DMCA
Learning Spatially Localized, Parts-Based Representation (2001)
| Citations: | 200 - 7 self |
BibTeX
@INPROCEEDINGS{Li01learningspatially,
author = {Stan Z. Li and Xinwen Hou and Hongjiang Zhang and QianSheng Cheng},
title = {Learning Spatially Localized, Parts-Based Representation},
booktitle = {},
year = {2001},
pages = {207--212}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper, we propose a novel method, called local nonnegative 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 [1]. 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.
Keyphrases
parts-based representation spatially localized localized feature local nonnegative matrix factorization localization constraint non-negativity constraint standard nmf parts-based subspace representation basis component novel method pca method experimental result visual pattern objective function face representation
