Learning A Tree-Structured Dictionary For Efficient Image Representation With Adaptive Sparse Coding

Jérémy Aghaei Mazaheri 1, * Christine Guillemot 1 Claude Labit 1
* Corresponding author
1 Sirocco - Analysis representation, compression and communication of visual data
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : We introduce a new method, called Tree K-SVD, to learn a tree-structured dictionary for sparse representations, as well as a new adaptive sparse coding method, in a context of image compression. Each dictionary at a level in the tree is learned from residuals from the previous level with the K-SVD method. The tree-structured dictionary allows efficient search of the atoms along the tree as well as efficient coding of their indices. Besides, it is scalable in the sense that it can be used, once learned, for several sparsity constraints. We show experimentally on face images that, for a high sparsity, Tree K-SVD offers better rate-distortion performances than state-of-the-art "flat" dictionaries learned by K-SVD or Sparse K-SVD, or than the predetermined overcomplete DCT dictionary. We also show that our adaptive sparse coding method, used on a tree-structured dictionary to adapt the sparsity per level, improves the quality of reconstruction.
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/hal-00876030
Contributor : Jérémy Aghaei Mazaheri <>
Submitted on : Wednesday, October 23, 2013 - 2:58:56 PM
Last modification on : Wednesday, December 18, 2019 - 5:09:47 PM
Long-term archiving on: Friday, January 24, 2014 - 4:25:56 AM

File

aghaei_mazaheri.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00876030, version 1

Citation

Jérémy Aghaei Mazaheri, Christine Guillemot, Claude Labit. Learning A Tree-Structured Dictionary For Efficient Image Representation With Adaptive Sparse Coding. ICASSP - 38th International Conference on Acoustics, Speech, and Signal Processing, May 2013, Vancouver, Canada. ⟨hal-00876030⟩

Share

Metrics

Record views

477

Files downloads

539