A novel approach for detecting human face with various poses

This paper describes a novel approach to detect the rough face and facial feature regions with various poses in gray intensity images. Using the eye edge information and gray distribution, an energy function is designed to evaluate whether the current rectangle in the image contains the eye region or not. Basing on the extracted eye region, the potential mouth region is evaluated as to whether it contains a mouth by using some rules. A genetic algorithm is used to perform the search process in the whole input image according to the value of an energy function. Experimental results show that the proposed approach is fast and reliable.