Face detection using evolutionary agents

This paper presents a novel approach to the detection, segmentation and localization of human faces in color images. A number of agents with evolutionary behaviors are uniformly distributed in the 2-D image environment to search the skin-like pixels and locate each face-like region by evaluating the local color distribution. The possible face-like regions can be segmented by analyzing the relationship between each region detected by different family of agents. Finally, the shape information of each located face-like region is examined and those regions that can not be approximated to a reasonable face-like elliptical shape or have smaller size are ignored. Experimental results show that the proposed approach is fast and has a high detecting rate