摘要
针对传统人脸特征点定位方法中存在的算法复杂、鲁棒性差以及精确度低等问题,本文提出一种基于肤色特征的人脸特征点自动定位方法.首先对预处理后的图像在多个色彩空间中利用肤色特征实现人脸区域的精确定位;然后,在人脸区域内根据各特征部位的特性构造色度模型函数来标定其特征区域;最后,在特征区域内完成人脸特征点的自动定位.实验结果表明,该算法简单、鲁棒性较高,且能够快速高效地实现人脸特征点定位.
Considering the high computational complexity ,poor robustness and low accuracy of traditional algorithm positioning facial feature points ,a method based on skin color fea-ture for automatic positioning facial feature points is proposed in this paper .First ,the face region was positioned precisely using skin color feature in the multi-skin color space after pretreating the face image .Next ,the feature regions were positioned using color model func-tion according to the characteristics of each part in the face region .Finally ,the facial feature points were positioned automatically in the feature region .The experiments show that this method is not only simple and robust ,but also capable of positioning the facial feature points quickly and efficiently .
出处
《陕西科技大学学报（自然科学版）》
2014年第1期156-160,168,共6页
Journal of Shaanxi University of Science & Technology
基金
河南省科技厅科技基础研究项目(132300410395)
关键词
人脸特征点
多色彩空间
人脸检测
特征区域
自动定位
facial feature points
multi-skin color space
face detection
feature regions
au-tomatic positioning
