Face recognition using localized features based on non-negative sparse coding

Authors:
Bhavin J. Shastri;Martin D. Levine
Affiliations:
McGill University, Centre for Intelligent Machines and Department of Electrical and Computer Engineering, 3480 University Street, Rm. 410, Montreal, QC, Canada;McGill University, Centre for Intelligent Machines and Department of Electrical and Computer Engineering, 3480 University Street, Rm. 410, Montreal, QC, Canada
Venue:
Machine Vision and Applications
Year:
2007

Citing 0
Cited 6

Total variation norm-based nonnegative matrix factorization for identifying discriminant representation of image patterns

Neurocomputing
3D face recognition with sparse spherical representations

Pattern Recognition
Face recognition using the feature fusion technique based on LNMF and NNSC algorithms

ICIC'10 Proceedings of the 6th international conference on Advanced intelligent computing theories and applications: intelligent computing
An integrated approach for head gesture based interface

Applied Soft Computing
Online learning and generalization of parts-based image representations by non-negative sparse autoencoders

Neural Networks
Nonnegative matrix factorizations performing object detection and localization

Applied Computational Intelligence and Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Neural networks in the visual system may be performing sparse coding of learnt local features that are qualitatively very similar to the receptive fields of simple cells in the primary visual cortex, V1. In conventional sparse coding, the data are described as a combination of elementary features involving both additive and subtractive components. However, the fact that features can ‘cancel each other out’ using subtraction is contrary to the intuitive notion of combining parts to form a whole. Thus, it has recently been argued forcefully for completely non-negative representations. This paper presents Non-Negative Sparse Coding (NNSC) applied to the learning of facial features for face recognition and a comparison is made with the other part-based techniques, Non-negative Matrix Factorization (NMF) and Local-Non-negative Matrix Factorization (LNMF). The NNSC approach has been tested on the Aleix–Robert (AR), the Face Recognition Technology (FERET), the Yale B, and the Cambridge ORL databases, respectively. In doing so, we have compared and evaluated the proposed NNSC face recognition technique under varying expressions, varying illumination, occlusion with sunglasses, occlusion with scarf, and varying pose. Tests were performed with different distance metrics such as the L1-metric, L2-metric, and Normalized Cross-Correlation (NCC). All these experiments involved a large range of basis dimensions. In general, NNSC was found to be the best approach of the three part-based methods, although it must be observed that the best distance measure was not consistent for the different experiments.