基于肤色模型与人脸特征的多姿态人脸检测

山东大学学报(工学版) ›› 2011, Vol. 41 ›› Issue (2): 36-39.

基于肤色模型与人脸特征的多姿态人脸检测

孙亚新, 战荫伟*

广东工业大学计算机学院, 广东广州 510006

收稿日期:2010-12-01 出版日期:2011-04-16 发布日期:2010-12-01
通讯作者: 战荫伟(1966- ),男,吉林九台人,教授,博士,主要研究方向为图像处理和视频分析,机器学习,小波分析. E-mail:E-mail:ywzhan@gdut.edu.cn
作者简介:孙亚新(1986- ),男,湖北咸宁人,硕士,主要研究方向为图像处理和视频分析，机器学习.Email:sunyaxin2005@163.com

Multi-pose face detection based on color model and face feature

SUN Yaxin, ZHAN Yinwei*

Faculty of Computer, Guangdong University of Technology, Guangzhou 510006, China

Received:2010-12-01 Online:2011-04-16 Published:2010-12-01

摘要/Abstract

摘要：

传统AdaBoost人脸检测算法使用正面人脸训练分类器,不能检测有任意偏转角度的多姿态人脸。本研究利用各种多姿态人脸中人眼结构变化比较小的性质,使用人眼训练AdaBoost算法的分类器,设计出一种快速的复杂场景下的多人多姿态人脸检测算法。先将图像映射到一种色彩空间,运用皮肤颜色分布特性检测皮肤区域;再运用AdaBoost算法从肤色区域检测出人眼区域;最后根据人眼在人脸中的位置计算出人脸的位置。实验结果表明:该算法对多姿态人脸有很好的检测效果。

关键词: 色彩空间, 肤色模型, 多姿态人脸检测, 人眼检测

Abstract:

Traditionally, AdaBoost based face detection algorithms use frontal faces to train classifiers, which cannot detect multipose faces with arbitrary rotations. Noticing that the eye structures vary less than face structures in multipose faces, eyes were used to train the classifier in AdaBoost algorithm, and present a fast algorithm to detect multipose faces in complex scenes. An image is first mapped to a YCrCb color space and the skin region is detected with the skin color distribution. The eye region is then detected from the skin region via the AdaBoost algorithm. The face is located according to the eye positions relative to faces. Experimental results show that this algorithm performs well for the detection of multipose faces.

Key words: color space, skin model, multi-pose face detection, eye detection

孙亚新, 战荫伟*. 基于肤色模型与人脸特征的多姿态人脸检测[J]. 山东大学学报(工学版), 2011, 41(2): 36-39.

SUN Yaxin, ZHAN Yinwei*. Multi-pose face detection based on color model and face feature[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2011, 41(2): 36-39.

参考文献

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

[1]	刘一方1,2, 张云峰1,2*, 迟静1,2,张彩明1,2. 基于SSLUT的颜色空间转换的快速算法[J]. 山东大学学报(工学版), 2013, 43(1): 41-47.
[2]	黄伟1,王书文2*,杨筱平3,贾建芳3. 基于图像分解的敦煌壁画图像修复方法[J]. 山东大学学报(工学版), 2010, 40(2): 24-27.
[3]	董文会,曲培树,吴晓娟,徐祗军 . 复杂背景下多姿态人脸图像中的人眼检测[J]. 山东大学学报(工学版), 2006, 36(3): 18-21 .