一种新的多视角背景下人脸检测方法  

A Human Face Detection Algorithm Based on Skin and Depth of a Feature Binary Tree

作　　者：尹远 何强[1] 文凯[1,2] 

机构地区：[1]重庆邮电大学通信新技术应用研究中心,重庆400065 [2]重庆信科设计有限公司,重庆400065 [3]中国电信股份有限公司重庆分公司,重庆400065

出　　处：《重庆工商大学学报（自然科学版）》2017年第6期1-8,共8页Journal of Chongqing Technology and Business University:Natural Science Edition

基　　金：2015年重庆市研究生创新科研项目(CYS15166)

摘　　要：针对实际生活中普遍存在的多视角、多人脸检测问题,提出了一种新的分类器训练方法及人脸检测的解决方案;首先采用NPD差分特征对人脸特征进行描述,NPD特征通过判断两个像素值间相对差异对人脸进行描述,其特征值可从二维表直接获取,能大大节省训练时间;同时提出了一种深度二叉特征树结构来训练分类器,可有效结合特征间的关联性,将训练得到分类器与肤色算法相结合来提高检测速度;通过在CMU人脸数据库上对所提出算法进行验证,仿真结果证明在多人脸、多视角检测背景环境下,该算法较Ada Boost算法在检测率提高了8.7%,误检率降低了4.1%,检测速度提高了27.7%。In this paper,a new classifier training method and human face detection solution are proposed for multi-face and multi-view face detection problems which are prevalent in real life. Firstly,NPD（ Normalized Pixel Difference） feature is used to describe the facial feature,the NPD feature describes the human face by judging the relative difference between the two pixel values,its eigenvalues can be obtained directly from the two-dimensional table,which can greatly save the training time. At the same time,a kind of depth binary function tree structure is proposed to train the classifier,which can effectively combine the correlation between the features and combine the training with the skin color algorithm to improve the detection speed. Through the test of the proposed algorithm in this paper in CMU human face database,simulation results indicate that the algorithm improves the detection rate by 8. 7%,error detection rate reduced 4. 1%,detection speed improved 27. 7% under multi-face and multi-view background.

关 键 词：NPD特征 深度二叉特征树 肤色 ADABOOST算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]