Face Detection in Non-uniform Illumination Conditions by Using Color and Triangle-based Approach

This investigation develops an efficient face detection scheme that can detect multiple faces in color images with complex environments and non-uniform illumination conditions. The proposed scheme comprises two stages. The first stage adopts YES color and triangle-based segmentation to search potential face regions. The second stage involves face verification using a weighting mask function. The system can handle various sizes of faces, non-uniform illumination conditions, pose and changeable expression. In particular, the scheme significantly increases the execution speed of the face detection algorithm in complex backgrounds. A result of this study performs better than previous methods in terms of speed and ability to handle non-uniform illumination conditions.