Show simple item record

dc.contributor.advisorConnan, James
dc.contributor.authorNaidoo, Nathan Lyle
dc.contributor.otherDept. of Computer Science
dc.contributor.otherFaculty of Science
dc.date.accessioned2013-12-10T14:10:46Z
dc.date.available2011/02/17 08:20
dc.date.available2011/02/17
dc.date.available2013-12-10T14:10:46Z
dc.date.issued2010
dc.identifier.urihttp://hdl.handle.net/11394/2527
dc.descriptionMasters of Scienceen_US
dc.description.abstractThis thesis presents a system for performing whole gesture recognition for South African Sign Language. The system uses feature vectors combined with Hidden Markov models. In order to constuct a feature vector, dynamic segmentation must occur to extract the signer's hand movements. Techniques and methods for normalising variations that occur when recording a signer performing a gesture, are investigated. The system has a classification rate of 69%.en_US
dc.language.isoenen_US
dc.publisherUniversity of the Western Capeen_US
dc.subjectOptical pattern recognitionen_US
dc.subjectMathematical modelsen_US
dc.subjectImage processingen_US
dc.subjectDigital techniquesen_US
dc.subjectMarkov processesen_US
dc.titleSouth African sign language recognition using feature vectors and Hidden Markov Modelsen_US
dc.typeThesisen_US
dc.rights.holderUniversity of the Western Capeen_US
dc.description.countrySouth Africa


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record