Sparse Image Representation with Epitomes

Louise Benoît (1, 2, 3) , Julien Mairal (1, 2) , Francis Bach (3) , Jean Ponce (1)

1 WILLOW - Models of visual object recognition and scene understanding
2 LIENS - Laboratoire d'informatique de l'école normale supérieure
3 SIERRA - Statistical Machine Learning and Parsimony

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.

Mots clés: Epitome; Dictionary Learning; Denoising; Sparse Coding

Domaines: Apprentissage [cs.LG]; Machine Learning [stat.ML]; Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Louise Benoît, Julien Mairal, Francis Bach, Jean Ponce. Sparse Image Representation with Epitomes. Computer Vision and Pattern Recognition, Jun 2011, Colorado Springs, United States. pp.2913 - 2920, ⟨10.1109/CVPR.2011.5995636⟩. ⟨hal-00631652⟩