CN111513671A - Glasses comfort evaluation method based on eye image - Google Patents
Glasses comfort evaluation method based on eye image Download PDFInfo
- Publication number
- CN111513671A CN111513671A CN202010250319.5A CN202010250319A CN111513671A CN 111513671 A CN111513671 A CN 111513671A CN 202010250319 A CN202010250319 A CN 202010250319A CN 111513671 A CN111513671 A CN 111513671A
- Authority
- CN
- China
- Prior art keywords
- comfort
- eyelid
- function
- pupil diameter
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000011521 glass Substances 0.000 title claims abstract description 41
- 238000011156 evaluation Methods 0.000 title claims abstract description 12
- 210000001747 pupil Anatomy 0.000 claims abstract description 88
- 210000000744 eyelid Anatomy 0.000 claims abstract description 84
- 238000000034 method Methods 0.000 claims abstract description 31
- 230000004424 eye movement Effects 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000001514 detection method Methods 0.000 claims description 14
- 238000003708 edge detection Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 12
- 101100356682 Caenorhabditis elegans rho-1 gene Proteins 0.000 claims description 11
- 230000000877 morphologic effect Effects 0.000 claims description 8
- 230000007797 corrosion Effects 0.000 claims description 7
- 238000005260 corrosion Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 abstract description 3
- 210000001508 eye Anatomy 0.000 description 31
- 238000001914 filtration Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 4
- 210000005252 bulbus oculi Anatomy 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000010219 correlation analysis Methods 0.000 description 3
- 210000000720 eyelash Anatomy 0.000 description 2
- 230000004438 eyesight Effects 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 208000029091 Refraction disease Diseases 0.000 description 1
- 230000004430 ametropia Effects 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002330 electrospray ionisation mass spectrometry Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 201000010041 presbyopia Diseases 0.000 description 1
- 208000014733 refractive error Diseases 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 230000004382 visual function Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/11—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for measuring interpupillary distance or diameter of pupils
- A61B3/112—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for measuring interpupillary distance or diameter of pupils for measuring diameter of pupils
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/113—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for determining or recording eye movement
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/14—Arrangements specially adapted for eye photography
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Ophthalmology & Optometry (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Human Computer Interaction (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention relates to a glasses comfort evaluation method based on eye images, which comprises the following steps: acquiring an eye image of a subject over a period of time; processing the acquired eye image to acquire eye movement parameters including a pupil diameter XPDAnd eyelid spacing XES(ii) a Obtaining the comfort level of a subject and recording the value as Y; and establishing a function model of the comfort degree, the pupil diameter and the eyelid distance according to the relationship between the eyelid distance and the comfort degree and the relationship between the pupil diameter and the comfort degree, and further judging the comfort degree of the glasses. According to the method, the influence of the eyelid distance and the pupil diameter on the glasses wearing comfort level is quantitatively researched through a large number of subjective samples and experiments, a function model about the comfort level, the pupil diameter and the eyelid distance is established, and a quantitative standard is provided for the subsequent glasses wearing comfort level judgmentWhether the glasses of the testee are comfortable or not can be directly and quickly judged, and the result is objective and reliable.
Description
Technical Field
The invention relates to a glasses wearing comfort evaluation method, in particular to a glasses comfort evaluation method based on eye images.
Background
The glasses are a special medical appliance for correcting refraction of eyeballs, protecting eye health and improving visual function. The glasses are closely related to everyone, and almost everyone is provided with the glasses due to ametropia and presbyopia or for the purposes of health care and beauty. With the development of science and the increasing demand of people on vision, the ideal glasses not only bring clear vision, but also lead the wearer to obtain comfortable feeling, read at a short distance for a long time and have high-grade appearance. However, the level of practitioners in the eyeglass industry is not uniform, so that various problems may occur in the eyeglass dispensing process, and the eyeglasses are relatively sensitive optical devices, and particularly, any deviation of the eyeglasses on the human body causes discomfort; meanwhile, in the wearing process after the glasses are manufactured, the phenomenon of wearing discomfort can occur, so that the human body can generate some uncomfortable reactions. Therefore, if a set of objective evaluation criteria is available, the practitioner can be guided to better perform the fitting work.
Disclosure of Invention
The technical problem to be solved by the invention is to provide an objective eyeglass comfort evaluation method based on eye images according to the defects of the prior art method, so as to help practitioners and wearers judge the real wearing comfort condition of customers by using an objective method.
The objective of the invention is to provide an objective evaluation method for practitioners in the glasses industry and customers themselves to a system consisting of glasses and eyes, and not only to provide subjective feelings after the customers wear the glasses, but also the feelings can not be understood by the glasses practitioners necessarily, thereby further improving the customer experience.
The invention provides a glasses comfort evaluation method based on eye images, which comprises the following steps:
s1, acquiring an eye image of the subject within a period of time; go to step S2;
s2, processing the obtained eye image to obtain the eye movement parameter, wherein the eye movement parameter comprises the pupil diameter XPDAnd eyelid spacing XES(ii) a Go to step S3;
s3, obtaining the comfort level of the subject and recording the comfort level as Y; go to step S4;
s4, establishing a function model of comfort degree, pupil diameter and eyelid distance according to the relationship between eyelid distance (eyelid distance is the vertical distance between the upper eyelid and the lower eyelid) and comfort degree, and further judging the comfort degree of the glasses, wherein the function model F is the comfort degree of the glasses
F＝Υ1f1+Υ2f2
Wherein F represents comfort value, γ1Gamma, a correlation coefficient representing eyelid spacing and comfort after unitized treatment2Coefficient of correlation f representing pupil diameter and comfort after unitization1Representing a function between eyelid spacing and comfort, f2Representing a function between pupil diameter and comfort.
The invention mainly judges whether the glasses are comfortable by detecting the change conditions of the pupils and the eyelids before and after the wearer wears the glasses, and judges the error of the comfort degree by simply measuring the change of the pupil diameter or the eyelids, and the comfort degree of wearing the glasses can be better reflected by comprehensively considering the pupil diameter and the eyelid. The invention calculates the size change of the pupil and the eyelid of the wearer after wearing the glasses through a preset algorithm, and further evaluates the comfort degree of the glasses.
In step S1 of the above technical solution, the original data is acquired, and the eye movement data is acquired in the following step by recording the eye image of the subject over a period of time with the eye movement monitor.
In step S2 of the above technical solution, a specific method for processing the acquired eye image is as follows:
s201, image preprocessing, namely preprocessing the acquired eye image, wherein the preprocessing comprises denoising, binarization, edge detection and the like; go to step S201;
s202, morphological processing, namely performing morphological expansion and corrosion on the preprocessed image to improve the image effect; go to step S203;
s203, performing eyelid detection and pupil segmentation on the morphologically processed image, and separating a required eyelid and pupil region from the initial image by adopting a mode of combining Hough circle detection and edge detection; go to step S204;
s204, according to the image processing result, the data related to the eye movement index is obtained, namely, the eye movement parameter including the pupil diameter X is obtained from the separated eyelid and pupil area imagePDAnd eyelid spacing XES。
In step S3 of the above technical solution, the comfort level Y value is obtained by questionnaire statistics.
In step S4 of the above technical solution, a specific method for establishing a function model of comfort, pupil diameter, and eyelid distance is as follows:
s401, calculating correlation coefficients of eyelid spacing and comfort level and pupil diameter and comfort level according to the Pearson correlation coefficient, and recording the correlation coefficients as rho 1 and rho 2 respectively; go to step S401;
s402, fitting a function through the corresponding relation between the eyelid spacing and the comfort degree and between the pupil diameter and the comfort degree to describe the functional relation between the two pairs of indexes, and recording the function between the eyelid spacing and the comfort degree as f1Noting that the function between pupil diameter and comfort is f2(ii) a Go to step S403;
s403, rootUnitizing the correlation coefficients ρ 1 and ρ 2 calculated in step S401 according to the following formula, and changing the correlation coefficient ρ 1 of eyelid distance and comfort level into γ after unitizing1The correlation coefficient rho 2 of the pupil diameter and the comfort degree is changed into gamma2，
Wherein i is 1 or 2; go to step S404;
s404, establishing a function model of comfort degree, pupil diameter and eyelid distance after the treatment,
F＝Υ1f1+Υ2f2。
further, in step S402, f1，f2The two letters each represent a model function which is fitted, wherein
f2＝axPD 2-bxPD+c，f1Representing a function between eyelid spacing and comfort, f2Representing a function between pupil diameter and comfort, at function f1Where m denotes the coefficient of the fitting function, e denotes the base of the exponential function, n denotes the coefficient of the argument, xESRepresenting eyelid spacing; at function f2In xPDDenotes the pupil diameter, a denotes the coefficients of the quadratic term of the fitting function, b denotes the coefficients of the first order term of the fitting function, and c denotes the constant term of the fitting function.
According to the method, the influence of the eyelid distance and the pupil diameter on the glasses wearing comfort level is quantitatively researched through a large number of subjective samplings and experiments, and a function model related to the comfort level, the pupil diameter and the eyelid distance is established, so that a quantitative standard is provided for the subsequent glasses wearing comfort level judgment, whether glasses of a subject are comfortable or not can be directly and rapidly judged, and the result is objective and reliable.
Drawings
The invention is further described below with reference to the accompanying drawings.
Fig. 1 is a flow chart of a method for evaluating comfort of eyeglasses according to the present invention.
Detailed Description
The invention provides a glasses comfort evaluation method based on eye images, which comprises the following steps as shown in figure 1:
s1, acquiring original data
An eye tracker is used to record an eye image of the subject over a period of time for subsequent acquisition of eye movement data.
The method specifically comprises the following steps: the eye tracker is worn on the eyes of a subject, and an infrared camera is arranged on a frame of the eye tracker. An eyeball image is acquired through an infrared camera in the worn detection device, infrared light is used as a lighting source of the infrared camera, the infrared camera is insensitive to visible light, and the work of the infrared camera is basically not influenced by the brightness of a test environment. Meanwhile, the skin of a person and the eyeball absorb and reflect light with different wavelengths, so that gray values of all parts in the eye gray image obtained under different environment illumination are relatively constant, and then the eye gray image is preprocessed by using an image processing algorithm, so that the subsequent further eye data can be conveniently obtained.
S2, processing the obtained eye image to obtain the eye movement parameter, wherein the eye movement parameter comprises the pupil diameter XPDAnd eyelid spacing XES。
The specific method for processing the acquired eye image is as follows:
s201, image preprocessing, namely preprocessing the acquired eye image, wherein the preprocessing comprises filtering and denoising, binarization, edge detection and the like.
(1) Image filtering
The method is one of the common methods for image denoising, and can improve the image quality and enhance the characteristic information. Here, gaussian filtering, which is a kind of weighted average filtering, is used, and weighting weights at different positions in the template are selected according to the shape of gaussian distribution. In the image processing, according to a two-dimensional discrete Gaussian function, the weight value is selected to be larger at the position closer to the center in the template. Similarly, the gaussian filter template is also normalized. The 3 × 3 templates are as follows:
(2) binarization processing
Image binarization is one of common methods in image analysis and processing, and refers to converting a grayscale image into a black-and-white image, that is, setting the grayscale values of all points on the image from 0 to 255 as two fixed grayscale values, one larger and one smaller. For the detection of the pupil image, because the gray value of the pupil part is obviously lower than that of other parts under the infrared light background, the image can be quickly divided into the pupil part and the background part by selecting a proper binarization threshold value. The most common method in binarization is global binarization, and the basic idea is to set an appropriate threshold value, change the points in the original image whose gray value is greater than the threshold value into white in the binary image, i.e. the gray value is set to 1, and change the points in the original image whose gray value is less than the threshold value into black in the binary image, i.e. the gray value is set to 0, or vice versa. The binarization operation is performed according to the following formula:
wherein i is 1, 2, 3, …, w, j is 1, 2, 3, …, h, and w represents the image width and h represents the image height; bi，jValue g representing pixel point of ith row and jth column of binary image Bi，jAnd expressing the value of the pixel point of the ith row and the jth column of the gray image G.
(3) Edge detection
An edge is a distinct feature of an image that contains much information, separating two distinct regions. Due to this characteristic of edges, edges help to identify the position of objects and the boundaries of specific entities in the image, and edge detection is usually based on abrupt changes in image color, gray scale, and texture. Because the eye image comprises the pupil and the iris which are obviously distinguished in color, a boundary exists, and the pupil can be separated by finding the boundary through an edge detection algorithm. The invention adopts a Sobel edge detector to carry out edge detection.
S202, morphological filtering processing
And performing morphological expansion and corrosion on the preprocessed image to improve the image effect.
The method specifically comprises the following steps: the influence of the eyelashes and light spots caused by infrared reflection is eliminated, the effect generated by expansion or corrosion operation on the gray image has a certain relation with structural elements, and the values are positive, the expansion can enhance the image brightness, and the corrosion can weaken the image brightness. Meanwhile, by selecting the structural elements with proper shapes and sizes, partial dark details or bright details of the input image can be eliminated through expansion or corrosion operation. The formula of the morphological filtering process is as follows:
A＝RB(M)·S
in the formula, "·" represents a closed operation of expansion and corrosion, S is a disk structural element with a radius of 3, rb (M) is a reconstruction operation, M is a logo image, and a represents a small region of the image.
S203, eyelid detection and pupil segmentation
The desired image containing the eyelid and pupil areas is separated from the initial image by a combination of Hough circle detection and edge detection.
S204, calculating the eye movement index
Determining eye movement parameters including pupil diameter X from the separated eyelid and pupil region images by calculating data related to eye movement indexPDAnd eyelid spacing XES。
In the pupil image, the pupil area only occupies a small part of the pupil image, and peripheral areas such as eyelids and eyelashes in the image belong to interference factors. Therefore, its pupil segmentation task is to separate the required pupil region from the original image. The edge of the pupil is approximately circular, so the Hough circle detection can be used to find the pupil boundary. The Hough circle detection and the edge detection are combined, the edge detection obtains a plurality of discrete edge points, and the discrete points are connected through the Hough circle detection to form a closed circular pupil boundary and an eyelid boundary. It is basicallyThe principle is that according to the nature of a circle, the perpendicular line of the tangent line on the circle must pass through the center of the circle. Therefore, according to the property, if the perpendicular line of each boundary point is found along the edge of the circle, the intersection point of all the perpendicular lines is the center of the circle. Then calculating the number of pixel points of a straight line passing through the center of the circle in the pupil boundary, and obtaining the pupil diameter according to the conversion relation between the pixel points and the millimeters, namely { XPD1,XPD2,XPD3,…,XPDnWhere n is the subject population; for the detection of the eyelids, the eyelids have curve characteristics, so the Hough circle detection can be utilized to find the boundaries of the upper eyelid and the lower eyelid, then the number of pixel points between the two boundaries is calculated in the vertical direction passing through the centers of the pupils according to the found centers of the pupils, and then the eyelid distance, namely { X is obtained according to the conversion relation between the pixel points and millimetersES1,XES2,XES3,…,XESnWhere n is the number of subjects.
And S3, acquiring the comfort level of the subject and recording the value as Y.
The comfort Y value is obtained by questionnaire statistics. Subjects were filled out an eye comfort questionnaire at the end of the experiment. The questionnaire comprises twenty questions, each question comprises four options, different options correspond to different scores, and the final comfort score is formed by adding the scores of all the questions. The score of the questionnaire was scored as (Y)1,Y2,Y3,…,Yn) Where n is the number of subjects.
S4, establishing a function model of the comfort degree, the pupil diameter and the eyelid distance according to the relationship between the eyelid distance and the comfort degree and the relationship between the pupil diameter and the comfort degree, and further judging the comfort degree of the glasses.
In the evaluation process, the specific method for establishing the function model of the comfort degree, the pupil diameter and the eyelid distance is as follows:
s401, the obtained data are processed according to a Pearson correlation coefficient formula (Pearson correlation coefficient is widely used for measuring the correlation degree between two variables, and the value of the Pearson correlation coefficient is between-1 and 1), and correlation coefficients of eyelid distance and comfort level and pupil diameter and comfort level are calculated according to the Pearson correlation coefficient and are respectively marked as rho 1 and rho 2, namely the correlation degree between the two is found.
Calculating correlation coefficients rho 1 and rho 2 of eyelid distance, pupil diameter and comfort degree respectively by using a Pearson correlation coefficient formula,
s402, fitting a function through the corresponding relation between the eyelid distance and the comfort degree and between the pupil diameter and the comfort degree to describe the functional relation between the two pairs of indexes. Fitting can be performed by using an exponential function, a polynomial function, a power function and the like, then a function with the best fitting effect is selected according to the principle of a least square method, and the function between the eyelid interval and the comfort level is recorded as f1Noting that the function between pupil diameter and comfort is f2。
The method specifically comprises the following steps: the pupil diameter is matched with the comfort degree, and the eyelid opening degree is matched with the comfort degree. Wherein, the corresponding form of eyelid opening and comfort is (X)ES1,Y1),(XES2,Y2),(XES3,Y3),(…,…),(XESn，Yn) (ii) a The corresponding form of the pupil diameter and the comfort degree is (X)PD1,Y1),(XPD2,Y2),(XPD3,Y3)，(…,…),(XPDn，Yn). Then, performing function fitting, fitting by using exponential function, power function, polynomial function and the like, and finding the best fitting function, wherein the fitting function of the eyelid interval is f1The fitting function of the pupil diameter is f2。
S403, unitizing the correlation coefficients rho 1 and rho 2 calculated in the step S401 according to the following formula, and changing the correlation coefficient rho 1 of eyelid spacing and comfort level into gamma after unitizing1The correlation coefficient rho 2 of the pupil diameter and the comfort degree is changed into gamma2，
Wherein i is 1 or 2. When rhoi＝ρ1Gamma-gamma after calculation1When rhoi＝ρ2Gamma-gamma after calculation2。
S404, synthesizing the correlation coefficient processed by the unit and the fitted function to obtain a comfort model, namely establishing a function model of the comfort, the pupil diameter and the eyelid interval,
F＝Υ1f1+Υ2f2
wherein the content of the first and second substances,
f1representing a function between eyelid spacing and comfort, f2Represents a function between pupil diameter and comfort, and
f2＝axPD 2-bxPD+ c at function f1Where m denotes the coefficient of the fitting function, e denotes the base of the exponential function, n denotes the coefficient of the argument, xESRepresenting eyelid spacing; at function f2In xPDDenotes the pupil diameter, a denotes the coefficients of the quadratic term of the fitting function, b denotes the coefficients of the first order term of the fitting function, and c denotes the constant term of the fitting function. The function f can be obtained by least square method1Medium coefficients m, n, function f2Medium coefficients a, b, c.
S405, after the model is established successfully, eye movement data of other people can be collected and then substituted into the comfort level model, and the comfort level of the people is calculated.
Example 1
The following describes the implementation of the method by taking data acquisition and processing for a certain tester as an example. After a certain tester is selected for data acquisition, the tester is firstly worn on the eye tracker, the equipment is adjusted to be in a normal working state, the experimental time is three minutes, and the eye movement data of the time is continuously acquired in a natural state.
And (2) performing each preprocessing, including image processing such as denoising, binarization, edge detection and the like, on the eye image acquired at a certain moment to obtain a preprocessing result image, and performing the morphological filtering in the step (S202) on the preprocessing result image to obtain an improved eye image. After the improved eye image is obtained, the desired image containing the eyelid and pupil areas is separated from the image using Hough circle detection and edge detection. Then, based on the image processing result, the data related to the eye movement index, i.e. the diameter X including the pupil is obtainedPDAnd eyelid spacing XES. Meanwhile, the comfort level Y of the subject is obtained by means of a questionnaire. Finally, according to eyelid spacing XESPupil diameter XPDEstablishing a function model of the comfort degree, the pupil diameter and the eyelid distance according to the relation with the comfort degree Y,
F＝Υ1f1+Υ2f2
repeating the above operations, collecting eye images of 10 testers, and storing the collection and calculation results in a sample table as shown in table 1 below, wherein the sample table includes eyelid distance XESPupil diameter XPDSubjective scores of the comfort of the glasses, and the like.
Table sample data example
Unit: rice (m)
And performing data correlation analysis and data fitting according to the sample data.
By utilizing the first 7 pieces of data of the sample table, firstly, correlation analysis is carried out, the correlation relation between the eyelid distance and the comfort level is defined as rho 1, the correlation relation between the pupil diameter and the comfort level is defined as rho 2, and the correlation analysis is calculated to obtain:
ρ1＝-0.8772，ρ2＝0.7507。
then, fitting the data by using different function models based on a least square method to find the most consistent function relation, and finding out that the fitting function of the eyelid opening degree and the comfort degree is as follows:
the fit function of pupil diameter and comfort is:
f2(xPD)＝1.489×106×xPD 2-9098xPD+15.38
wherein f is1(XES) In xESI.e. eyelid spacing, f2(XPD) In xPDIs the pupil diameter.
Unitizing the correlation coefficient to obtain each coefficient in the comprehensive formula as follows:
Υ1＝0.5388
Υ2＝0.4612。
solving a comprehensive fitting formula, namely a glasses comfort degree formula, as follows:
in the above formula, xESIs the eyelid spacing, xPDIs the pupil diameter.
The last three data in sample table 1, which did not participate in the fitting process described above, can be used to test the model.
Wherein x isPD＝0.00468；xES＝0.01115；
F — 4.7021 actual value (comfort): 5
xPD＝0.00453；xES＝0.01036
F — 5.3668 actual value (comfort): 5
xPD＝0.00413；xES＝0.01101
F — 3.8316 actual value (comfort): 4
F represents a predicted value of the comfort level, and the predicted value of the comfort level is compared with an actual value, so that the determined model equation is high in reliability.
After the evaluation model is determined, when the glasses wearing comfort degree of a new subject needs to be tested, the subject wears the eye tracker and obtains eye movement data, and new eyelid distance x is obtained after steps S1 to S2ES0.01102, new pupil diameter xPD0.00488, substituting the above determined model equation to obtain a new comfort prediction of the subject:
therefore, the wearing comfort of the new test subject can be evaluated to a certain level according to the magnitude of the evaluation F of the new test subject.
In addition to the above embodiments, the present invention may have other embodiments. All technical solutions formed by adopting equivalent substitutions or equivalent transformations fall within the protection scope of the claims of the present invention.
Claims (6)
1. A glasses comfort evaluation method based on eye images is characterized by comprising the following steps:
s1, acquiring an eye image of the subject within a period of time; go to step S2;
s2, processing the obtained eye image to obtain the eye movement parameter, wherein the eye movement parameter comprises the pupil diameter XPDAnd eyelid spacing XES(ii) a Go to step S3;
s3, obtaining the comfort level of the subject and recording the comfort level as Y; go to step S4;
s4, establishing a function model of comfort level, pupil diameter and eyelid distance according to the relationship between the eyelid distance and the comfort level and the relationship between the pupil diameter and the comfort level, and further judging the comfort level of the glasses, wherein the function model F is
F＝Υ1f1+Υ2f2
Wherein, γ1Represents passing throughGamma, the correlation coefficient of eyelid spacing and comfort after unit treatment2Coefficient of correlation f representing pupil diameter and comfort after unitization1Representing a function between eyelid spacing and comfort, f2Representing a function between pupil diameter and comfort.
2. The method for evaluating comfort of glasses based on eye image according to claim 1, wherein in step S1, the eye image of the subject is recorded with an eye tracker for a period of time.
3. The method for evaluating comfort of glasses based on eye images according to claim 1, wherein in step S2, the specific method for processing the acquired eye images is as follows:
s201, image preprocessing, namely preprocessing the acquired eye image, wherein the preprocessing comprises denoising, binarization and edge detection; go to step S202;
s202, morphological processing, namely performing morphological expansion and corrosion on the preprocessed image to improve the image effect; go to step S203;
s203, performing eyelid detection and pupil segmentation on the morphologically processed image, and separating a required eyelid and a required pupil region from the initial image by using Hough circle detection and edge detection; go to step S204;
s204, obtaining an eye movement parameter, namely pupil diameter X, from the separated eyelid and pupil area imagePDAnd eyelid spacing XES。
4. The method for evaluating comfort of glasses based on eye images according to claim 1, wherein the comfort Y value in step S3 is obtained by questionnaire statistics.
5. The method for evaluating comfort of glasses based on eye images of claim 1, wherein in step S4, the specific method for establishing the functional model of comfort, pupil diameter and eyelid distance is as follows:
s401, calculating correlation coefficients of eyelid spacing and comfort level and pupil diameter and comfort level according to the Pearson correlation coefficient, and recording the correlation coefficients as rho 1 and rho 2 respectively; go to step S401;
s402, fitting a function through the corresponding relation between the eyelid spacing and the comfort degree and between the pupil diameter and the comfort degree to describe the functional relation between the two pairs of indexes, and recording the function between the eyelid spacing and the comfort degree as f1Noting that the function between pupil diameter and comfort is f2(ii) a Go to step S403;
s403, unitizing the correlation coefficients rho 1 and rho 2 calculated in the step S401 according to the following formula, and changing the correlation coefficient rho 1 of eyelid spacing and comfort level into gamma after unitizing1The correlation coefficient rho 2 of the pupil diameter and the comfort degree is changed into gamma2，
Wherein i is 1 or 2; go to step S404;
s404, establishing a function model of comfort degree, pupil diameter and eyelid distance after the treatment,
F＝Υ1f1+Υ2f2。
6. the method for evaluating comfort of glasses based on eye image of claim 5, wherein in step S402, f1，f2The two letters each represent a model function which is fitted, wherein
f2＝axPD 2-bxPD+c，f1Representing a function between eyelid spacing and comfort, f2Representing a function between pupil diameter and comfort, at function f1Where m denotes the coefficients of the fitting function, e denotes the base of the exponential function, n denotesCoefficient of the independent variable, xESRepresenting eyelid spacing; at function f2In xPDDenotes the pupil diameter, a denotes the coefficients of the quadratic term of the fitting function, b denotes the coefficients of the first order term of the fitting function, and c denotes the constant term of the fitting function.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020100651690 | 2020-01-20 | ||
| CN202010065169 | 2020-01-20 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111513671A true CN111513671A (en) | 2020-08-11 |
Family
ID=71902199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010250319.5A Pending CN111513671A (en) | 2020-01-20 | 2020-04-01 | Glasses comfort evaluation method based on eye image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111513671A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958885A (en) * | 2023-09-19 | 2023-10-27 | 四川大学 | Correcting glasses wearing comfort evaluation method and system based on reading vision |
| CN117460126A (en) * | 2023-10-27 | 2024-01-26 | 石家庄铁道大学 | Subway platform light environment design method based on passenger comfort level |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040145729A1 (en) * | 2003-01-24 | 2004-07-29 | Tzvika Verfel | Method and device for testing sunglasses |
| CN101916362A (en) * | 2010-05-28 | 2010-12-15 | 深圳大学 | Iris positioning method and iris identification system |
| CN106203338A (en) * | 2016-07-11 | 2016-12-07 | 南京航空航天大学 | Based on net region segmentation and the human eye state method for quickly identifying of threshold adaptive |
| CN107066957A (en) * | 2017-03-27 | 2017-08-18 | 北京理工大学 | Iris locating method and device in visible ray eyes image |
| CN107798316A (en) * | 2017-11-30 | 2018-03-13 | 西安科锐盛创新科技有限公司 | A kind of method that eye state is judged based on pupil feature |
| CN108354584A (en) * | 2018-03-06 | 2018-08-03 | 京东方科技集团股份有限公司 | Eyeball tracking module and its method for tracing, virtual reality device |
| CN110083799A (en) * | 2019-03-12 | 2019-08-02 | 江苏明月光电科技有限公司 | A kind of eyeglasses-wearing Comfort Evaluation method based on eye movement technique |
-
2020
- 2020-04-01 CN CN202010250319.5A patent/CN111513671A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040145729A1 (en) * | 2003-01-24 | 2004-07-29 | Tzvika Verfel | Method and device for testing sunglasses |
| CN101916362A (en) * | 2010-05-28 | 2010-12-15 | 深圳大学 | Iris positioning method and iris identification system |
| CN106203338A (en) * | 2016-07-11 | 2016-12-07 | 南京航空航天大学 | Based on net region segmentation and the human eye state method for quickly identifying of threshold adaptive |
| CN107066957A (en) * | 2017-03-27 | 2017-08-18 | 北京理工大学 | Iris locating method and device in visible ray eyes image |
| CN107798316A (en) * | 2017-11-30 | 2018-03-13 | 西安科锐盛创新科技有限公司 | A kind of method that eye state is judged based on pupil feature |
| CN108354584A (en) * | 2018-03-06 | 2018-08-03 | 京东方科技集团股份有限公司 | Eyeball tracking module and its method for tracing, virtual reality device |
| CN110083799A (en) * | 2019-03-12 | 2019-08-02 | 江苏明月光电科技有限公司 | A kind of eyeglasses-wearing Comfort Evaluation method based on eye movement technique |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958885A (en) * | 2023-09-19 | 2023-10-27 | 四川大学 | Correcting glasses wearing comfort evaluation method and system based on reading vision |
| CN116958885B (en) * | 2023-09-19 | 2023-12-05 | 四川大学 | Correcting glasses wearing comfort evaluation method and system based on reading vision |
| CN117460126A (en) * | 2023-10-27 | 2024-01-26 | 石家庄铁道大学 | Subway platform light environment design method based on passenger comfort level |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9779492B1 (en) | Retinal image quality assessment, error identification and automatic quality correction | |
| Kauppi et al. | The diaretdb1 diabetic retinopathy database and evaluation protocol. | |
| US9462945B1 (en) | System and methods for automatic processing of digital retinal images in conjunction with an imaging device | |
| JP4786119B2 (en) | Optometry system, optometry apparatus, program and recording medium thereof, and standardization method | |
| CN109684915B (en) | Pupil tracking image processing method | |
| CN111933275B (en) | Depression evaluation system based on eye movement and facial expression | |
| de Almeida et al. | Computational methodology for automatic detection of strabismus in digital images through Hirschberg test | |
| CN111513671A (en) | Glasses comfort evaluation method based on eye image | |
| CN110575134A (en) | method for calculating myopia degree based on eccentric photography | |
| EP4264627A1 (en) | System for determining one or more characteristics of a user based on an image of their eye using an ar/vr headset | |
| CN110575132A (en) | Method for calculating degree of strabismus based on eccentric photography | |
| Daud et al. | Keratoconus detection using the fusion features of anterior and lateral segment photographed images | |
| CN116682564A (en) | Near-sighted traction maculopathy risk prediction method and device based on machine learning | |
| Onkaew et al. | Automatic extraction of retinal vessels based on gradient orientation analysis | |
| US20230020160A1 (en) | Method for determining a value of at least one geometrico-morphological parameter of a subject wearing an eyewear | |
| Consejo et al. | Detection of subclinical keratoconus with a validated alternative method to corneal densitometry | |
| CN117338234A (en) | Diopter and vision joint detection method | |
| Concepcion-Grande et al. | Eye movements as a predictor of preference for progressive power lenses | |
| Jana et al. | A semi-supervised approach for automatic detection and segmentation of optic disc from retinal fundus image | |
| CN110083799B (en) | Glasses wearing comfort evaluation method based on eye movement technology | |
| CN115223232A (en) | Eye health comprehensive management system | |
| CN111259743B (en) | Training method and system for myopia image deep learning recognition model | |
| CN115375611A (en) | Model training-based refraction detection method and detection system | |
| CN113197543A (en) | Method and system for evaluating vision quality after refractive surgery based on vector aberration theory | |
| Otuna-Hernández et al. | Diagnosis and degree of evolution in a Keratoconus-type corneal Ectasia from image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200811 |
|
| RJ01 | Rejection of invention patent application after publication |