Show simple item record

dc.contributor.authorTan, Lu
dc.contributor.supervisorLing Lien_US
dc.contributor.supervisorWan-Quan Liuen_US

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.

dc.publisherCurtin Universityen_US
dc.titleImage Processing by Variational Methods, Stochastic Programming and Deep Learning Techniquesen_US
curtin.departmentSchool of Electrical Engineering, Computing and Mathematical Sciencesen_US
curtin.accessStatusOpen accessen_US
curtin.facultyScience and Engineeringen_US
curtin.contributor.orcidTan, Lu [0000-0002-3361-3060]en_US

Files in this item


This item appears in the following Collection(s)

Show simple item record