Face Recognition Based on Circularly Symmetrical Gabor Transform

摘要：

In this paper, we propose a face recognition approach using circularly symmetrical Gabor transform (CSGT). The traditional Gabor transform is replaced by CSGT. All the face images are transformed by CSGT first and then face recognition is performed in CSGT feature space. Detailed theoretical analysis is presented and simulation results on Yale, AR and ORL face databases are given. The recognition rates can reach 92.59％, 85.29％ and 97.5％ respectively by the proposed algorithm.

作者: Huiyuan Wang Jinjun Wang Xiaojuan Wu Jose Vieira Paulo Ferreira

作者单位: School of Information Science and Engineering,Shandong University,Jinan,Shandong 250100,China IEETA,Universidade de Aveiro,3810-193 Aveiro,Portugal

会议类型: 国际会议

会议名称: 2009 IEEE International Conference on Information and Automation(2009年 IEEE信息与自动化国际学术会议)

会议地点: 珠海、澳门

会议语种:英文

页码: 1264-1268

在线出版日期: 2009-06-22（万方平台首次上网日期，不代表论文的发表时间）