HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation

DC programming and DCA in image processing : compressed sensing, segmentation and restoration

Abstract : Image is one of the most important information in our lives. Along with the rapid development of digital image acquisition devices such as digital cameras, phone cameras, the medical imaging devices or the satellite imaging devices..., the needs of processing and analyzing images is more and more demanding. It concerns with the problem of image acquiring, storing, enhancing or extracting information from an image,... In this thesis, we are considering the image processing and analyzing problems including: compressed sensing, dictionary learning and image denoising, and image segmentation. Our method is based on deterministic optimization approach, named the DC (Difference of Convex) programming and DCA (Difference of Convex Algorithms) for solving some classes of image analysis addressed above. 1. Compressed sensing is a signal processing technique for efficiently acquiring and reconstructing a signal, which is breaking the traditional limits of sampling theory of Nyquist–Shannon by finding solutions to underdetermined linear systems. This takes advantage of the signal’s sparseness or compressibility when it is represented in a suitable basis or dictionary, which allows the entire signal to be determined from few relative measurements. In this problem, we are interested in two aspects phases. The first one is finding the sparse representation of a signal. The other one is recovering the signal from its compressed measurements on an incoherent basis or dictionary. These problems lead to solve a NP–hard nonconvex optimization problem. We investigated three models with four approximations for each model. Appropriate algorithms based on DC programming and DCA are presented. 2. Dictionary learning: we have seen the power and the advantages of the sparse representation of signals in compressed sensing. Finding out the sparsest representation of a set of signals depends not only on the sparse representation algorithms but also on the basis or the dictionary used to represent them. This leads to the critical problems and other applications in a natural way. Instead of using a fixed basis such as wavelets or Fourier, one can learn the dictionary, a matrix D, to optimize the sparsity of the representation for a large class of given signals (data). The matrix D is called the learned dictionary. For this problem, we proposed an efficient DCA based algorithm including two stages: sparse coding and dictionary updating. An application of this problem, image denoising, is also considered. 3. Image segmentation: partitioning a digital image into multiple segments (sets of pixels). The goal of segmentation is to simplify and/or change the representation of an image into a form that is more meaningful and easier to analyze. We have developed an efficient method for image segmentation via feature weighted fuzzy clustering model. We also study an application of image segmentation for cell counting problem in medicine. We propose a combination of segmentation phase and morphological operations to automatically count the number of cells. Our approach gives promising results in comparison with the traditional manual analysis in despite of the very high cell density
Document type :
Complete list of metadata

Cited literature [210 references]  Display  Hide  Download

Contributor : Thèses Ul Connect in order to contact the contributor
Submitted on : Thursday, March 29, 2018 - 1:22:37 PM
Last modification on : Wednesday, July 25, 2018 - 1:23:47 AM


Files produced by the author(s)


  • HAL Id : tel-01751600, version 1



Thi Bich Thuy Nguyen. DC programming and DCA in image processing : compressed sensing, segmentation and restoration. Other [cs.OH]. Université de Lorraine, 2014. English. ⟨NNT : 2014LORR0350⟩. ⟨tel-01751600⟩



Record views


Files downloads