| Gabor特征判别分析人脸识别方法的误配准鲁棒性分析 |
| |
| 引用本文： | 唱轶钲,山世光,高文,曹波,杨澎.Gabor特征判别分析人脸识别方法的误配准鲁棒性分析[J].计算机工程与应用,2005,41(5):56-59. |
| |
| 作者姓名： | 唱轶钲 山世光 高文 曹波 杨澎 |
| |
| 作者单位： | 哈尔滨工业大学计算机学院,哈尔滨,150001;中科院计算所ICT-ISVISION面像识别联合实验室,北京,100080;哈尔滨工业大学计算机学院,哈尔滨,150001;中科院计算所ICT-ISVISION面像识别联合实验室,北京,100080 |
| |
| 基金项目： | 国家自然科学基金重点项目“基于生物特征的身份识别研究”(编号:60332010)，国家863高技术研究发展计划项目(编号:2002AA118010的资助 |
| |
| 摘 要： | 人脸识别领域中,Gabor特征人脸表示方法因其在应用中获得的高首选识别率而被认为是一种理想的人脸特征表示方法。文章用一种全新的量化评价方法,结合配准精度和识别率,从误配准鲁棒性角度评价Gabor特征在人脸识别中的优越性。实验表明,和图像灰度信息特征相比,Gabor特征不仅在精确配准时具有高识别率,而且对由于人脸特征定位不精确而导致的图像变化的鲁棒性也更强。
|
| 关 键 词： | 人脸识别 误配准 Gabor 小波特征 |
| 文章编号： | 1002-8331-(2005)05-0056-04 |
Evaluation of Gabor Features for Face Recognition from the Angle of Robustness to Mis-alignment |
| |
| Chang Yizheng,Shan Shiguang,Gao Wen,Cao Bo,Yang Peng.Evaluation of Gabor Features for Face Recognition from the Angle of Robustness to Mis-alignment[J].Computer Engineering and Applications,2005,41(5):56-59. |
| |
| Authors: | Chang Yizheng Shan Shiguang Gao Wen Cao Bo Yang Peng |
| |
| Affiliation: | Chang Yizheng1 Shan Shiguang2 Gao Wen1,2 Cao Bo2 Yang Peng21 |
| |
| Abstract: | Gabor feature has been widely recognized as a desirous representation for face recognition in terms of its high recognition rate.This paper evaluates Gabor feature for face recognition from a new angle of its robustness to mis-alignment using a novel quantificational evaluation method which combines the alignment precision with the recognition accuracy.This experiments show that,compared with the gray-level intensity,Gabor feature is much more robust to image variation caused by the imprecision of facial feature localization,which further support the feasibility of Gabor representation. |
| |
| Keywords: | face recognition mis-alignment Gabor feature |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
