Sparse Representations, Compressive Sensing and dictionaries for pattern recognition

Abstract

In recent years, the theories of Compressive Sensing (CS), Sparse Representation (SR) and Dictionary Learning (DL) have emerged as powerful tools for efficiently processing data in non-traditional ways. An area of promise for these theories is object recognition. In this paper, we review the role of SR, CS and DL for object recognition. Algorithms to perform object recognition using these theories are reviewed. An important aspect in object recognition is feature extraction. Recent works in SR and CS have shown that if sparsity in the recognition problem is properly harnessed then the choice of features is less critical. What becomes critical, however, is the number of features and the sparsity of representation. This issue is discussed in detail.