基于ASM和线段Hausdorff距离的人脸识别

Face recognition based on ASM and line Hausdorff distance

主动形状模型(ASM)是人脸特征定位的有效方法。针对ASM的不足,从初始定位、建模方法和搜索策略等三个方面进行了改进,提出了基于模块化ASM(MASM)的定位方法。实验结果表明,改进后的方法在定位准确度上有了较大提高。此外,利用模块化ASM定位得到的人脸轮廓及各器官的形状特征,采用线段Hausdorff距离(LHD)作为相似性测度,在CVL人脸数据库上进行人脸识别,获得了较好的识别效果。

The Active Shape Model （ASM） was an efficient method for facial features localization. In this paper, Modular ASM （MASM） was proposed which made improvements in three aspects which were initialization, model construction and search strategy. Experiments show the propsed method improves the accuracy of facial ＇features localization than the old method. Besides, the result of MASM for facial features localization is finally used in the extraction procedure of line edge map. Then Line Hausdorff Distance （LHD） is calculated as the features of face image. The recognition rate of the proposed method is high based on the CVL face database.