Is face recognition really a Compressive Sensing problem?

Authors:
Qinfeng Shi;A. Eriksson;A. van den Hengel; Chunhua Shen
Affiliations:
Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia;Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia;Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia;Australian Centre for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia
Venue:
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Year:
2011

Citing 0
Cited 13

Supervised sparse representation method with a heuristic strategy and face recognition experiments

Neurocomputing
Heteroscedastic Sparse Representation Based Classification for Face Recognition

Neural Processing Letters
Locality constrained representation based classification with spatial pyramid patches

Neurocomputing
Collaborative neighbor representation based classification using l2-minimization approach

Pattern Recognition Letters
Bimodal biometrics based on a two-stage test sample representation

AICI'12 Proceedings of the 4th international conference on Artificial Intelligence and Computational Intelligence
Adaptive weighted learning for linear regression problems via Kullback-Leibler divergence

Pattern Recognition
Incremental face recognition: hybrid approach using short-term memory and long-term memory

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part I
Sparse coding based visual tracking: Review and experimental comparison

Pattern Recognition
A robust face and ear based multimodal biometric system using sparse representation

Pattern Recognition
Letters: Two-dimensional relaxed representation

Neurocomputing
A novel classification method for palmprint recognition based on reconstruction error and normalized distance

Applied Intelligence
Face recognition for web-scale datasets

Computer Vision and Image Understanding
Linear reconstruction measure steered nearest neighbor classification framework

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Compressive Sensing has become one of the standard methods of face recognition within the literature. We show, however, that the sparsity assumption which underpins much of this work is not supported by the data. This lack of sparsity in the data means that compressive sensing approach cannot be guaranteed to recover the exact signal, and therefore that sparse approximations may not deliver the robustness or performance desired. In this vein we show that a simple $/ell_2$ approach to the face recognition problem is not only significantly more accurate than the state-of-the-art approach, it is also more robust, and much faster. These results are demonstrated on the publicly available YaleB and AR face datasets but have implications for the application of Compressive Sensing more broadly.