Face detection using color and symmetry information

Abstract

The localization of human faces in digital images is a fundamental step in the process of face recognition. This paper presents a face detection method based on color, local symmetry and geometry information of human face. The algorithm first detects most likely face regions or ROIs (Region- Of-Interest) from the image using skin color model and face outline model and produces a face color similarity map. Then it performs local symmetry detection within these ROIs to obtain a local symmetry similarity map. These two maps are fused to obtain potential facial feature points. Finally similarity matching is performed to identify faces between the fusion map and face geometry model under affine transformation. The output results are the detected faces with confidence values. Experimental results demonstrate its validity and robustness to identify faces under certain variations.