Face detection in color images using fusion of the chrominance and luminance channel decisions

摘要

We propose a new face detection model based on the fusion of the color and luminance channel decisions. Each of the two detection branches has its own technique of finding face candidates. We have also investigated the decision improvement of skin detection over the color channel by applying the conversion from the conventional RGB space into the 3D uncorrelated color space (UCS). One evaluates the performances of the proposed model by comparison to several standard color spaces.