Image Processing by Variational Methods, Stochastic Programming and Deep Learning Techniques

This thesis is to investigate effective approaches to tackle different problems in computer vision: variational methods are first studied for image processing, illusory contour reconstruction and segmentation as well as their efficiency improvement. Next, we develop variational segmentation methods...

Full description

Bibliographic Details
Main Author: Tan, Lu
Format: Thesis
Published: Curtin University 2020
Online Access:http://hdl.handle.net/20.500.11937/82126
_version_ 1848764478463672320
author Tan, Lu
author_facet Tan, Lu
author_sort Tan, Lu
building Curtin Institutional Repository
collection Online Access
description This thesis is to investigate effective approaches to tackle different problems in computer vision: variational methods are first studied for image processing, illusory contour reconstruction and segmentation as well as their efficiency improvement. Next, we develop variational segmentation methods by stochastic programming, tackling diverse problems with random noises. Third, the fusion approaches integrating varaitional models and deep neural networks are explored for challenging image tasks. These innovative ideas are validated by significant performance gains.
first_indexed 2025-11-14T11:20:00Z
format Thesis
id curtin-20.500.11937-82126
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:20:00Z
publishDate 2020
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-821262023-01-12T08:18:18Z Image Processing by Variational Methods, Stochastic Programming and Deep Learning Techniques Tan, Lu This thesis is to investigate effective approaches to tackle different problems in computer vision: variational methods are first studied for image processing, illusory contour reconstruction and segmentation as well as their efficiency improvement. Next, we develop variational segmentation methods by stochastic programming, tackling diverse problems with random noises. Third, the fusion approaches integrating varaitional models and deep neural networks are explored for challenging image tasks. These innovative ideas are validated by significant performance gains. 2020 Thesis http://hdl.handle.net/20.500.11937/82126 Curtin University fulltext
spellingShingle Tan, Lu
Image Processing by Variational Methods, Stochastic Programming and Deep Learning Techniques
title Image Processing by Variational Methods, Stochastic Programming and Deep Learning Techniques
title_full Image Processing by Variational Methods, Stochastic Programming and Deep Learning Techniques
title_fullStr Image Processing by Variational Methods, Stochastic Programming and Deep Learning Techniques
title_full_unstemmed Image Processing by Variational Methods, Stochastic Programming and Deep Learning Techniques
title_short Image Processing by Variational Methods, Stochastic Programming and Deep Learning Techniques
title_sort image processing by variational methods, stochastic programming and deep learning techniques
url http://hdl.handle.net/20.500.11937/82126