FACE DETECTION BASED ON VECTOR QUANTIZATION IN COLOR IMAGES
Zhe‐Ming Lu, Xiu-Na Xu, Jeng‐Shyang Pan · 2006
Abstract. Nowadays, face detection plays important roles in many applications, such as: human-computer interaction, security and surveillance, face recognition etc. In this paper, a novel scheme for human face detection in color images under non-constrained scene conditions is presented. Color clustering and filtering based on the vector quantization (VQ) technique are performed on the original input image, providing binary skin color regions. In order to provide a set of candidate face areas, constrains related to shape and size of faces are considered. Finally, mouths are searched in all of the candidate face regions by means of mouth detector to verify each face region. Experimental results show that the proposed method is efficient and robust to head rotation to some extent.