Spatial histogram features for face detection in color images

This paper presents a novel face detection approach in color images. We employ spatial histograms as robust features for face detection. The spatial histograms consist of marginal distribution of color image information. Facial texture and shape are preserved by the spatial histogram representation. A hierarchical classifier combining histogram matching and support vector machine is utilized to identify face and non-face. The experiments show that this approach performs an excellent capability for face detection, and it is robust to lighting changes.