Sparsity and Robustness in Face Recognition

TL;DR

This paper discusses the application of sparse signal representation and error correction techniques to improve face recognition, analyzing their validity and robustness in practical scenarios.

Contribution

It clarifies key questions about the use of sparse representation methods for face recognition and assesses their effectiveness and limitations.

Findings

Sparse representation techniques can be effective for face recognition.

The validity of sparse methods depends on certain technical conditions.

Robustness of these methods varies with data and noise conditions.

Abstract

This report concerns the use of techniques for sparse signal representation and sparse error correction for automatic face recognition. Much of the recent interest in these techniques comes from the paper "Robust Face Recognition via Sparse Representation" by Wright et al. (2009), which showed how, under certain technical conditions, one could cast the face recognition problem as one of seeking a sparse representation of a given input face image in terms of a "dictionary" of training images and images of individual pixels. In this report, we have attempted to clarify some frequently encountered questions about this work and particularly, on the validity of using sparse representation techniques for face recognition.