| 基于SVD-TRIM特征和LSSVM人脸识别方法 |
| |
| 引用本文： | 田海军,赵龙,田尊华.基于SVD-TRIM特征和LSSVM人脸识别方法[J].工程图学学报,2010,31(5):74-80. |
| |
| 作者姓名： | 田海军 赵龙 田尊华 |
| |
| 作者单位： | 国防科学技术大学计算机学院,湖南,长沙,410073 |
| |
| 基金项目： | 863国家高技术发展计划资助项目(2006AAJ119;2006AAJ210) |
| |
| 摘 要： | 人脸特征的选择对识别结果起关键作用。传统上只提取较大奇异值特征作为识别特征的人脸识别方法,识别率不高,对表情和姿态变化敏感。SVD-TRIM算法选择的奇异值识别特征融合了人脸整体和局部细节特征,并采用基于＂一对一＂的LSSVM多类分类器分类识别。实验结果表明SVD-TRIM算法选择的识别特征对提高识别率具有较大贡献,且对光照、姿态和表情具有鲁棒性。
|
| 关 键 词： | 计算机应用 SVD-TRIM算法 奇异值分解 LSSVM 人脸识别 |
An Approach to Face Recognition Based on SVD-TRIM and LSSVM Algorithm |
| |
| TIAN Hai-jun,ZHAO Long,TIAN Zun-hua.An Approach to Face Recognition Based on SVD-TRIM and LSSVM Algorithm[J].Journal of Engineering Graphics,2010,31(5):74-80. |
| |
| Authors: | TIAN Hai-jun ZHAO Long TIAN Zun-hua |
| |
| Affiliation: | TIAN Hai-jun,ZHAO Long,TIAN Zun-hua(School of Computer Science,National University of Defense Technology,Changsha Hunan 410073,China) |
| |
| Abstract: | Feature selection of face image is the key to face recognition.The conventional method to extract algebraic features of face image based on the Singular Value Decomposition(SVD) leads to low recognition accuracy and high sensitivity to the varieties of facial expression,illumination and posture.In this paper,a novel method of features selection based on SVD-TRIM algorithm is proposed.The new features syncretize whole and part features of face image.Experimental results,based on LSSVM,suggest that the new fe... |
| |
| Keywords: | computer application SVD-TRIM algorithm singular value decomposition LSSVM face recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
