计算机科学与探索 ›› 2010, Vol. 4 ›› Issue (5): 420-425.DOI: 10.3778/j.issn.1673-9418.2010.05.004

• 学术研究 • 上一篇    下一篇

面向小样本库的全局Gabor滤波人脸识别*

李 宽+; 殷建平;李 永; 詹宇斌

  

  1. 国防科技大学 计算机学院, 长沙 410073
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2010-05-11 发布日期:2010-05-11
  • 通讯作者: 李 宽

Face Recognition Using Global Gabor Filter in Small Sample Case*

LI Kuan+;YIN Jianping; LI Yong; ZHAN Yubin

  

  1. School of Computer Science, National University of Defense Technology, Changsha 410073, China
  • Received:1900-01-01 Revised:1900-01-01 Online:2010-05-11 Published:2010-05-11
  • Contact: LI Kuan

摘要: 虽然约束条件下的人脸识别已取得很大进展, 但开放环境下的人脸识别仍有很多问题需要解决; 其次, 人脸识别实用系统往往难以获得待识别人的多个样本。针对上述两点, 研究小样本库情况下的人脸识别问题, 提出了一种新的人脸特征提取方法:对人脸图像进行多尺度多方向Gabor滤波, 用特定尺度/方向滤波后的均值和方差作为新的人脸特征进行识别。基于JAFFE和ORL数据库进行“小样本训练, 大样本测试”验证, 实验结果及后续分析比对证明了方法的有效性。

关键词: 人脸识别, 开放环境, Gabor滤波器, 均值, 方差

Abstract: Although progress in face recognition has been encouraged in constraint conditions, many problems still exist in unconstraint tasks. Also, it is not easy to collect a large number of face samples of each people. To solve the problems above, the task of face recognition with a small number of training images of each people is considered. A new feature extraction method is proposed based on Gabor filter. Experiments in small sample case are carried out under JAFFE and ORL dataset. The result and analysis verify the validity and robustness of proposed method.

Key words: face recognition, unconstrain tasks, Gabor filter, mean, variance

中图分类号: