Sparse Modeling for Image and Vision Processing

TL;DR

This paper reviews sparse modeling techniques in image and vision processing, emphasizing learned dictionaries for compact data representation and their cross-disciplinary applications.

Contribution

It provides a comprehensive, self-contained overview of sparse models with a focus on learned dictionaries for visual recognition and image processing.

Findings

Sparse models enable effective data representation in vision tasks.

Learned dictionaries improve model adaptability and compactness.

Sparse coding techniques are widely adopted across scientific fields.

Abstract

In recent years, a large amount of multi-disciplinary research has been conducted on sparse models and their applications. In statistics and machine learning, the sparsity principle is used to perform model selection---that is, automatically selecting a simple model among a large collection of them. In signal processing, sparse coding consists of representing data with linear combinations of a few dictionary elements. Subsequently, the corresponding tools have been widely adopted by several scientific communities such as neuroscience, bioinformatics, or computer vision. The goal of this monograph is to offer a self-contained view of sparse modeling for visual recognition and image processing. More specifically, we focus on applications where the dictionary is learned and adapted to data, yielding a compact representation that has been successful in various contexts.