Face detection system based on feature-based chrominance colour information

This paper presents a novel face detection system based on feature-based chrominance colour information from an image containing one face in indoor environment with non-uniform background. The face detection algorithm is based on the adapted chain code (ACC), eye detection and modified golden ratio (MGR). ACC is proposed to obtain a face boundary. MGR attempts to extract part of a face that includes eyes, eyebrows, nose and mouth, based on the detected eyes' positions. Experimental results show that the proposed algorithm is able to detect a face of near frontal with high accuracy. The database consists of faces with and without spectacles, wearing headscarf and without wearing headscarf.

[1]  David C. Gibbon,et al.  Multi-modal system for locating heads and faces , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[2]  Anil K. Jain,et al.  Face Detection in Color Images , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Narendra Ahuja,et al.  Detecting Faces in Images: A Survey , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Erik Hjelmås,et al.  Face Detection: A Survey , 2001, Comput. Vis. Image Underst..

[5]  A. Bouzerdoum,et al.  A Bayesian approach to skin color classification in YCbCr color space , 2000, 2000 TENCON Proceedings. Intelligent Systems and Technologies for the New Millennium (Cat. No.00CH37119).

[6]  Alberto Sanfeliu,et al.  Localization of human faces fusing color segmentation and depth from stereo , 2001, ETFA 2001. 8th International Conference on Emerging Technologies and Factory Automation. Proceedings (Cat. No.01TH8597).

[7]  L. Farkas,et al.  Anthropometric Facial Proportions in Medicine , 1986 .

[8]  Georgios Tziritas,et al.  Face detection in color images using wavelet packet analysis , 1999, Proceedings IEEE International Conference on Multimedia Computing and Systems.