Abstract: This paper improves a method of face recognition based on profile. The vertical direction of face is determined by the PCA at the random pose. Based on surface registration, the symmetrical surface and symmetrical profile are extracted. Curvatures on the symmetrical profile are calculated to extract the other three transverse profiles. Four profiles are sampled and standardized. Only the valuable parts are used as the input of ICP algorithm for face recognition. Experimental results show that the method performs well and provides higher recognition rate and lower false recognition rate.

Key words: 3D face recognition, profile, ICP

摘要： 对已有的基于轮廓线的人脸识别方法进行了改进，在人脸的任意位置利用PCA自动确定人脸纵方向，采用网格配准方法提取对称面和对称轮廓线。通过计算对称轮廓线上的曲率，提取其他3条横向轮廓线。对提取的4条轮廓线进行重采样和归一化，截取轮廓线的有价值部分作为ICP算法的输入，进行人脸识别。试验证明，该算法将人脸识别率从原来的86.5%提高到了94%，降低了误识率。

关键词: 三维人脸识别, 轮廓线, ICP算法

CLC Number: 

• TP301.6