Avatar animation from SignWriting notation

Simple item page
dc.contributor.advisorGhaziasgar, Mehrdad
dc.contributor.advisorConnan, James
dc.contributor.authorAbrahams, Kenzo
dc.date.accessioned2015-07-28T11:24:35Z
dc.date.accessioned2024-10-30T14:00:53Z
dc.date.available2015-07-28T11:24:35Z
dc.date.available2024-10-30T14:00:53Z
dc.date.issued2015
dc.description>Magister Scientiae - MScen_US
dc.description.abstractThe SASL project at the University of the Western Cape is in the process of developing a machine translation system that can translate fully-fledged phrases between South African Sign Language (SASL) and English in real-time.To visualise sign language,the system aims to make use of a 3D humanoid avatar created by van Wyk. Moemedi used this avatar to create an animation system that visualises a small set of simple Phrases from very simple SignWriting notation input. This research aims to achieve an animation system that can render full sign language sentences given complex SignWriting notation glyphs with multiple sections. The specific focus of the research is achieving animations that are accurate representations of the SignWriting input in terms of the five fundamental parameters of sign language, namely, hand motion, location, orientation and shape, as well as non-manual features such as facial expressions. An experiment Was carried out to determine the accuracy of the proposed system on a set of 20 SASL phrases annotated with SignWriting notation. It was found that the proposed system is highly accurate, achieving an average accuracy of 81.6%.en_US
dc.identifier.urihttps://hdl.handle.net/10566/16976
dc.language.isoenen_US
dc.publisherUniversity of the Western Capeen_US
dc.rights.holderUniversity of the Western Capeen_US
dc.subjectAnimationen_US
dc.subjectHumanoid avataren_US
dc.subjectKey frame animationen_US
dc.subjectSignWritingen_US
dc.titleAvatar animation from SignWriting notationen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
abrahams_k_msc_sc_2015.pdf
Size:
12.2 MB
Format:
Adobe Portable Document Format
Description:
Thesis
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.62 KB
Format:
Plain Text
Description:
Download

Collections

Magister Scientiae - MSc (Computer Science)