Linear projection-based non-negative matrix factorization

被引：5
|
作者：
Li L. [1 ,2 ,3 ]
Zhang Y.-J. [1 ,2 ]
机构：
[1] Tsinghua National Laboratory for Information Science and Technology, Tsinghua University
[2] Department of Electronic Engineering, Tsinghua University
[3] China Center for Information Industry Development
来源：
Zidonghua Xuebao/ Acta Automatica Sinica | 2010年 / 36卷 / 01期
关键词：
Data representation; Efficiency of dimensionality reduction; Feature extraction; Linear projection-based NMF (LPBNMF); Non-negative matrix factorization (NMF); Occluded face recognition; Sparse feature;
D O I：
10.3724/SP.J.1004.2010.00023
中图分类号：
学科分类号：
摘要：
Non-negative matrix factorization (NMF) is a newly popular method for non-negative dimensionality reduction, feature extraction, data mining, etc. The mathematical model in NMF definition is based on nonlinear projection, therefore dimension reduction by NMF is implemented by iterative updates which lead to high computational load. Additionally, NMF features extracted by this model are usually not very sparse, and this fails to meet the expectation of designing NMF. To simultaneously resolve the above two problems, this paper proposes a new model, linear projection-based NMF (LPBNMF), and designs an monotonic algorithm for it. From mathematical point of view, LPBNMF is a special mode for implementing NMF, which linearly implements dimension reduction. The high sparseness of LPBNMF features is assured by the inherent characteristics of its mathematic model. The comparison experiments validate that dimension reduction by LPBNMF is much more efficient than that by NMF, and that LPBNMF features are much more sparse and localized than NMF ones. Finally, experiments based on AR face database indicate that LPBNMF features are more suitable for nearest neighbor classification-based occluded face recognition than NMF, LDA, and PCA ones. © 2010 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：23 / 39
页数：16
相关论文
共 45 条
  • [1] Lee D.D., Seung H.S., Learning the parts of objects by non-negative matrix factorization, Nature, 401, 6755, pp. 788-791, (1999)
  • [2] Palmer S.E., Hierarchial structure in perceptual representation, Cognitive Psychology, 9, 4, pp. 441-474, (1977)
  • [3] Wachsmuth E., Oram M.W., Perrett D.I., Recognition of objects and their component parts: Responses of single units in the temporal cortex of the macaque, Cerebral Cortex, 4, 5, pp. 509-522, (1994)
  • [4] Logothetis N.K., Sheinberg D.L., Visual object recognition, Annual Review of Neuroscience, 19, 1, pp. 577-621, (1996)
  • [5] Lee D.D., Seung H.S., Algorithms for non-negative matrix factorization, Proceedings of the Conference on Neural Information Processing Systems, pp. 556-562, (2000)
  • [6] Wild S., Curry J., Dougherty A., Improving non-negative matrix factorizations through structured initialization, Pattern Recognition, 37, 11, pp. 2217-2232, (2004)
  • [7] Cichocki A., Amari S., Zdunek R., Kompass R., Hori G., He Z.H., Extended SMART algorithms for non-negative matrix factorization, Proceedings of the 8th International Conference on Artificial Intelligence and Soft Computing, pp. 548-562, (2006)
  • [8] Heiler M., Schnorr C., Learning sparse representations by non-negative matrix factorization and sequential cone programming, Journal of Machine Learning Research, 7, 7, pp. 1385-1407, (2006)
  • [9] Chen W.-G., Qi F.-H., Learning NMF representation using a hybrid method combining feasible direction algorithm and simulated annealing, Acta Electronica Sinica, 31, z1, pp. 2190-2193, (2003)
  • [10] Li L., Zhang Y.J., FastNMF: Highly efficient monotonic fixed-point non-negative matrix factorization algorithm with good applicability, Journal of Electronic Imaging, 18, 3, (2009)
12345