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...

增强LLE特征分类性能的人脸识别

Keywords: 人脸识别,特征提取,分类,流形学习,距离学习

Full-Text   Cite this paper   Add to My Lib

Abstract:

为了增强局部线性嵌入(LLE)特征的可分类性,提出一种应用LMNN算法改善LLE特征分类性能的人脸识别方法.LMNN算法寻求一个线性变换,变换空间的欧氏距离等价于原始空间的马氏距离,马氏距离增强了LLE特征的kNN分类性能.在ORL数据库和扩展的YaleB数据库上进行实验,并与其他方法进行了比较.实验结果验证了该算法的有效性.

References

[1]  Zhao W, Chellappa R, Phillips P J, et al. Face recognition: a literature survey[J]. ACM Computing Surveys, 2003,35(4):399-458.
[2]  Zhou S K, Chellappa R, Zhao W. Unconstrained face recognition[M]. New York: Springer, 2006:17-41.
[3]  Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000,290:2323-2326.
[4]  Seung H S, Daniel D L. The manifold ways of perception[J]. Science, 2000,290(12):2268-2269.
[5]  He X, Yan S, Hu Y, et al. Face recognition using Laplacianfaces[J]. IEEE Transaction on Patterm Analysis and Machine Intelligence, 27(3):328-340.
[6]  He X, Cai D, Yan S, et al. Neighborhood preserving embedding[C]//Proceeding of the 10th IEEE International Conference on Computer Vision (ICCV’2005). Beijing: IEEE, 2005.
[7]  张军平.监督流形学习[M]//周志华.机器学习及其应用.北京:清华大学出版社,2007:195-230.Zhang Junping. Supervised manifold learning[M]//Zhou Zhihua. Machine Learing and Its Application. Beijing: Tsinghua University Press, 2007:195-230. (in Chinese)
[8]  Zhang J, Zhou Z H. Unified locally linear embedding and linear discriminant analysisi algorithm (ULLELDA)for face recognition[C]//Proceedings of Adavance in Biometric Personal Authentication Lecture Notes on Computer Science. Berlin, Heidelberg: Springer-Verlag, 2004:296-304.
[9]  Weinberger K Q, Saul L K. Distance metric learning for large margin nearest nerghbor classification[J]. Journal of Machine Learning Research, 2009(10):207-244.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133