Face and eye detection in images using skin color segmentation and circular hough transform

Abstract

The aim of this project is to develop a technique to control a wheel chair by tracking the eye movement of a person. This device will assist those severely disable people, who cannot move their hands and legs, to easily move just by the motion of their eyes. The first step is to locate the face of the person. Face detection is done by segmentation through skin color using an adaptive thresholding method. The advantage of adaptive thresholding method is that it adapts automatically to the skin color of the user. After face detection, eyes will be detected and tracked. The basic Houghman circle detection algorithm is used to process the image to detect the iris. The position of the iris is then compared with respect to the calibrated center point with the help of a square grid on which an algorithm is applied to calculate the speed and angle of the wheel chair.