Block-coordinate proximal algorithms for scale-free texture segmentation

Abstract : Texture segmentation still constitutes an ongoing challenge, especially when processing large-size images. Recently, procedures integrating a scale-free (or fractal) wavelet-leader model allowed the problem to be reformulated in a convex optimization framework by including a TV penalization. In this case, the TV penalty plays a prominent role with respect to the data fidelity term, which makes the approach costly in terms of memory and computation cost. The present contribution aims to investigate the potential of recent block-coordinate dual and primal-dual proximal algorithms for overcoming this numerical issue. Our study shows that a key ingredient in the success of the proposed block-coordinate approaches lies in the design of the blocks of variables which are updated at each iteration. Numerical experiments conducted over synthetic textures having piece-wise constant fractal properties confirm our theoretical analysis. The proposed lattice block design strategy is shown to yield significantly lower memory and computational requirements.
Liste complète des métadonnées

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/hal-01736991
Contributor : Barbara Pascal <>
Submitted on : Monday, March 19, 2018 - 9:42:53 AM
Last modification on : Tuesday, October 2, 2018 - 1:15:38 AM
Document(s) archivé(s) le : Tuesday, September 11, 2018 - 8:26:31 AM

File

Templv2.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01736991, version 1

Citation

Barbara Pascal, Nelly Pustelnik, Patrice Abry, Jean-Christophe Pesquet. Block-coordinate proximal algorithms for scale-free texture segmentation. ICASSP 2018 - IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Canada. pp.1-5. ⟨hal-01736991⟩

Share

Metrics

Record views

326

Files downloads

132