Human face detection using color spaces and region property measures

Abstract

Face detection is the first step in automated face recognition and the important cue to detect the human face is skin color. This proposed paper consists of two steps, the first step is to detect the more skinned region by the fusion of RGB, YCbCr skin color region and CIEL* a* b skin labeled image using HillClimbing segmentation with K-Means clustering. This step helps to simplify and improves the detection of human faces, since nonskin regions are eliminated. The second step is to locate the faces in a fused image by Region property measures. The proposed method has been tested on various real images and its performance is found to be quite satisfactory.