Multiview active shape models with SIFT descriptors

Simple item page
dc.contributor.advisorNicolls, Fred Cen_ZA
dc.contributor.authorMilborrow, Stephenen_ZA
dc.date.accessioned2017-01-23T07:37:33Z
dc.date.available2017-01-23T07:37:33Z
dc.date.issued2016en_ZA
dc.description.abstractThis thesis presents techniques for locating landmarks in images of human faces. A modified Active Shape Model (ASM [21]) is introduced that uses a form of SIFT descriptors [68]. Multivariate Adaptive Regression Splines (MARS [40]) are used to efficiently match descriptors around landmarks. This modified ASM is fast and performs well on frontal faces. The model is then extended to also handle non-frontal faces. This is done by first estimating the face's pose, rotating the face upright, then applying one of three ASM submodels specialized for frontal, left, or right three-quarter views. The multiview model is shown to be effective on a variety of datasets.en_ZA
dc.identifier.apacitationMilborrow, S. (2016). <i>Multiview active shape models with SIFT descriptors</i>. (Thesis). University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering. Retrieved from http://hdl.handle.net/11427/22867en_ZA
dc.identifier.chicagocitationMilborrow, Stephen. <i>"Multiview active shape models with SIFT descriptors."</i> Thesis., University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering, 2016. http://hdl.handle.net/11427/22867en_ZA
dc.identifier.citationMilborrow, S. 2016. Multiview active shape models with SIFT descriptors. University of Cape Town.en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Milborrow, Stephen AB - This thesis presents techniques for locating landmarks in images of human faces. A modified Active Shape Model (ASM [21]) is introduced that uses a form of SIFT descriptors [68]. Multivariate Adaptive Regression Splines (MARS [40]) are used to efficiently match descriptors around landmarks. This modified ASM is fast and performs well on frontal faces. The model is then extended to also handle non-frontal faces. This is done by first estimating the face's pose, rotating the face upright, then applying one of three ASM submodels specialized for frontal, left, or right three-quarter views. The multiview model is shown to be effective on a variety of datasets. DA - 2016 DB - OpenUCT DP - University of Cape Town LK - https://open.uct.ac.za PB - University of Cape Town PY - 2016 T1 - Multiview active shape models with SIFT descriptors TI - Multiview active shape models with SIFT descriptors UR - http://hdl.handle.net/11427/22867 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/22867
dc.identifier.vancouvercitationMilborrow S. Multiview active shape models with SIFT descriptors. [Thesis]. University of Cape Town ,Faculty of Engineering & the Built Environment ,Department of Electrical Engineering, 2016 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/22867en_ZA
dc.language.isoengen_ZA
dc.publisher.departmentDepartment of Electrical Engineeringen_ZA
dc.publisher.facultyFaculty of Engineering and the Built Environment
dc.publisher.institutionUniversity of Cape Town
dc.subject.otherElectrical Engineeringen_ZA
dc.subject.otherimage recognitionen_ZA
dc.subject.otherfacial recognitionen_ZA
dc.titleMultiview active shape models with SIFT descriptorsen_ZA
dc.typeDoctoral Thesis
dc.type.qualificationlevelDoctoral
dc.type.qualificationnamePhDen_ZA
uct.type.filetypeText
uct.type.filetypeImage
uct.type.publicationResearchen_ZA
uct.type.resourceThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
thesis_hum_milborrow_2016_stephen.pdf
Size:
11.68 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
PhD / Doctoral