摘要
为了提高主动形状模型(ASM)算法的性能,提出一种改进的ASM算法.首先,精确定位出瞳孔的位置用作平均形状模型的初始化;其次,采用全局形状模型、面部显著特征区域成分形状模型以及人脸面部的相似性构形相结合的办法来共同约束特征点的定位结果;最后,特征点周围采用Log-Gabor小波系数进行描述,并建立局部纹理模型,提高了算法对光照和噪声的鲁棒性.实验结果表明,与传统的ASM算法相比,该算法特征点定位精确度有显著的提高.
To improve active shape model （ASM） accuracy in facial feature points location in facial images, an improved ASM based algorithm is proposed. First, the irises are localized and utilized to initialize the shape model; Second, facial similar configuration, feature subspaces of global face shape model and salient feature local shape models are all employed to constrain the movement of feature points; at last, log-Gabor coefficients are used to describe the local texture distribution and build models for each feature point to increase the robustness to illumination change and other noises. Experimental results show that our algorithm performs significantly better than the traditional ASM.
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2007年第11期1411-1415,共5页
Journal of Computer-Aided Design & Computer Graphics
基金
国家自然科学基金(60475021)
