期刊文献+

基于非线性子流形的人脸识别 被引量:2

Face Recognition Based on Nonlinear Manifold Learning
下载PDF
导出
摘要 介绍了流形、流形学习的数学基础及其应用时的核心问题,流形学习方法用于人脸识别的技术路线;通过实例分析讨论了流形学习主流算法——局部线性嵌入(LLE)算法的优势和存在的不足;使用ORL人脸数据库进行仿真实验并将识别效果与原始图像直接分类法、主成分分析法进行比较,验证了LLE算法的有效性及优势。 A brief introduction on the manifold learning way, its mathematical basis, the key points and the technical approach for its application in face recognition is described. The advantages and disadvantages of locally linear embedding (LLE), a main calculating way adopted in manifold learning, are studied via analysis of examples. Furthermore, we have realized the emulation experiments of ORL face data base. A full comparison of the original image classifications of PCA and LLE demonstrates that LLE is effective approach.
出处 《重庆大学学报(自然科学版)》 EI CAS CSCD 北大核心 2008年第3期303-306,共4页 Journal of Chongqing University
基金 重庆市自然科学基金资助项目"鉴别性流形学习算法及其在人脸识别中的应用研究"(CSTC2006BB2152)
关键词 流形 流形学习 人脸识别 局部线性嵌入算法 manifold manifold learning face recognition locally linear embedding
  • 相关文献

参考文献9

  • 1涂承胜,陆玉昌.Boosting理论基础[J].计算机科学,2004,31(10):11-14. 被引量:5
  • 2王刚,刘伟,冯贵玉.基于ICA的多姿态人脸表示[J].国防科技大学学报,2003,25(3):84-87. 被引量:2
  • 3罗四维,赵连伟.流形学习研究综述[EB/OL].[2005-12-12]http://www.paper.edu.cn.
  • 4SEUNG H, SEBASTIAN, LEE DANIEL D. The manifold ways of perception [ J ]. Science, 2000, 290 ( 12 ) : 2268-2269.
  • 5罗四维,赵连伟.基于谱图理论的流形学习算法[J].计算机研究与发展,2006,43(7):1173-1179. 被引量:76
  • 6施思伟.流形上的微积分[M].北京:科学出版社,2004.
  • 7DE SILVA V, TENENBAUM J B. Global versus local methods in nonlinear dimensionality reduction [ G ]. In Advances in NIPS15. Cambridge,M A: MIT Press, 2002: 705-712.
  • 8MIKA S, RATSCH G, WESTON J, et al. Fisher discriminant analysis with kernels [ C ] //Proceedings of IEEE Neural Networks for Signal Processing Workshop, Wisconsin, USA: [ s. n. ] ,1999:41-48.
  • 9ROWEIS S T, SAUL L K. Nonlinear dimensionality reduction by locally linear embedding [ J ]. Science, 2000,290: 2323 -2326.

二级参考文献58

  • 1张振跃,查宏远.线性低秩逼近与非线性降维[J].中国科学(A辑),2005,35(3):273-285. 被引量:8
  • 2杨剑,李伏欣,王珏.一种改进的局部切空间排列算法[J].软件学报,2005,16(9):1584-1590. 被引量:36
  • 3Bartlett M S, Sejnowski T J. Independent Component of Face Images: A Representation of Face Recognition[ C]. Proceedings of the 4th Annual Jount Symposium on Nearal Computation,Pasadena,CA,May 17,1997.
  • 4Bartlett M S,Sejnowski T J.Viewpoint Invariant Face Recognition Using Independent Component Analysis and Attractor Networks[J].Neural Information Procession Systems-Natural and Synthetic,1997,9:817-823.
  • 5Schapire R E. The strength of weak learnability. Machine Learning, 1990,5(2) :197-227
  • 6Kearns M,Valiant L G. Learning Boolean Formulae or Factoring: [Technical Report TR- 1488]. Cambridge, MA: Havard University Aiken Computation Laboratory, 1988
  • 7Kearns M, Valiant L G. Crytographic Limitation on Learning Boolean Formulae and Finite Automata. In: Proc. of the 21st annual ACM Symposium on Theory of Computing,New York. NY:ACM press, 1989. 433-444
  • 8Valiant L G. A theory of the learnable. Communications of the ACM,1984, 27(11):1134-1142
  • 9Kearns M J,Vazirani L G. Learning Boolean formulae or finite automata is as hard as factoring: [Technical Report TR-14-88].Harvard University Aiken Computation Laboratory, Aug. 1988
  • 10Kearns M J,Vazirani L G. Cryptographic limitations on learning Boolean formulae and finite automata. Journal of the Association for Computing Machinery, 1994,41(1): 67-95

共引文献80

同被引文献38

引证文献2

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部