Face Detection Based on the Matching of Multiple Related Templates
Liang Lü · 2001
In this paper, a face detection algorithm based on the matching of multiple related templates is presented. The templates are a series of related types: eyes-in-whole and face itself, which are produced by affine transforms varying in stretch and pose from an average frontal face. The eyes-in-whole templates are used as the first search step for face candidates and then the face templates are matched. Finally some heuristic rules are used to verify face detection results. Experimental results obtained from images containing frontal and in-plane rotated faces demonstrate the feasibility of this approach.