A real time pupil location system using multiple illuminations clustering under varying environment

Abstract

In an eye gaze estimation system, pupil location is key part. And in order to get the position of pupil with high accuracy, edge detector algorithm is necessary. The canny edge detector is widely used in computer vision to locate sharp intensity changes and to find object boundaries in an image. In this paper, we make a improvement based on dynamic threshold of edge detection algorithm. It makes up for the disadvantage of traditional canny algorithm, which would lose some edges during detecting images with different situation like illumination, glass-wear and so on using fixed threshold.