A Color-Triangle-Based Approach to the Detection of Human Face

A robust and e$cient human face detection system that can detect multiple faces in complex backgrounds is presented in this paper. The proposed system consists of two primary parts. The "rst part is to search for the potential face regions. The second part is to perform face verixcation. Our system can conquer di!erent sizes, di!erent lighting conditions, varying pose and expression, and noise and defocus problems. In addition to overcoming the problem of partial occlusion of mouth and sunglasses, the system can also detect faces from the side view. Experimental results demonstrate that an approximately 98% success rate is achieved. The experimental results reveal that the proposed method is better than traditional methods in terms of e$ciency and accuracy. 2001 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.