A New Method of Face Localization Based on Symmetrical Features
Chang Xin-hua · Computer Engineering and Science · 2006
This paper proposes a new method of face localization in complex poses. The main idea is to use the symmetry of human faces. First, skin regions are detected based on a model of skin color. Second, based on the observation that the eye area is at a low gray level and great gradient, we can get the finite candidate regions of eyes and match these regions to find the best matches. Experimental results are given to show the robustness and effectiveness of the method in complex conditions.