| 基于对角DCT与2DPCA算法的人脸识别 |
| |
| 引用本文： | 甘俊英,高建虎,李春芝.基于对角DCT与2DPCA算法的人脸识别[J].计算机工程与应用,2007,43(31):210-213. |
| |
| 作者姓名： | 甘俊英 高建虎 李春芝 |
| |
| 作者单位： | 五邑大学信息学院，五邑大学信息学院，五邑大学信息学院 广东江门529020北京大学视觉与听觉信息处理国家重点实验室，北京100871，广东江门529020，广东江门529020 |
| |
| 基金项目： | 广东省自然科学基金
,
国家重点实验室基金 |
| |
| 摘 要： | 提出了一种对角离散余弦变换(Discrete Cosine Transform,DCT)和二维主元分析(Two-Dimensional Principal Component Analysis,2DPCA)相结合的人脸识别方法。该算法首先将人脸图像转换成对角图像,同时利用DCT压缩并重建人脸图像;然后通过2DPCA进行特征提取得到人脸识别特征;最后运用最近邻分类器进行识别。基于ORL(Olivetti Research Laboratory)、受污损ORL及Yale人脸数据库的实验结果证明了该算法的有效性。
|
| 关 键 词： | 离散余弦变换 二维主元分析 图像重建 人脸识别 |
| 文章编号： | 1002-8331（2007）31-0210-04 |
| 修稿时间： | 2007-03 |
Face recognition based on diagonal Discrete Cosine Transform and Two-Dimensional Principal Component Analysis |
| |
| GAN Jun-ying,GAO Jian-hu,LI Chun-zhi.Face recognition based on diagonal Discrete Cosine Transform and Two-Dimensional Principal Component Analysis[J].Computer Engineering and Applications,2007,43(31):210-213. |
| |
| Authors: | GAN Jun-ying GAO Jian-hu LI Chun-zhi |
| |
| Affiliation: | 1.School of Information,Wuyi University,Jiangmen,Guangdong 529020,China; 2.National Laboratory on Machine Perception,Peking University,Beijing 100871,China |
| |
| Abstract: | Combined with Discrete Cosine Transform(DCT) and Two-Dimensional Principal Component Analysis(2DPCA),a novel method in face recognition was presented in this paper.Firstly,face image is turned into diagonal image,and dimension is reduced by DCT.Then image is reconstructed by IDCT.Secondly,2DPCA is used in feature extraction,and face recognition features are obtained.Finally,the Nearest Neighbor(NN) classifier is selected to perform face recognition.Experimental results on ORL(Olivetti Research Laboratory),damaged ORL and Yale face database show that the method is efficient in face recognition. |
| |
| Keywords: | Discrete Cosine Transform(DCT) Two-Dimensional Principal Component Analysis(2DPCA) image reconstruction face recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
|
