Eyeball motion analysis method and device and storage medium

Abstract

The invention discloses an eyeball motion analysis method and device and a storage medium. The eyeball motion analysis method comprises the steps of acquiring a real-time image taken by a camera shooting device, and extracting a real-time face image from the real-time image; inputting the real-time face image into a pre-trained eye average model, and recognizing n1 orbit feature points and n2 eyeball feature points representing an eye position in the real-time face image; determining an eye region according to the (n1+n2) feature points, and judging whether the eye region is a human eye regionor not by using a human eye classification model; if so, acquiring the motion direction and the motion distance of the eyeball in the real-time face image according to x, y coordinates of the n1 orbit feature points and the n2 eyeball feature points in the real-time face image. According to the invention, motion information of the eyeball in the real-time face image is calculated according to thecoordinates of the eye feature points, and analysis for the eye region and real-time capturing for eyeball motions are achieved.

Description

technical field [0001] The present invention relates to the technical field of computer vision processing, in particular to an eye movement analysis method, device and computer-readable storage medium. Background technique [0002] Eye motion capture is a biometric recognition technology for user eye motion recognition based on human facial feature information. At present, the application fields of eye motion capture are very wide, and it plays a very important role in many fields such as financial payment, access control and attendance, and identification, and brings great convenience to people's life. The general product method is to use professional equipment to detect the change of the electric field around the eyeball, so as to realize the capture of the eyeball; or use the camera equipment to identify the change of the iris angle to realize the tracking of the eyeball. [0003] However, both of the above two methods have shortcomings. The first one requires wearing pr...

AI Technical Summary

Problems solved by technology

[0003] However, both of the above two methods have shortcomings. The first one requires professional equipment and is very demanding on the environment.

The second type, iris detection, requires the distance between the human eye and the camera to be relatively close, and the iris detection speed is slow, which is not suitable for real-time use

Images