Variational models and numerical algorithms for selective image segmentation

Rada, Lavdie
Variational models and numerical algorithms for selective image segmentation. Doctor of Philosophy thesis, University of Liverpool.

[img] PDF
RadaLav_May2013_11093.pdf - Author Accepted Manuscript
Available under License Creative Commons Attribution No Derivatives.

Download (18MB)


This thesis deals with the numerical solution of nonlinear partial differential equations and their application in image processing. The differential equations we deal with here arise from the minimization of variational models for image restoration techniques (such as denoising) and recognition of objects techniques (such as segmentation). Image denoising is a technique aimed at restoring a digital image that has been contaminated by noise while segmentation is a fundamental task in image analysis responsible for partitioning an image as sub-regions or representing the image into something that is more meaningful and easier to analyze such as extracting one or more specific objects of interest in images based on relevant information or a desired feature. Although there has been a lot of research in the restoration of images, the performance of such methods is still poor, especially when the images have a high level of noise or when the algorithms are slow. Task of the segmentation is even more challenging problem due to the difficulty of delineating, even manually, the contours of the objects of interest. The problems are often due to low contrast, fuzzy contours, similar intensities with adjacent objects, or the objects to be extracted having no real contours. The first objective of this work is to develop fast image restoration and segmentation methods which provide better denoising and fast and robust performance for image segmentation. The contribution presented here is the development of a restarted homotopy analysis method which has been designed to be easily adaptable to various types of image processing problems. As a second research objective we propose a framework for image selective segmentation which partitions an image based on the information known in advance of the object/objects to be extracted (for example the left kidney is the target to be extracted in a CT image and the prior knowledge is a few markers in this object of interest). This kind of segmentation appears especially in medical applications. Medical experts usually estimate and manually draw the boundaries of the organ/organs based on their experience. Our aim is to introduce automatic segmentation of the object of interest as a contribution not only to the way doctors and surgeons diagnose and operate but to other fields as well. The proposed methods showed success in segmenting different objects and perform well in different types of images not only in two-dimensional but in three-dimensional images as well.

Item Type: Thesis (Doctor of Philosophy)
Additional Information: Date: 2013-05 (completed)
Uncontrolled Keywords: Image processing, Denoising, Image segmentation, Image selective segmentation, Total variation, Level set function, Edge detection, 2D image segmentation, Euler-Lagrange equation, Discrete homotopy, analysis method, Finite difference scheme, Series solution
Divisions: Faculty of Science and Engineering > School of Physical Sciences > Mathematical Sciences
Depositing User: Symplectic Admin
Date Deposited: 03 Sep 2013 09:00
Last Modified: 16 Dec 2022 04:38
DOI: 10.17638/00011093
  • Chen, Ke