South African Sign Language Recognition Using Feature Vectors and Hidden Markov Models

Loading...
Thumbnail Image

Date

2010

Journal Title

Journal ISSN

Volume Title

Publisher

University of the Western Cape

Abstract

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 construct 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%.

Description

>Magister Scientiae - MSc

Keywords

Hidden Markov models, Personal computer (PC), South African Sign Language (SASL), Recognition and Animation, University of the Western Cape (UWC), Gesture Recognition (GR)

Citation