基于几何约束的人脸检测研究

Research on Geometric Constrains-Based Face Detection

提出并实现了一种新的基于颜色空间的人脸检测算法;在充分考虑人脸与头发的颜色特征与几何关系的基础上,给出了一种用于人脸和头发表达的几何模型,在对肤色区域和头发区域分别进行检测后,根据不同区域之间的几何关系,通过几何约束对人脸和头发可能存在的区域进行特征判别。对不同姿态的人脸进行检测的结果表明了算法的可行性和鲁棒性。

A novel face detection algorithm is presented and realized in this paper. Considering the different color features and geometric relations between the face the hair, a geometric model is proposed to represent the face region and the hair region. After a coarse detecting for the skin likeness regions and hair likeness regions, the geometric constrains of different regions are adopted to detect the face and the hair. Different detecting results indicate that the proposed method is both efficient and robust.