Human eye positioning method based on edge information integral projection

Abstract

The invention belongs to the field of machine vision and image processing and specifically relates to a human eye positioning method based on edge information integral projection. The human eye positioning method comprises determining a human face region by use of the skin color characteristic, establishing an edge strength information image by use of a Kirsch operator, performing integral projection in different polar angle directions to determine the human eye angle direction, performing differential accumulation operation on the edge strength of the angle direction of the human eye to determine the polar radius of the human eye, and then realizing polar coordinate positioning on the human eye. The human eye positioning method based on the edge information integral projection is applicable to the human eye recognition field.

Description

technical field [0001] The invention belongs to the field of machine vision and image processing, and relates to a human eye positioning method in a human face image, in particular to a human eye positioning method for performing integral projection on edge intensity information in a polar coordinate system. Background technique [0002] The detection and positioning of human eyes has always been a hot issue in the field of machine vision research, and has important application value in systems such as visual fatigue detection, eye tracking, and identity authentication. At present, the commonly used human eye detection methods can be roughly divided into three categories: detection methods based on statistics, detection methods based on knowledge, and detection methods based on projection functions. The statistical method is to use the obtained target samples and non-target samples to train the classifier to realize the detection of human eye targets. Such as neural network...

AI Technical Summary

Problems solved by technology

Such methods generally require more prior knowledge and are less versatile.

The detection method based on the projection function generally determines the face area according to the skin color feature, and then projects some information (such as grayscale) of the face image to the horizontal and vertical directions to determine the position of the human eye. This type of method can Effectively improve the positioning accuracy of the human eye from different angles. Generally speaking, it has the advantages of simple mechanism and easy implementation. However, in practical applications, there are also disadvantages that require relatively strict requirements for the posture of the human face. When the human face rotates at a certain angle When the two eyes are not on the same horizontal line, it is easy to cause human eye positioning errors. In addition, the gray information is unevenly distributed in the entire image, which also increases the error rate of human eye recognition and positioning.

Images