摘要
本文研究了复杂多变人脸的检测和定位问题,提出了一种新的基于对称特征的人脸定位方法。该方法基于肤色特征提取出人脸,根据眼睛的颜色和梯度特征在肤色区找到眼睛可能存在的有限的候选区域;根据人脸的对称特征把这些候选区域分别进行匹配,找到最佳匹配的区域就是眼睛区域。实验证明,这种方法在复杂姿态和复杂表情以及戴眼镜的情况下有很强的稳健性。
This paper proposes a new method of face localization in complex poses. The main idea is to use the symmetry of human faces. First, skin regions are detected based on a model of skin color. Second, based on the observation that the eye area is at a low gray level and great gradient, we can get the finite candidate regions of eyes and match these regions to find the best matches. Experimental results are given to show the robustness and effectiveness of the method in complex conditions.
出处
《计算机工程与科学》
CSCD
2006年第10期54-56,共3页
Computer Engineering & Science
基金
国家自然科学基金资助项目(60172022)
关键词
对称特征
人脸定位
区域匹配
symmetrical feature
face localization
area matching
