| 一种基于轮廓图像的人脸检测方法 |
| |
| 引用本文： | 龚文胜,陈宇,辛国江. 一种基于轮廓图像的人脸检测方法[J]. 计算机工程与设计, 2006, 27(21): 4068-4070 |
| |
| 作者姓名： | 龚文胜 陈宇 辛国江 |
| |
| 作者单位： | 湖南大学,计算机与通信学院,湖南,长沙,410082;湖南大学,计算机与通信学院,湖南,长沙,410082;湖南大学,计算机与通信学院,湖南,长沙,410082 |
| |
| 摘 要： | 提出了一种基于轮廓图像的人脸检测方法。针对人脸的生理结构特征，对人脸的灰度图像进行水平和垂直方向的轮廓分割；在此基础上对轮廓图像进行分块，抽取水平和垂直方向的轮廓特征；将抽取的特征用支持向量机（support vector machine，SVM）进行分类，将分类结果用于人脸检测。实验表明：轮廓特征能较好的反映人的脸部特征，用支持向量机对轮廓特征进行分类的方法来检测人脸是有效的。
|
| 关 键 词： | 人脸检测 轮廓图像 轮廓特征 支持向量机 分类 |
| 文章编号： | 1000-7024（2006）21-4068-03 |
| 收稿时间： | 2005-09-21 |
| 修稿时间： | 2005-09-21 |
New method for detecting human face based on profile image |
| |
| GONG Wen-sheng,CHEN Yu,XIN Guo-jiang. New method for detecting human face based on profile image[J]. Computer Engineering and Design, 2006, 27(21): 4068-4070 |
| |
| Authors: | GONG Wen-sheng CHEN Yu XIN Guo-jiang |
| |
| Affiliation: | College of Computer and Communication, Hunan University, Changsha 410082, China |
| |
| Abstract: | A new method for detecting human face based on profile image is proposed.First,according to physiological features of human faces,the profiles are segmented from both vertical and horizontal directions of the human face's gray image.Then,the profile image is divided into some blocks,the profile features are extracted from both vertical and horizontal directions.Finally,support vector machines(SVM) is used to classify those features.Experiments show that the method reflects the features of human faces very well and using SVM to classify profile features is an effective method for detecting human face. |
| |
| Keywords: | human face detection profile image profile feature SVM classify |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
