Unlock instant, AI-driven research and patent intelligence for your innovation.

Upper eyelid droop image measurement method based on static photo face recognition

A face recognition and image measurement technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of patients being unsuitable and relying on the recognition of corneal light points, so as to improve accuracy and objectivity, save money and improve medical treatment resources, optimize the effect of medical resources

Active Publication Date: 2019-09-06
ZHEJIANG UNIV
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing computer-aided diagnosis techniques for ptosis still rely on the identification of corneal lig

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Upper eyelid droop image measurement method based on static photo face recognition
  • Upper eyelid droop image measurement method based on static photo face recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described below in conjunction with embodiment.

[0031] Embodiments of the present invention and its implementation process are as follows:

[0032] Step 1: Static facial photos of 66 patients (132 eyes) with ptosis who visited the ophthalmology center of a hospital between November 2016 and May 2017 were collected.

[0033] Patients ranged in age from 1 to 40 years, including 50 cases of unilateral ptosis and 16 cases of bilateral ptosis. Ask the patient to look ahead, paste a circular marker (diameter 10mm) on the forehead, and under the same lighting conditions, use a Canon 500D camera and a 100mm macro lens to take pictures of eyes open in a natural state at a distance of 1m in front of the patient (resolution rate of 4752×3168 pixels).

[0034] The actual MRD1 and MRD2 of the patient's eyes were measured by an experienced oculoplastic specialist following clinical standard methods.

[0035] Step 2: Use the open source face ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an upper eyelid droop image measurement method based on static photo face recognition. The method includes: acquiring a face front image, processing the face front image to obtain a face area, and further obtaining an eye image area, wherein the preprocessing includes graying and binaryzation; obtaining the center position of the iris through positioning, and obtaining theradius of the iris through the relation between the center position of the iris and the outline of the outer edge of the iris; obtaining the pixel spacing MRD1 from the center position of the iris tothe upper eyelid edge and the pixel spacing MRD2 from the center position of the iris to the lower eyelid edge; obtaining the resolution size relation of the image by using the actual size of the markand the pixel size, and further obtaining the actual sizes of the MRD1 and the MRD2. The method can automatically detect the severity degree of the upper eyelid sagging, thereby improving the accuracy and objectivity of upper eyelid sagging diagnosis, avoiding the trouble of manual measurement in an image processing mode, and providing possibility for physical examination screening, remote medical treatment and the like.

Description

technical field [0001] The invention relates to an eye image processing method, in particular to an image measurement method for ptosis based on still photo facial recognition. Background technique [0002] Ptosis is a common ophthalmic plastic disease, which not only affects the appearance and visual function of patients, but also is easily accompanied by complications such as myopia, amblyopia and strabismus, which adversely affects the quality of life of patients. Therefore, early diagnosis and surgical intervention of ptosis are very important to improve the prognosis of patients. Ptosis correction surgery is considered to be the most challenging surgery in the field of ophthalmic plastic surgery. In order to obtain a more ideal surgical effect, a comprehensive specialist examination is required before surgery to evaluate the pathogenesis and ptosis status of ptosis. Margin reflex distance (MRD) is an internationally accepted index for evaluating the severity of blepha...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/46G06T7/00G06T7/13G06T7/70
CPCG06T7/0012G06T7/13G06T7/70G06T2207/10004G06T2207/30041G06V40/171G06V40/161G06V40/193G06V10/44
Inventor 叶娟钱大宏楼丽霞杨龙召朱琰王少泽
Owner ZHEJIANG UNIV