基于曲率和积分投影的人脸特征检测

Facial Feature Detection Based on Curvature and Integral Projections

针对以往基于图像的人脸特征检测对光照敏感的缺陷,提出了一种基于3D数据的人脸特征检测算法.首先对人脸3D数据计算其主曲率,设定阈值进行人脸特征的初步分割得到二值化的分割图,然后在二值化图上进行水平和垂直积分投影进一步确定人脸特征的位置,最后利用人脸特征的先验拓扑知识对检测到的人脸特征进行验证.实验结果表明,该算法能够有效地提取人脸特征点,具有一定的鲁棒性.

To compensate for the illumination limitation of facial features detection in image, the paper is concentrated on the 3D facial features extraction, Firstly, surface curvatures, which can represent a local surface shape, are used in the segrhentation. Secondly, horizontal and vertical integral projections are performed on the segmented facial image to find feature locations. Finally, feature locations should also be validated using the geometric constraints and symmetry constraints. The experimental results on real range images of several faces are provided.