South African sign language recognition using feature vectors and Hidden Markov Models

Description

<p>This 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&rsquo / 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%</p>

Links & Downloads

1. http://etd.uwc.ac.za/index.php?module=etd&action=viewtitle&id=gen8Srv25Nme4_8533_1297923615

Tags

Optical pattern recognition

Mathematical models

Image processing

Digital techniques

Markov processes.

Additional Fields

Identifer	oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:uwc/oai:UWC_ETD:http%3A%2F%2Fetd.uwc.ac.za%2Findex.php%3Fmodule%3Detd%26action%3Dviewtitle%26id%3Dgen8Srv25Nme4_8533_1297923615
Date	January 2010
Creators	Nathan Lyle Naidoo
Source Sets	South African National ETD Portal
Language	English
Detected Language	English
Type	Thesis and dissertation
Format	Pdf
Coverage	ZA
Rights	Copyright: University of the Western Cape