CN116687340A - Ophthalmic examination auxiliary equipment based on facial eye feature recognition - Google Patents
Ophthalmic examination auxiliary equipment based on facial eye feature recognition Download PDFInfo
- Publication number
- CN116687340A CN116687340A CN202310756639.1A CN202310756639A CN116687340A CN 116687340 A CN116687340 A CN 116687340A CN 202310756639 A CN202310756639 A CN 202310756639A CN 116687340 A CN116687340 A CN 116687340A
- Authority
- CN
- China
- Prior art keywords
- image
- ellipse
- eye
- ophthalmic examination
- eye feature
- 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
- 230000001815 facial effect Effects 0.000 title claims abstract description 15
- 210000001508 eye Anatomy 0.000 claims abstract description 54
- 210000001747 pupil Anatomy 0.000 claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000005259 measurement Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 13
- 241000282414 Homo sapiens Species 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 16
- 210000003128 head Anatomy 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 230000000903 blocking effect Effects 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 description 22
- 210000005252 bulbus oculi Anatomy 0.000 description 7
- 238000005286 illumination Methods 0.000 description 5
- 230000004888 barrier function Effects 0.000 description 2
- 208000001491 myopia Diseases 0.000 description 2
- 230000004379 myopia Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 208000002177 Cataract Diseases 0.000 description 1
- 241000227425 Pieris rapae crucivora Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 210000000608 photoreceptor cell Anatomy 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 210000001525 retina Anatomy 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- A61B3/14—Arrangements specially adapted for eye photography
- A61B3/15—Arrangements specially adapted for eye photography with means for aligning, spacing or blocking spurious reflection ; with means for relaxing
- A61B3/152—Arrangements specially adapted for eye photography with means for aligning, spacing or blocking spurious reflection ; with means for relaxing for aligning
-
- 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
- A61B3/0016—Operational features thereof
-
- 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
- A61B3/0083—Apparatus for testing the eyes; Instruments for examining the eyes provided with means for patient positioning
-
- 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
- A61B3/15—Arrangements specially adapted for eye photography with means for aligning, spacing or blocking spurious reflection ; with means for relaxing
- A61B3/156—Arrangements specially adapted for eye photography with means for aligning, spacing or blocking spurious reflection ; with means for relaxing for blocking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/143—Sensing or illuminating at different wavelengths
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/197—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Surgery (AREA)
- Human Computer Interaction (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention discloses an ophthalmic examination auxiliary device based on facial eye feature recognition, which comprises an examination auxiliary device, wherein an infrared camera and an image processing system are arranged on the examination auxiliary device, and the infrared camera is used for shooting a front image of a subject; an image processing system: carrying out gray scale and binarization processing on the image of part of the face to obtain a binarized image; after identifying that the eye features appear in the auxiliary equipment camera window, searching pupil positions in the eyes; the method and the device have the advantages that the speed and the accuracy of the ophthalmic examination are remarkably improved, the working intensity of operators is reduced, the measurement accuracy is improved, and the ophthalmic examination flow is optimized.
Description
Technical Field
The invention relates to the technical field of ophthalmic examination, in particular to an ophthalmic examination auxiliary device based on facial eye feature recognition.
Background
The trend of myopia to lower the age and to increase the height is very prominent, and great importance is attached to education and hygiene related departments. Various instruments required for ophthalmic examination, which are important technical means for myopia prevention, have been popularized in spectacle stores, vision centers, and hospital clinics, and these instruments include ophthalmic examination apparatuses such as fundus cameras, optical biometer, optometry, OCT, and the like.
The human eye can see the image mainly because the pupil of the human eye is transparent, the light entering the pupil stimulates the photoreceptor cells in the retina to form the image, and the working principle of most ophthalmic inspection devices relies on the characteristic to perform measurement inspection on the eyeball data. The conventional pupil size of human beings is about 1.5 mm-8 mm, the pupil is contracted in bright light, and the pupil is enlarged in dark places, so that most medical institutions are arranged in a special darkroom for examination when using ophthalmic examination equipment. In the darkroom, high-brightness light or lower-brightness peripheral illumination is not used as much as possible, so that the pupil of the tested person is enlarged as much as possible when the tested person is tested, and more light can be used when the testing device is used for testing.
While darkroom is a great aid to the ophthalmic inspection apparatus in acquiring more accurate data, darkroom inspection requires a special room and lighting design for the inspection environment. Meanwhile, because the darkroom lacks illumination, a user cannot conveniently observe the condition of a detected person in the darkroom, and under the condition of poor detection matching degree, for example, a child with low young age, the darkroom is difficult to detect. Finally, when more inspection devices exist in the same darkroom, the security of the personnel or the equipment is easily affected by the accident of the testee in the darkroom due to the lack of illumination when the environment is complex. For these reasons, many of the prior art organizations have abandoned the use of darkroom in the use of ophthalmic examination equipment, and the examination in a normal environment has problems of poor measurement results or slightly low data accuracy.
Disclosure of Invention
The invention aims to solve the problems that when an ophthalmic examination device is used, a darkroom is abandoned, and the measurement effect is poor or the data accuracy is slightly low when the examination is performed in a common environment, and provides an ophthalmic examination auxiliary device based on facial eye feature recognition.
The aim of the invention can be achieved by the following technical scheme:
the ophthalmic examination auxiliary equipment based on the facial eye feature recognition comprises an examination auxiliary device, wherein the examination auxiliary device is provided with an infrared camera and an image processing system, and the infrared camera is in communication connection with the image processing system;
the infrared camera is used for shooting a front image of the detected person;
the specific working process of the image processing system is as follows:
step 1: carrying out gray scale and binarization processing on the image of part of the face to obtain a binarized image;
step 2: after the identified eye features appear in the auxiliary equipment camera window, searching pupil positions in the eyes through eye structure identification and sight line calculation;
step 3: and calculating parameters of the long and short axes, the central point and the horizontal included angle of the pupils through the fitted ellipse to obtain positions and directions of the two pupils, judging whether the edge distances of the two pupils from the camera picture are symmetrical or not, and judging whether the connecting line of the two pupils is kept horizontal with the camera picture or not, and if the allowable error is exceeded, adjusting the sight line of the checked person.
As a further scheme of the invention: in step 1, according to the positions of pixels in the image and the symmetrically distributed abstract shape characteristics, judging whether the image photographed by the infrared camera of the auxiliary equipment at present accords with human eye characteristics, if so, entering the next step of eye structure recognition and sight line calculation, and if not, putting the head at a proper position by a display screen and voice prompt to the testee.
As a further scheme of the invention: in step 1, slicing and segmenting the image, wherein the segmentation fineness is 50×50-25×25, and obtaining a denoising image of the eye position.
As a further scheme of the invention: in step 2, after the eye image is obtained, identifying the pupil image edge through a Soble edge detection algorithm, wherein the Soble algorithm convolution algorithm formula is as follows:;
a represents an original image, gx and Gy represent the horizontal gray value and the vertical gray value of each pixel of the image respectively, and finally the gray value of the point is as follows:。
as a further scheme of the invention: in step 2, after obtaining an image edge through a Soble algorithm, dividing the image according to line edges, taking out black pixels in the infrared gray level image, fitting pixels of an approximate ellipse part according to calculation to form an ellipse, and using a least square method to make ellipse fitting, wherein the fitted ellipse is the pupil of a normal human eye.
As a further scheme of the invention: the ellipse fitting process is specifically as follows:
the fit ellipse equation is set as:;
the accuracy of the fit is determined by the sum of squares of the measured errors, the smaller the error the higher the accuracy, the error function being:
;
in order to take the minimum error, each coefficient bias is set to be 0, an extreme point is obtained through calculation, and then 6 values of a, b, c, d, e and f are solved, wherein the formula is as follows:
;
and obtaining coefficient values of a, b, c, d, e and f by using a formula, and then substituting the following parameter formulas to obtain the coordinates of the center point, the short axis length, the long axis length and the axis position angle of the ellipse, wherein the ellipse can be fitted by the following parameter formulas:
;
wherein a, b, c, d, e, f represent position parameters, x i And y i Representing the image measurement points.
As a further scheme of the invention: the head position of the detected region of the detection auxiliary device is provided with a light blocking structure, so that a darkroom effect is formed.
As a further scheme of the invention: the ophthalmic examination auxiliary equipment is also provided with a loudspeaker and a display screen, and language and graphic instructions are respectively and correspondingly given through the loudspeaker and the display screen, so that the examination position of the examined person is adjusted.
The invention has the beneficial effects that:
the ophthalmic examination auxiliary equipment simulates darkroom conditions in a complex environment or an environment unsuitable for setting the darkroom, and helps the ophthalmic examination equipment to improve measurement accuracy and stability; and the speed and accuracy of the ophthalmic examination can be obviously improved, the working strength of operators is reduced, the measurement accuracy is improved, and the ophthalmic examination flow is optimized.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a schematic view showing the structure of an examination assisting apparatus of the present invention in an ophthalmic examination instrument;
fig. 2 is a schematic view of the structure of the inside of the inspection assisting device of the present invention.
In the figure: 1. an ophthalmic examination apparatus; 2. an infrared camera; 3. a horn; 4. a display screen; 5. an inspection assisting device; 6. a light blocking structure.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1-2, the present invention is an ophthalmic examination auxiliary device based on facial eye feature recognition, comprising an ophthalmic examination apparatus 1;
the ophthalmic inspection instrument 1 is provided with a U-shaped inspection auxiliary device 5, the inspection auxiliary device 5 is internally provided with an infrared camera 2 and an image processing system, and the infrared camera 2 is in communication connection with the image processing system;
an infrared camera 2 for capturing a front image of a subject; the infrared camera 2 has the advantages that the influence of visible light on the measuring effect of an ophthalmic instrument can be avoided, meanwhile, the required face picture can be captured through the infrared camera 2, and the recognition effect is improved; considering the positions of the infrared camera 2 and the equipment, the position of the human face, because of the position and distance limitation of the auxiliary equipment, the image can not intercept the full-face image of the human and can intercept only part of the human face image;
the image processing system is used for processing the infrared image acquired by the infrared camera 2, identifying the eyes of a detected person, and tracking the shape of the iris of the eyeball so as to realize tracking and identification of the movement state of the eyeball;
the inspection auxiliary device 5 is provided with a light barrier in the head placement area, and by arranging the light barrier, the external light environment during the inspection by using the ophthalmic inspection instrument 1 can be controlled to simulate the darkroom environment, so that the interference of external light on the ophthalmic inspection is reduced as much as possible, the pupil of the inspected person is enlarged as much as possible, and the accuracy of the measurement data acquired by the ophthalmic inspection equipment is improved;
the auxiliary checking device 5 is also provided with a loudspeaker 3 and a display screen 4, and the checking position of the checked person is adjusted by arranging the loudspeaker 3 and the display screen 4 to respectively give out language and graphic instructions correspondingly, wherein the display screen 4 aims at the patient with poor hearing, and the direction needing to be adjusted is displayed through the display screen 4 for the checked person to refer to; the display screen 4 is a low-brightness display screen, so that the interference of light rays of the display screen 4 on a patient is reduced;
the auxiliary inspection equipment is also provided with a Bluetooth and USB data interface, can be in data communication with the ophthalmic equipment through a Bluetooth or USB data line, and can control the ophthalmic equipment to measure through the Bluetooth or USB data line when the auxiliary inspection equipment finds the most suitable measurement condition, so that automatic measurement is realized, and the measurement efficiency and the success rate of the ophthalmic inspection equipment are improved;
the auxiliary examination device is also provided with a remote controller, when some special patients, such as blind patients, severe cataract patients and the like, are encountered, the eye structures of the patients are different from those of most people, the automatic identification of eyeball tracking is invalid or is wrong, the examination cannot be automatically completed, at this time, an operator can control the auxiliary examination device to play different prompt signals (voice and images) through the remote controller and manually track the eyeball positions through the remote controller, so that the measurement success rate of the auxiliary eye examination device is realized.
Example 2
Based on the above embodiment 1, since the captured image is a partial image of the face, and there is no feature of the mouth, the ear, the face, etc., the conventional face recognition algorithm cannot function; the image processing system therefore comprises the steps of:
step 1, carrying out gray scale and binarization processing on an image of a part of human face to obtain a binarized image, judging whether the image photographed by an infrared camera 2 of the auxiliary equipment at present accords with human eye characteristics or not according to abstract shape characteristics such as positions and symmetrical distribution of pixels in the image, if so, entering the next step of eye structure recognition and sight line calculation, and if not, prompting a subject to put the head at a proper position through a display screen 4 and voice;
because of the difference between the human eye structure and the facial skin, the image is binarized, and then the larger numerical characteristic difference exists; then, slicing and segmenting the image, wherein the segmentation fineness is adjusted from 50 to 25 according to conditions so as to obtain a denoised image of the eye position, and the denoised image is obtained;
step 2, after the identified eye features appear in the auxiliary equipment camera window, further searching pupil positions in the eyes;
because the approximate pixel position of the eyes in the image can be judged through the binarized noise reduction image before, and the eye picture is cut out independently;
the pupil position finding process is specifically as follows:
step 21: after the eye image is obtained, pupil image edges are identified through a Soble edge detection algorithm, and a Soble algorithm convolution algorithm formula is as follows:
;
a represents an original image, gx and Gy represent the horizontal gray value and the vertical gray value of each pixel of the image respectively, and finally the gray value of the point is as follows:;
step 22: the focal length and the picture area of a camera of the equipment are known, after an image edge is obtained through a Soble algorithm, the image is segmented according to line edges, black pixels in an infrared gray image are taken out, pixels of an approximate ellipse part are selected according to calculation to fit an ellipse, a least square method is used for carrying out ellipse fitting, and the fitted ellipse is the pupil of a normal human eye;
the ellipse fitting process is specifically as follows:
the fit ellipse equation is set as:;
the accuracy of the fit is determined by the sum of squares of the measured errors, the smaller the error the higher the accuracy, the error function being:
;
in order to take the minimum error, each coefficient bias is set to be 0, an extreme point is obtained through calculation, and then 6 values of a, b, c, d, e and f are solved, wherein the formula is as follows:
;
and obtaining coefficient values of a, b, c, d, e and f by using a formula, and then substituting the following parameter formulas to obtain the coordinates of the center point, the short axis length, the long axis length and the axis position angle of the ellipse, wherein the ellipse can be fitted by the following parameter formulas:
;
wherein a, b, c, d, e, f represent position parameters, x i And y i Representing image measurement points;
step 3: according to the physiological characteristics of human beings, the center point of the pupil elliptical plane is considered to be approximately the direction of sight, and because of the relationship between the pupil and the angle of the camera, the length of the long and short axes of the pupil elliptical plane and the included angle between the long and short axes and the horizontal plane can be changed differently, and the closer the camera is seen, the closer the long and short axes are, and the more parallel the camera is;
obtaining the position and direction of two pupils by fitting ellipse, calculating parameters of long and short axes, central points and horizontal included angles of pupils, and judging whether the edge distances of the two pupils from a camera picture are symmetrical or not and whether connecting lines of the two pupils are kept level with the camera picture or not by utilizing the characteristic of face symmetry, wherein if the allowable error is exceeded, the error range is +60 degrees to-60 degrees; the head of the person to be examined is prompted to be righted leftwards or rightwards through voice, and after the head of the person to be examined is righted, if the pupils of the eyes are not rightwards, the person to be examined is guided to move the sight in the correct direction through the display device and voice;
preferably, because the human eye recognition of the device is mainly based on image processing and calculation of shape characteristics, the operation amount is not large, and the auxiliary device has higher requirements on the self volume size and the reduction of power consumption, so the device is not suitable for processing by using general purpose computing devices such as X86 or ARM, an FPGA (programmable gate array) chip is adopted as a main image processing and shape characteristic calculation module, an original image of an infrared camera is input into the FPGA operation chip, the FPGA chip processes and calculates binocular position and sight line parameters, a judgment result is transmitted to a display and voice module after the calculation is completed, and the display module and the voice module output corresponding graphics and voice according to received signals. The parallel processing characteristics of the FPGA are utilized in the processing, so that the requirement of an application scene on calculation can be met, and meanwhile, the product size and the power consumption can be greatly reduced.
Example 3
Based on the above embodiment 2, the present invention is a working method of an ophthalmic examination auxiliary device based on facial eye feature recognition, comprising the following steps:
step 1: firstly, a subject places a head in a designated area on an instrument according to an inspection requirement, an auxiliary equipment general sensing device senses that external light is blocked and then triggers, an object is considered to enter the detection area, an infrared camera 2 and a group of invisible infrared illumination light with the wavelength of 940nm are started at the moment, and when the sensing device is not triggered, the camera, the infrared illumination and the identification calculation are not started;
step 2: when the identified eye features appear in the auxiliary equipment camera window, further searching pupil positions in the eyes;
step 3: the method comprises the steps of obtaining the position and the direction of two pupils through fitting ellipses, calculating parameters of long and short axes, central points and horizontal included angles of the pupils, judging whether the edge distances of the two pupils from a camera picture are symmetrical or not and whether connecting lines of the two pupils keep level with the camera picture or not by utilizing the characteristic of face symmetry, prompting the head of a subject to swing left or right through voice if an allowable error is exceeded, and guiding the subject to move the sight towards the correct direction through a display device and voice if the pupils of eyes are not right looking at the camera after the head of the subject is swung right.
The working principle of the invention is as follows: the device integrates the infrared camera 2 and the image processing chip, when an inspector puts the head on the ophthalmic inspection instrument 1, the sensing device at the upper part of the inspection auxiliary device 5 senses that the head is put at a proper position, then the camera device is started, the common white light camera does not work or images poorly because of simulating a darkroom, so the infrared camera 2 is adopted to shoot the front image of the inspector, then the infrared image acquired by the infrared camera 2 is processed through the image processing chip, the eyes of the inspector are identified, and the shape of the iris of the eyeball is tracked, so that the tracking identification of the movement state of the eyeball is realized.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (7)
1. The ophthalmic examination auxiliary equipment based on the facial eye feature recognition is characterized by comprising an examination auxiliary device, wherein an infrared camera and an image processing system are arranged on the examination auxiliary device, and the infrared camera is in communication connection with the image processing system; the head position of the detected person in the detection area of the detection auxiliary device is provided with a light blocking structure, so that a darkroom effect is formed;
the infrared camera is used for shooting a front image of the detected person;
the specific working process of the image processing system is as follows:
step 1: carrying out gray scale and binarization processing on the image of part of the face to obtain a binarized image;
step 2: after the eye features are identified to appear in the auxiliary equipment camera window, the pupil position in the eyes is found through eye structure identification and sight line calculation;
step 3: and calculating parameters of the long and short axes, the central point and the horizontal included angle of the pupils through the fitted ellipse to obtain positions and directions of the two pupils, judging whether the edge distances of the two pupils from the camera picture are symmetrical or not, and judging whether the connecting line of the two pupils is kept horizontal with the camera picture or not, and if the allowable error is exceeded, adjusting the sight line of the checked person.
2. The device according to claim 1, wherein in step 1, it is determined whether the image photographed by the infrared camera of the device is in accordance with the human eye feature or not according to the position of the pixels in the image and the symmetrically distributed abstract shape feature, if the image is in accordance with the human eye feature, the device proceeds to the next eye structure recognition and line-of-sight calculation, and if the image is not in accordance with the human eye feature, the subject puts the head in a proper position through the display screen and voice prompt.
3. The ophthalmic examination auxiliary device based on facial eye feature recognition according to claim 2, wherein in step 1, the image is sliced, the fineness of the slicing is 50 x 50-25 x 25, and a denoised image of the eye position is obtained.
4. The ophthalmic examination auxiliary device based on facial eye feature recognition according to claim 1, wherein in step 2, after obtaining an eye image, pupil image edges are recognized by a Soble edge detection algorithm, and a Soble algorithm convolution algorithm formula is as follows:
;
a represents an original image, gx and Gy represent the horizontal gray value and the vertical gray value of each pixel of the image respectively, and finally the gray value of the point is as follows:。
5. the ophthalmic examination auxiliary device based on facial eye feature recognition according to claim 4, wherein in step 2, after obtaining an image edge through a Soble algorithm, dividing the image according to line edges, taking out black pixels in an infrared gray image, fitting pixels of a near-elliptical portion according to calculation to form an ellipse, and using a least square method to make ellipse fitting, wherein the fitted ellipse is the pupil of a normal human eye.
6. An ophthalmic examination assistance device based on facial eye feature recognition according to claim 5, wherein the ellipse fitting procedure is specifically as follows:
the fit ellipse equation is set as:
;
the accuracy of the fit is determined by the sum of squares of the measured errors, the smaller the error the higher the accuracy, the error function being:
;
in order to take the minimum error, each coefficient bias is set to be 0, an extreme point is obtained through calculation, and then 6 values of a, b, c, d, e and f are solved, wherein the formula is as follows:
;
and obtaining coefficient values of a, b, c, d, e and f by using a formula, and then substituting the following parameter formulas to obtain the coordinates of the center point, the short axis length, the long axis length and the axis position angle of the ellipse, wherein the ellipse can be fitted by the following parameter formulas:
;
wherein a, b, c, d, e, f represent position parameters, x i And y i Representing the image measurement points.
7. The ophthalmic examination assisting apparatus based on facial eye feature recognition according to claim 1, wherein the examination assisting means is further provided with a horn and a display screen, and the examination position of the subject is adjusted by providing the horn and the display screen with respective corresponding given language and graphic instructions.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310756639.1A CN116687340A (en) | 2023-06-26 | 2023-06-26 | Ophthalmic examination auxiliary equipment based on facial eye feature recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310756639.1A CN116687340A (en) | 2023-06-26 | 2023-06-26 | Ophthalmic examination auxiliary equipment based on facial eye feature recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116687340A true CN116687340A (en) | 2023-09-05 |
Family
ID=87837254
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310756639.1A Pending CN116687340A (en) | 2023-06-26 | 2023-06-26 | Ophthalmic examination auxiliary equipment based on facial eye feature recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116687340A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103082990A (en) * | 2011-10-28 | 2013-05-08 | 明达医学科技股份有限公司 | Three-axis positioning device and method of ophthalmologic detection instrument |
CN110472546A (en) * | 2019-08-07 | 2019-11-19 | 南京大学 | A kind of contactless eye movement characteristics extraction element of infant and method |
CN110680275A (en) * | 2019-10-21 | 2020-01-14 | 徐明娜 | Binocular multispectral pupil light reflex quantitative measuring instrument |
CN211094003U (en) * | 2019-08-06 | 2020-07-28 | 甘肃声源康贸易有限公司 | Eye shake inspection device |
CN113342161A (en) * | 2021-05-27 | 2021-09-03 | 常州工学院 | Sight tracking method based on near-to-eye camera |
CN115359548A (en) * | 2022-07-22 | 2022-11-18 | 吉林大学第一医院 | Handheld intelligent pupil detection device and detection method |
-
2023
- 2023-06-26 CN CN202310756639.1A patent/CN116687340A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103082990A (en) * | 2011-10-28 | 2013-05-08 | 明达医学科技股份有限公司 | Three-axis positioning device and method of ophthalmologic detection instrument |
CN211094003U (en) * | 2019-08-06 | 2020-07-28 | 甘肃声源康贸易有限公司 | Eye shake inspection device |
CN110472546A (en) * | 2019-08-07 | 2019-11-19 | 南京大学 | A kind of contactless eye movement characteristics extraction element of infant and method |
CN110680275A (en) * | 2019-10-21 | 2020-01-14 | 徐明娜 | Binocular multispectral pupil light reflex quantitative measuring instrument |
CN113342161A (en) * | 2021-05-27 | 2021-09-03 | 常州工学院 | Sight tracking method based on near-to-eye camera |
CN115359548A (en) * | 2022-07-22 | 2022-11-18 | 吉林大学第一医院 | Handheld intelligent pupil detection device and detection method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8708490B2 (en) | Method and a device for automatically measuring at least one refractive characteristic of both eyes of an individual | |
US20160038069A1 (en) | Eye Tracking Headset and System for Neuropsychological Testing Including the Detection of Brain Damage | |
CN106774863A (en) | A kind of method that Eye-controlling focus are realized based on pupil feature | |
US20110242486A1 (en) | Autism diagnosis support apparatus | |
WO2021135557A1 (en) | Artificial intelligence multi-mode imaging analysis apparatus | |
KR20140103900A (en) | System and methods for documenting and recording of the pupillary red reflex test and corneal light reflex screening of the eye in infants and young children | |
CN110279391B (en) | Eyesight detection algorithm for portable infrared camera | |
CN111295129B (en) | Visual acuity examination | |
KR101812249B1 (en) | Automatic measurement machine of strabismus | |
US20230084582A1 (en) | Image processing method, program, and image processing device | |
CN115590462A (en) | Vision detection method and device based on camera | |
CN106725280B (en) | A kind of slant visibility measuring device | |
CN107014592B (en) | Safety goggles visual field detection system and detection method | |
Bhangdiya | Cholesterol presence detection using iris recognition | |
CN111588345A (en) | Eye disease detection method, AR glasses and readable storage medium | |
CN116687340A (en) | Ophthalmic examination auxiliary equipment based on facial eye feature recognition | |
CN115670370A (en) | Retina imaging method and device for removing vitreous opacity spots of fundus image | |
RU2352244C2 (en) | Method of measurement of fast movements of eyes and deviations of solid vision and device for its realisation | |
CN113197542B (en) | Online self-service vision detection system, mobile terminal and storage medium | |
CN111419173B (en) | Macular pigment density measurement method and device based on fundus image | |
CN108742510B (en) | Oblique vision and horizontal torsion angle detector suitable for children with low age | |
JP2015123262A (en) | Sight line measurement method using corneal surface reflection image, and device for the same | |
CN113116292B (en) | Eye position measurement method, device, terminal and equipment based on eye appearance image | |
CN112043235B (en) | Portable eyeball static rotation measuring instrument and method for measuring eyeball rotation angle by utilizing same | |
CN112587083B (en) | Visual processing method, device and computer storage medium |
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 |