Eyeball movement identification method based on face identification

Abstract

The invention discloses an eyeball movement identification method based on face identification. The eyeball movement identification method based on the face identification includes: detecting an eyeball, performing edge detection on multiple images of a face, positioning an initialization feature point of the eyeball, and calculating a position and a ratio of the eyeball relative to the face according to the initialization feature point so as to obtain a face dimension angle normalization ratio; identifying the eyeball, obtaining a face image to be detected, and calculating positions of the eyeball in the face images according to the face dimension angle normalization ratio; identifying eyeball movements, identifying the positions of the eyeball in more than two face images, and identifying the eyeball movements according to position changes. The eyeball movement identification method based on the face identification can accurately position the eyeball on the face, and not only support eyeball identification on the static face, but also can support the eyeball identification on the face in dynamic video.

Description

technical field [0001] The invention relates to face recognition technology, in particular to an eye movement recognition method based on face recognition. Background technique [0002] Face recognition is a very popular research topic in the field of computer vision and pattern recognition, and has important applications in public security, communication, virtual reality, information retrieval, etc. In terms of public safety and information security, facial recognition-based facial features detection and facial expression recognition are fast and effective automatic identity verification methods. Currently, biometric-based recognition technologies mainly include: fingerprint recognition, retina recognition, iris recognition, gait recognition, vein recognition, face recognition, etc. Compared with other recognition methods, face recognition is easy to be accepted by users because of its direct, friendly and convenient features, and it will not cause any psychological barrie...

AI Technical Summary

Problems solved by technology

However, because the images are easily affected by the shooting environment, such as strong light or shadows, which reduce the difference between the eyeball and face pixels, it is impossible to accurately determine the position of the eyeball from these images

However, for this kind of phenomenon, most of the existing technologies use feature extraction and classification algorithms to identify eyeballs, but the premise is that the feature points have been manually marked out, and the manually marked feature points are assumed to be very accurate in positioning, but the actual The accuracy of manually marked feature point positioning is insufficient, which affects the accuracy of subsequent algorithms, so the current method of manual calibration will inevitably become the bottleneck of the recognition system

On the other hand, the existing methods to solve the above problems, such as the Snake method, the variable template method and the elastic graph matching method, all have the problems of slow processing speed, low accuracy and high implementation complexity. The effect is not ideal

Images