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

A Regression-Based Judgment Method of Human Eye State

A state judgment, human eye technology, applied in the field of video analysis, can solve problems such as unreasonable eye state classification, and achieve the effect of easy implementation, good robustness and flexible application

Inactive Publication Date: 2019-02-26
ZHEJIANG ICARE VISION TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is not reasonable to simply use a classifier to classify eye states

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
  • A Regression-Based Judgment Method of Human Eye State
  • A Regression-Based Judgment Method of Human Eye State

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with the accompanying drawings.

[0020] Step 1: Mark the eyelid position of the human eye in the sample. The sample contains at least 10,000 face images, and should include different states of opening and closing; human eyes mark the lowest point of the upper eyelid and the highest point of the lower eyelid, and the left and right corners of the human eye.

[0021] Step 2: Generate a normalized human eye sample x. Such as figure 1 , first take the center of the eyes as the benchmark, and perform a similar transformation on all the faces so that their center positions of the eyes are aligned. In this way, the distance between the centers of the eyes of all face images is the same, using D eye_cent Indicates that the center of the eye is the intersection of the midlines of the two canthus and the midlines of the upper and lower eyelids;

[0022] Then, taking the center of the eye as the center, cut ...

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 relates to a human eye state judgment method based on regression. The method comprises the steps that firstly, the positions of eyelids of a human eye in a sample are marked, and a normalized human eye sample x is generated; secondly, the human eye sample x and the opening degree d calculated by the distance 1 of the upper eyelid and the lower eyelid are used as training data (x, d), the training data are input into a statistical regression algorithm to conduct training, and a regression model M is obtained; then for a new human eye image, xi is input into the regression model M with normalization being as the standard, and the opening degree di is obtained and output; at last, according to different application demands, scenes and users, threshold values T are chosen; eye closing is detected, if di is smaller than or equal to Tc, it represents eye closing, Tc is the eye closing threshold value, if di is larger than or equal to To, it represents eye opening, and To is the eye opening threshold value. According to the human eye state judgment method based on regression, under the condition that the eyelids do not need to be precisely detected, the continuous closing and opening degree of the human eyes is obtained automatically by a statistical learning technology. The human eye state judgment method is easy to implement, good in robustness, and flexible in application.

Description

technical field [0001] The invention belongs to the technical field of video analysis, and relates to a regression-based human eye state judgment method. Background technique [0002] In face image analysis applications such as fatigue detection, it is necessary to automatically detect the closed state of human eyes. Existing methods can be divided into two categories. One is to accurately detect the eyelid contour line through edge analysis, active shape model (ASM), texture model (AAM) and other image analysis methods, and directly judge whether the eyes are closed through the distance between the two eyelids; the other Through the method of statistical learning, a large number of eye-opening and eye-closing samples are used to train a classifier to classify the state of human eyes as open and closed. The first type of method is direct and can give the degree of opening and closing of the eyes. However, to accurately detect the eyelid contour line, the technical require...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/66
Inventor 尚凌辉蒋宗杰高勇于晓静
Owner ZHEJIANG ICARE VISION TECH