An improved facial feature localization method based on ASM

Abstract

Active shape model is one of the commonly used-methods for facial feature localization. Regarding the traditional ASM excessively depends on the setting of the initial parameters of the model, a facial feature locating method based on improved ASM was presented. Firstly, we obtain the reconstructive parameters of the new gray image by example-based learning and use them to reconstruct the shape of the new image and compute the initial parameters of the ASM by the reconstructed facial shape. Then reduce the distance error between the model and the target contour by adjusting the parameters of the model. Finally get the model which is matched with the facial feature outline after several iterations. In contrast with the method of facial feature locating by conventional ASM, the improved ASM has higher accuracy and can locate the object feature rapidly