Hand shape estimation for South African sign language
| dc.contributor.advisor | Connan, James | |
| dc.contributor.advisor | Ghaziasgar, Mehrdad | |
| dc.contributor.author | Li, Pei | |
| dc.date.accessioned | 2015-08-13T15:47:55Z | |
| dc.date.accessioned | 2024-10-30T14:00:36Z | |
| dc.date.available | 2015-08-13T15:47:55Z | |
| dc.date.available | 2024-10-30T14:00:36Z | |
| dc.date.issued | 2012 | |
| dc.description | >Magister Scientiae - MSc | en_US |
| dc.description.abstract | Hand shape recognition is a pivotal part of any system that attempts to implement Sign Language recognition. This thesis presents a novel system which recognises hand shapes from a single camera view in 2D. By mapping the recognised hand shape from 2D to 3D,it is possible to obtain 3D co-ordinates for each of the joints within the hand using the kinematics embedded in a 3D hand avatar and smooth the transformation in 3D space between any given hand shapes. The novelty in this system is that it does not require a hand pose to be recognised at every frame, but rather that hand shapes be detected at a given step size. This architecture allows for a more efficient system with better accuracy than other related systems. Moreover, a real-time hand tracking strategy was developed that works efficiently for any skin tone and a complex background. | en_US |
| dc.identifier.uri | https://hdl.handle.net/10566/16909 | |
| dc.language.iso | en | en_US |
| dc.publisher | University of the Western Cape | en_US |
| dc.rights.holder | University of the Western Cape | en_US |
| dc.subject | Sign language | en_US |
| dc.subject | Sign language recognition | en_US |
| dc.subject | Hand shape recognition | en_US |
| dc.subject | Hand tracking | en_US |
| dc.title | Hand shape estimation for South African sign language | en_US |
| dc.type | Thesis | en_US |