an eye. Contour area A, one scleral area A1, one iris area A2, one pupil area A3, one pupil center point P1, one upper eyelid lower edge curve C1, one lower eyelid upper edge curve C2, one upper eyelid lower edge intersection point P2, and one The position coordinates of the intersection point P3 of the upper edge of the eyelid. Preferably, the plurality of characteristic variables may further include a left edge point P4 and a right edge edge of the eye corner. The coordinates of the respective positions of point P5.

Specifically, the processing unit 3 performs a symmetric transformation on the eye image to obtain an eye region. The processing unit 3 can perform a symmetric transformation on each pixel of the eye image to generate a plurality of symmetrical transformation results. The processing unit 3 uses the position coordinates of a maximum pixel point in the symmetrical transformation result to generate the eye contour. The starting point of area A. The eye contour area A may include eye features such as the scleral area A1, the iris area A2, the pupil area A3, the upper eyelid and the lower eyelid. Furthermore, because the sclera has relatively low color saturation compared to eye features such as the pupil, iris, upper eyelid, and lower eyelid, the processing unit 3 converts the eye image from RGB color space to HSV color Space to produce an HSV image. The processing unit 3 obtains an S-channel image from the HSV image, and forms pixels in the S-channel image with saturation less than a threshold to form the scleral region A1. The setting of the threshold value can be understood by those having ordinary knowledge in the related field of the present invention, and details are not described herein.

On the other hand, the processing unit 3 performs a symmetric transformation on the edge image to obtain a plurality of candidate pupil regions. In this embodiment, the symmetric transformation may be a fast radial symmetric transformation. The processing unit 3 calculates two projection points of each edge point of the edge image in the gradient direction, and obtains a plurality of radial symmetrical transformation results according to the gradient projection image and the gradient amplitude image formed by the two projection points respectively. , That is, to obtain the plurality of candidate pupil regions. The processing unit 3 calculates a pupil black value ratio for each of the plurality of candidate pupil areas, and uses the candidate pupil area with the largest ratio among the plurality of pupil black values as the pupil area A3. The pupil black value ratio is a ratio occupied by black pixels among all pixels in each candidate pupil area. Furthermore, the processing unit 3 can also obtain the position coordinates of the pupil center point P1 by positioning in the pupil area A3.

The processing unit 3 can obtain the upper eyelid lower edge curve C1 and the lower eyelid upper edge curve C2 in the eye contour area A. Specifically, the processing unit 3 calculates a tangent of each pixel point on the boundary of the scleral area A1 with respect to the eye contour area A by using a gradient direction formula. The slope is the boundary where each pixel on the boundary of the scleral area A1 and the slope of the tangent line A of the eye contour area are zero, which is expressed as an eyelid curve. The processing unit 3 can distinguish the eyelid curve into the upper eyelid lower edge curve C1 and the lower eyelid upper edge curve C2 according to the position coordinates of the eyelid curve. Furthermore, the processing unit 3 can also extend a vertical line from the pupil center point P1 in a direction perpendicular to the plane formed by the pupil viewing direction, and make the vertical lines intersect the lower edge curve C1 and The lower eyelid upper edge curve C2 is used to obtain position coordinates of the upper eyelid lower edge intersection point P2 and the lower eyelid upper edge intersection point P3, respectively.

Preferably, the processing unit 3 can obtain the left edge point P4 and the right edge point P5 of the eye corner in the eye contour area A. Specifically, the processing unit 3 calculates the boundary between the upper edge lower eye curve C1 and the lower edge upper eye curve C2 by using a corner distance formula, and obtains the left edge point P4 and the right edge point P5 of the eye corner. Preferably, the processing unit 3 can also extend from the pupil center point P1 and intersect at the lower edge curve C1 of the upper eyelid and the upper edge curve C2 of the lower eyelid respectively to obtain the intersection point P2 of the upper eyelid and the lower edge The position coordinates of the intersection point P3 of the upper edge of the eyelid.

The processing unit 3 can calculate according to the plurality of characteristic variables to obtain a characteristic parameter group. For example, the characteristic parameter system includes a height difference PS (Ptosis Severity) between an iris diameter and a palpebral fissure height (PFH), and a maximum movement when the pupil is forced upwards and downwards Distance LF. Preferably, the characteristic parameter group may further include a first distance MRD1 between the pupil center point P1 and the upper eyelid intersection point P2, and the pupil center point P1 to the lower eyelid upper edge intersection point P3. A second distance MRD2, a palpebral fissure height PFH between the upper edge lower edge intersection point P2 to the lower eyelid upper edge intersection point P3, a left edge point P4 to the right edge edge point P5 of the eyelid The palpebral fissure width (PFW) and the ocular surface area (OSA) of one eye calculated from the iris area A2.

The processing unit 3 compares with a preset eyelid droop information according to the feature parameter group Yes, we can infer the severity of eyelid droop and the function of eye lift. For example, the processing unit 3 calculates and obtains a first position coordinate P6 when the pupil is forced upwards according to a plurality of characteristic variables generated by the pupil with the pupil upwards, and according to a plurality of images generated by the pupils downward. The characteristic variable calculates a second position coordinate P7 when the pupil is forced downward, and the processing unit 3 calculates a distance difference between the first position coordinate P6 and the second position coordinate P7 to generate the maximum moving distance LF. When the maximum moving distance LF is equal to 7 mm, according to the above table 1 as an example, it means that the eye lifting muscle function is moderately abnormal.

According to the eyelid droop detection system of the present invention, the processing unit 3 may further form a virtual digital eye according to the plurality of characteristic variables, and the processing unit 3 may overlap the virtual digital eye with the eye image to analyze the virtual digital Whether there is a great deviation between the eye and the eye image. Specifically, the processing unit 3 sets a weight value for the scleral region A1, the pupil region A3, and the eyelid curve, respectively. Preferably, the processing unit 3 can also use the left edge point P4 of the corner of the eye and the right corner of the eye The edge point P5 sets another weight value. The calculation formula of the plurality of weight values can be shown in the above formulas (1) to (5). The processing unit 3 can use the weight value as an input variable of a weight value formula, and calculate and obtain a plurality of virtual digital eyes with different weights. The processing unit 3 selects the virtual digital eyes with the highest weight from the plurality of virtual digital eyes to replace the A virtual digital eye formed by a plurality of original characteristic variables. The calculation formula of the weight value can be shown in the above formula (6).

To sum up, the eyelid droop detection method and system of the present invention can use image processing technology and machine vision to obtain patient's eye information, and use the eye information to derive relevant data for judging eyelid droop, and according to the data Automated testing of the function of the eyelift and detection of the severity of eyelid sagging. In this way, the system can achieve convenient operation, greatly shorten the measurement time and improve the measurement consistency.

Although the present invention has been disclosed by using the above-mentioned preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make relative to the above implementation without departing from the spirit and scope of the present invention. Various changes and modifications are still included in the technical scope protected by the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope of the appended patent application.

Claims (12)

An eyelid droop detection method includes: shooting to generate an eye image, the eye image includes a pupil head-up image, a pupil force upward image, and a pupil force downward image; performing image processing on the eye image to generate An edge image; performing image operations on the eye image and the edge image to obtain a plurality of feature variables; calculating based on the plurality of feature variables to obtain a feature parameter group; and the feature parameter group and a preset eyelid droop information In contrast, the severity of eyelid droop and the function of the eye-lifting muscles are inferred. The eyelid droop detection method according to item 1 of the scope of patent application, wherein the plurality of characteristic variables include an eye contour area, a scleral area, an iris area, a pupil area, a pupil center point, and an upper eyelid Location coordinates of the edge curve, the upper edge of the lower eyelid, the intersection of the upper edge of the lower eyelid, and the intersection of the upper edge of the lower eyelid. The eyelid droop detection method according to item 2 of the scope of the patent application, wherein the plurality of characteristic variables further include position coordinates of a left edge point of the eye corner and a right edge point of the eye corner. The eyelid droop detection method according to item 3 of the scope of the patent application, wherein the characteristic parameter set includes a height difference between an iris diameter and a palpebral fissure height, and a time when the pupil is forced upwards and downwards. Maximum travel distance. The eyelid droop detection method according to item 4 of the scope of patent application, wherein the feature parameter group further includes a first distance between the pupil center point and the intersection point of the upper edge of the upper eyelid, and the pupil center point to the lower eyelid. A second distance between the intersection of the upper edge of the eyelid, the height of the palpebral fissure between the intersection of the upper edge of the lower eyelid and the intersection of the upper edge of the lower eyelid, and the distance between the left edge of the eye and the right edge of the eye Eyelid fissure width, and the surface area of a sphere calculated from the iris area. The method for detecting droopy eyelids according to item 3 of the scope of patent application, wherein The plurality of characteristic variables form a virtual digital eye, and the virtual digital eye is overlapped with the eye image to analyze whether the virtual digital eye has a great deviation from the eye image. An eyelid droop detection system includes: a photographing unit for photographing and generating an eye image. The eye image includes a pupil head-up image, a pupil force upward image, and a pupil force downward image; a storage unit, For storing a preset eyelid sagging information; and a processing unit coupled to the photographing unit and the storage unit, the processing unit performing image processing on the eye image to generate an edge image, and the processing unit for the eye image And the edge image performs image calculation to obtain a plurality of feature variables, the processing unit calculates a feature parameter group according to the plurality of feature variables, and compares the feature parameter group with the preset eyelid sagging information to infer eyelid sagging The severity and function of eye lift. The eyelid droop detection system according to item 7 of the scope of patent application, wherein the plurality of characteristic variables include an eye contour area, a sclera area, an iris area, a pupil area, a pupil center point, and an upper eyelid Location coordinates of the edge curve, the upper edge of the lower eyelid, the intersection of the upper edge of the lower eyelid, and the intersection of the upper edge of the lower eyelid. The eyelid droop detection system according to item 8 of the scope of the patent application, wherein the plurality of characteristic variables further include position coordinates of a left edge point of the eye corner and a right edge point of the eye corner. The eyelid droop detection system according to item 9 of the scope of the patent application, wherein the characteristic parameter set includes a height difference between an iris diameter and a palpebral fissure height, and Maximum travel distance. The eyelid droop detection system according to item 10 of the scope of patent application, wherein the feature parameter group further includes a first distance between the pupil center point and the intersection point of the lower edge of the upper eyelid, and the pupil center point to the lower eyelid. A second distance between the intersection of the upper edge of the eyelid, the height of the palpebral fissure between the intersection of the upper edge of the upper eyelid and the intersection of the upper edge of the lower eyelid, and the distance from the left edge of the eye to the right edge of the eye Between the width of a palpebral fissure, and the surface area of a sphere calculated from the iris area. The eyelid sagging detection system according to item 9 of the scope of patent application, wherein the processing unit forms a virtual digital eye according to the plurality of characteristic variables, and the processing unit overlaps the virtual digital eye with the eye image to Analyze whether the virtual digital eye has a great deviation from the eye image.