Glasses Detection and Extraction by Deformable Contour

To achieve a face recognition system robust to the presence of glasses, we have developped a glasses detection and extraction algorithm. Detection is realized using edge information within a small area dened between the eyes. Extraction is achieved with a deformable contour, combining edge features such as strength and orientation and geometrical features such as convexity, symmetry, smoothness and continuity. The nal position of the deformable contour is obtained using dynamic programming. Experimental results demonstrate the e ectiveness of the method, and the robustness to the variation of glasses' shapes and colours.

• Type: Conference
• Year: 2000
• Where: ICPR
• Authors: Zhong Jing, Robert Mariani
• Keywords: Computer Vision, Deformable Contour, Extraction Algorithm, Glasses Detection, ICPR 2000