全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于核函数的稳健线性嵌入方法

DOI: 10.11834/jig.20090621

Keywords: 流形学习,高维数据,维数约减,核函数

Full-Text   Cite this paper   Add to My Lib

Abstract:

LLE算法是一种新的非监督学习方法,主要针对非线性降维问题。针对该算法存在的缺点,提出了一种基于核函数的稳健线性嵌入方法,该方法通过引进核函数来优化算法邻域点的求解;在特征空间中,修正权值矩阵W,进行降噪处理,经过推导,最终将实际的子空间计算归结为标准的特征值分解问题。采用最小近邻分类器估算识别率。在Yale人脸库以及AT&T人脸库的测试结果表明,在姿态、光照、表情、训练样本数目变化的情况下,改进的算法都具有较好的识别率。

References

[1]  Kirby M, Sirovich L. Application of the karhunen21oeve procedure for the charatefization of human faces[J]. IEEE Transactions on Pattern A Nalysis and Machi nc Intelligence, 1990, 12( 1 ) : 103-108.
[2]  Turk M, Pentland A. Eigenfaces for recognition[J]. Journal of Cognitive Neuroscience, 1991, 3( 1 ) : 72-86.
[3]  Phillips P J, Moon H, Rizvi S, et al. The feret evaluation methodology for face recognition algorithms[J]. IEEE Transactions on Pattern A Nalysis and Machi ne Intelligence, 2000, 22(10) : 1090-1104.
[4]  Turk M, Pentalnd A. Eigenfaces for recognition [J]. Journal of Cognitive Neuroscience, 1991,3( 1 ) :71-86.
[5]  Zhao W, Chellappa R, Rosenfeld A, et al. Face recognition: A literature survey [R] . CS-Tech Report4167, University of Maryland, 2000.
[6]  Rowels S T, Saul L K. Nonlmensionality reduction by locally linear embedding [J]. Science, 2000,290(22) :2323-2326.
[7]  徐蓉 姜峰 姚鸿勋.流形学习概述[J].智能系统学报,2006,l(1):44-51.
[8]  赵连伟 罗四维 赵艳敞 等.高维数据流形的低维嵌入及嵌入维数研究[J].软件学报,2005,16(8):1423-1430.
[9]  Bengio Y, Palement J,Vincent P,et al. Out-of-sample extensions for LLE,isomap, MDS, eigenmaps, and special clustering [ A ]. Neural Information Processing Systems [C] , Cambridge, MA: M IT Press, 2003 : 1238-1248.
[10]  Tenenbaum J B, De Silva V, Lan Gford J C. A global geometric framework for nonlinear dimensionality reduction [J]. Science, 2000, 290(5500) :2319-2323.
[11]  Shashua A, Levin A, Avidan S. Manifold pursuit: A new approach to appearance based recognition [ A ]. In: Proceeding of 16th International Conference on Pattern Recognition [C], Quebec City, Canada, 2002:590-594.
[12]  Weng Shi-feng, Zhang Chang-shui, Zhang Xue-gong. Nonlinear dimensionality reduction in the analysis of high dimensional medical data [J]. Journal of Tsinghua University Sci&Tech ,2004,44 (4) :485- 488.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133