Sparse Image Representation with Epitomes

TL;DR

This paper introduces a structured dictionary learning method using epitomes for sparse image representation, enhancing shift-invariance and reducing parameters, with applications demonstrated in image denoising.

Contribution

It proposes a novel formulation and algorithm for learning epitome-based structured dictionaries for sparse coding in images.

Findings

Epitome-based dictionaries reduce the number of parameters needed.

Structured dictionaries improve shift-invariance in image representations.

Application to denoising shows competitive performance.

Abstract

Sparse coding, which is the decomposition of a vector using only a few basis elements, is widely used in machine learning and image processing. The basis set, also called dictionary, is learned to adapt to specific data. This approach has proven to be very effective in many image processing tasks. Traditionally, the dictionary is an unstructured "flat" set of atoms. In this paper, we study structured dictionaries which are obtained from an epitome, or a set of epitomes. The epitome is itself a small image, and the atoms are all the patches of a chosen size inside this image. This considerably reduces the number of parameters to learn and provides sparse image decompositions with shiftinvariance properties. We propose a new formulation and an algorithm for learning the structured dictionaries associated with epitomes, and illustrate their use in image denoising tasks.