Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 (2001)
Dec. 8, 2001 to Dec. 14, 2001
Stan Z. Li , Microsoft Research China
Xin Wen Hou , Peking University
HongJiang Zhang , Microsoft Research China
QianSheng Cheng , Peking University
In this paper, we propose a novel method, called local non-negative matrix factorization (LNMF), for learning spatially localized, parts-based subspace representation of visual patterns. An objective function is defined to impose localization constraint, in addition to the non-negativity constraint in the standard NMF . This gives a set of bases which not only allows a non-subtractive (part-based) representation of images but also manifests localized features. An algorithm is presented for the learning of such basis components. Experimental results are presented to compare LNMF with the NMF and PCA methods for face representation and recognition, which demonstrates advantages of LNMF.
Q. Cheng, S. Z. Li, H. Zhang and X. W. Hou, "Learning Spatially Localized, Parts-Based Representation," Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001(CVPR), Kauai, Hawaii, 2001, pp. 207.