A Fast and Efficient Chin Detection Method for 2-D Scalable Face Model Design

For scalable and model-based coding of videophone sequence at very low bit rates, a 2-D scalable face model has to be designed. In this paper, an efficient algorithm is presented for the automatic detection of chin contour of a person face. The chin is first represented by a deformable template consisting of two parabolas. Then, a cost function is minimized to find the best fit of template to the chin. Finally, chin contour is detected by using active snake algorithm, which is initialised by the best fit of template. In order to get the smoother external force of active snake model, gradient vector flow (GVF) is used, which is derived from the edge distribution. Experimental results show that the proposed method can drive the snake model to the most optimal chin position. This method can be used for 2-D scalable face model design and 3-D face model adaptation.