Sparse Representations of Hyperspectral Images

Handle URI:
http://hdl.handle.net/10754/583304
Title:
Sparse Representations of Hyperspectral Images
Authors:
Swanson, Robin J. ( 0000-0001-7528-0447 )
Abstract:
Hyperspectral image data has long been an important tool for many areas of sci- ence. The addition of spectral data yields significant improvements in areas such as object and image classification, chemical and mineral composition detection, and astronomy. Traditional capture methods for hyperspectral data often require each wavelength to be captured individually, or by sacrificing spatial resolution. Recently there have been significant improvements in snapshot hyperspectral captures using, in particular, compressed sensing methods. As we move to a compressed sensing image formation model the need for strong image priors to shape our reconstruction, as well as sparse basis become more important. Here we compare several several methods for representing hyperspectral images including learned three dimensional dictionaries, sparse convolutional coding, and decomposable nonlocal tensor dictionaries. Addi- tionally, we further explore their parameter space to identify which parameters provide the most faithful and sparse representations.
Advisors:
Heidrich, Wolfgang ( 0000-0002-4227-8508 )
Committee Member:
Hadwiger, Markus ( 0000-0003-1239-4871 ) ; Ghanem, Bader ( 0000-0002-2044-2434 )
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Program:
Computer Science
Issue Date:
23-Nov-2015
Type:
Thesis
Appears in Collections:
Theses; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.advisorHeidrich, Wolfgangen
dc.contributor.authorSwanson, Robin J.en
dc.date.accessioned2015-12-07T13:18:04Zen
dc.date.available2015-12-07T13:18:04Zen
dc.date.issued2015-11-23en
dc.identifier.urihttp://hdl.handle.net/10754/583304en
dc.description.abstractHyperspectral image data has long been an important tool for many areas of sci- ence. The addition of spectral data yields significant improvements in areas such as object and image classification, chemical and mineral composition detection, and astronomy. Traditional capture methods for hyperspectral data often require each wavelength to be captured individually, or by sacrificing spatial resolution. Recently there have been significant improvements in snapshot hyperspectral captures using, in particular, compressed sensing methods. As we move to a compressed sensing image formation model the need for strong image priors to shape our reconstruction, as well as sparse basis become more important. Here we compare several several methods for representing hyperspectral images including learned three dimensional dictionaries, sparse convolutional coding, and decomposable nonlocal tensor dictionaries. Addi- tionally, we further explore their parameter space to identify which parameters provide the most faithful and sparse representations.en
dc.language.isoenen
dc.subjecthyperspectralen
dc.subjectsparseen
dc.subjectcompressiveen
dc.subjectsensingen
dc.titleSparse Representations of Hyperspectral Imagesen
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.committeememberHadwiger, Markusen
dc.contributor.committeememberGhanem, Baderen
thesis.degree.disciplineComputer Scienceen
thesis.degree.nameMaster of Scienceen
dc.person.id132954en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.