This paper presents an automatic face detection method based on feature Invariant and knowledge-based approaches. The proposed method can segment out a person's face from a given image that consists of a head-and-shoulders view of the person and a complex background scene. It involves an algorithm that exploits the feature invariant approach based on the spatial distribution characteristics of human skin color. Only skin color regions with faces or facial regions are segmented out from the background. Non-facial regions that fall within the same chrominance range will not be segmented. The method can differentiate non-facial facial regions based on the knowledge-based approach. It also informs users automatically if no facial region presents in the image. The performance of the face detection technique is illustrated by simulation results carried out on various test images database in . Comparison with existing technique in - is included to reveal the good performance of the proposed scheme.
|Title of host publication||Proceedings of the IEEE Region 10 Annual International Conference/TENCON|
|Publication status||Published - 01 Dec 2004|
|Event||IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering - Chiang Mai, Thailand|
Duration: 21 Nov 2004 → 24 Nov 2004
|Conference||IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering|
|Period||21/11/04 → 24/11/04|