Circular hough transform based eye state detection in human face images

Abstract

Nowadays eye states are used as inputs to various applications such as facial expression recognition systems, human-computer interaction and driver fatigue detection systems. Especially with the pervasion of human computer interaction, eye state detection has drawn great attention in the past decade. In this study, an eye state detection system based on circular Hough transform has been offered. Initially, a face image is extracted from a given image. Eye pair images are obtained from this face image, and eyes are acquired from the eye pair images. After preprocessing, existence of circular iris structure is searched with the help of circular Hough transfrom within the eye image. Eyes are decided as open if iris is visible. © 2013 IEEE.