Human eye recognition system and method

Abstract

The invention discloses a human eye recognition system and method. The system comprises an identification module of a human eye area to be detected, a human eye detection module and a human eye weight recognition module, wherein the identification module of the human eye area to be detected is used for marking off the area to be detected of a left eye and a right eye on a human face area; the human eye detection module is used for detecting the target area of the left eye and the right eye from the area to be detected of a left eye and a right eye; the human eye weight recognition module is used for the weight calculation to the target area of the left eye and the right eye to obtain the human eye area; and the weight comprises the approximate degree of the size of the left eye and the right eye, the reasonable degree of the ratio of side length of the left eye area and the right eye area to the space between a left eye pupil and a right eye pupil, and an included angle between the ligature of the space between a left eye pupil and a right eye pupil and the horizontal direction. The human eye recognition system of the invention precisely positions the human eyes by three weights after detecting the target area of the left eye and the right eye, effectively solves the problem of positioning the target area of the human eyes and improves the accuracy of human eye recognition.

Description

technical field [0001] The present invention generally relates to the field of biometric feature recognition, and specifically relates to an auxiliary human eye detection system and method based on binocular structural weights. Background technique [0002] With the development of computer vision technology, more and more attention has been paid to face recognition and expression recognition, and human eye detection, as the prior condition of the preprocessing step of face recognition and expression recognition, its detection accuracy and speed directly affect the recognition process. Accuracy and speed, and the accuracy of human eye detection can effectively improve the accuracy and automation of face recognition and expression recognition. At present, most expression recognition and face recognition algorithms first locate the human eyes, then perform normalization, feature calculation, and feature point calculation based on the position information of the human eyes, and ...

AI Technical Summary

Problems solved by technology

Although the existing human eye positioning algorithm has achieved certain results, there are still problems, such as inaccurate positioning and the inability to locate multiple human eyes. Therefore, in many cases, a large amount of manual correction is still required in the human eye positioning process. This problem makes it difficult to Automate expression recognition and face recognition

Images