A novel method for eye region detection in gray-level image

This paper describes a novel method to detect the rough eye regions with various positions on gray intensity images. Using the eye edge information and gray distribution, an energy function is designed to evaluate whether the current rectangle in image contains the eye region or not. Then a genetic algorithm is used to search the potential eye regions in the whole input image according to the value of energy function. Experimental results show that the proposed approach is fast and reliable.