Sparse and Scale-Invariant Methods in Image Processing

Abstract : In this thesis, we present new techniques based on the notions of sparsity and scale invariance to design fast and efficient image processing applications. Instead of using the popular l1-norm to model sparsity, we focus on the use of non-convex penalties that promote more sparsity. We propose to use a first-order approximation to estimate a solution of non-convex proximal operators, which permits to easily use a wide rangeof penalties. We address also the problem of multi-sparsity, when the minimization problem is composed of various sparse terms, which typically arises in problems that require both a robust estimation to reject outliers and a sparse prior. These techniques are applied to various important problems in low-level computer vision such as edgeaware smoothing, image separation, robust integration and image deconvolution. We propose also to go beyond sparsity models and learn non-local spectral mapping with application to image denoising. Scale-invariance is another notion that plays an important role in our work. Using this principle, a precise definition of edges can be derived which can be complementary to sparsity. More precisely, we can extractinvariant features for classification from sparse representations in a deep convolutional framework. Scale-invariance permits also to extract relevant pixels for sparsifying images. We use this principle as well to improve optical ow estimation on turbulent images by imposing a sparse regularization on the local singular exponents instead of regular gradients.
Complete list of metadatas

Cited literature [265 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01239958
Contributor : Abes Star <>
Submitted on : Friday, January 15, 2016 - 11:24:07 AM
Last modification on : Thursday, May 17, 2018 - 1:11:24 AM
Long-term archiving on : Saturday, April 16, 2016 - 10:34:17 AM

File

BADRI_HICHAM_2015.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01239958, version 2

Collections

Citation

Hicham Badri. Sparse and Scale-Invariant Methods in Image Processing. Computer Vision and Pattern Recognition [cs.CV]. Université de Bordeaux, 2015. English. ⟨NNT : 2015BORD0139⟩. ⟨tel-01239958v2⟩

Share

Metrics

Record views

3269

Files downloads

973