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不足,提出一种基于局部特征区域快速高效的人脸特征点自动定位方法。首先对经过预处理后的人脸图像利用改进的积分投影算法结合肤色特性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、具有较高的鲁棒性,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 for posi- tioning facial feature points, this paper proposed a fast and efficient method based on the local feature regions for automatic po- sitioning facial feature points. First, it positioned the face region precisely using an improved integral projection algorithm combined with color characteristics of the facial skin after pretreating the face image. Next, it positioned the feature regions ac- cording to the characteristics of each part in the face region. Finally, it positioned the facial feature points 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
《计算机应用研究》
CSCD
北大核心
2014年第4期1270-1272,共3页
Application Research of Computers
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
自动定位
积分投影
人脸检测
特征区域
facial feature points
automatic positioning
integral projection
face detection
feature regions
