Face detection in color images and video sequences

Abstract

Face detection is no longer necessarily correlated with face recognition. Instead it has been established as an important tool in the framework of many multimedia applications like indexing, scene classification and news summarization. Many face detection algorithms based on skin color characteristics have appeared in the literature. Most of them face generalization problems due to the skin color model they use. Moreover, their verification stage exclusively depends on simple shape features limiting the reliability of detection. In this work we present a Gaussian model of the skin color distribution whose parameters are re-estimated based on the current image I frame. In this way the generalization problem is limited. Furthermore the verification stage, applied in the detected skin segments, is based on a template matching variation providing a robust detection.