Shape-Tailored Features and their Application to Texture Segmentation

Handle URI:
http://hdl.handle.net/10754/317258
Title:
Shape-Tailored Features and their Application to Texture Segmentation
Authors:
Khan, Naeemullah
Abstract:
Texture Segmentation is one of the most challenging areas of computer vision. One reason for this difficulty is the huge variety and variability of textures occurring in real world, making it very difficult to quantitatively study textures. One of the key tools used for texture segmentation is local invariant descriptors. Texture consists of textons, the basic building block of textures, that may vary by small nuisances like illumination variation, deformations, and noise. Local invariant descriptors are robust to these nuisances making them beneficial for texture segmentation. However, grouping dense descriptors directly for segmentation presents a problem: existing descriptors aggregate data from neighborhoods that may contain different textured regions, making descriptors from these neighborhoods difficult to group, leading to significant errors in segmentation. This work addresses this issue by proposing dense local descriptors, called Shape-Tailored Features, which are tailored to an arbitrarily shaped region, aggregating data only within the region of interest. Since the segmentation, i.e., the regions, are not known a-priori, we propose a joint problem for Shape-Tailored Features and the regions. We present a framework based on variational methods. Extensive experiments on a new large texture dataset, which we introduce, show that the joint approach with Shape-Tailored Features leads to better segmentations over the non-joint non Shape-Tailored approach, and the method out-performs existing state-of-the-art.
Advisors:
Sundaramoorthi, Ganesh
Committee Member:
Alouini, Mohamed-Slim ( 0000-0003-4827-1793 ) ; Wonka, Peter ( 0000-0003-0627-9746 )
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Program:
Electrical Engineering
Issue Date:
Apr-2014
Type:
Thesis
Appears in Collections:
Theses; Electrical Engineering Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.advisorSundaramoorthi, Ganeshen
dc.contributor.authorKhan, Naeemullahen
dc.date.accessioned2014-05-21T09:29:20Z-
dc.date.available2014-05-21T09:29:20Z-
dc.date.issued2014-04en
dc.identifier.urihttp://hdl.handle.net/10754/317258en
dc.description.abstractTexture Segmentation is one of the most challenging areas of computer vision. One reason for this difficulty is the huge variety and variability of textures occurring in real world, making it very difficult to quantitatively study textures. One of the key tools used for texture segmentation is local invariant descriptors. Texture consists of textons, the basic building block of textures, that may vary by small nuisances like illumination variation, deformations, and noise. Local invariant descriptors are robust to these nuisances making them beneficial for texture segmentation. However, grouping dense descriptors directly for segmentation presents a problem: existing descriptors aggregate data from neighborhoods that may contain different textured regions, making descriptors from these neighborhoods difficult to group, leading to significant errors in segmentation. This work addresses this issue by proposing dense local descriptors, called Shape-Tailored Features, which are tailored to an arbitrarily shaped region, aggregating data only within the region of interest. Since the segmentation, i.e., the regions, are not known a-priori, we propose a joint problem for Shape-Tailored Features and the regions. We present a framework based on variational methods. Extensive experiments on a new large texture dataset, which we introduce, show that the joint approach with Shape-Tailored Features leads to better segmentations over the non-joint non Shape-Tailored approach, and the method out-performs existing state-of-the-art.en
dc.language.isoenen
dc.subjectTexture Segmentationen
dc.subjectSegmentationen
dc.subjectFeaturesen
dc.subjectDescriptoren
dc.subjectTexture Analysisen
dc.subjectShape-tailored featuresen
dc.titleShape-Tailored Features and their Application to Texture Segmentationen
dc.typeThesisen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
thesis.degree.grantorKing Abdullah University of Science and Technologyen_GB
dc.contributor.committeememberAlouini, Mohamed-Slimen
dc.contributor.committeememberWonka, Peteren
thesis.degree.disciplineElectrical Engineeringen
thesis.degree.nameMaster of Scienceen
dc.person.id124838en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.