Connan, JamesNaidoo, Nathan Lyle2022-03-072024-10-302022-03-072024-10-302010https://hdl.handle.net/10566/16921>Magister Scientiae - MScThis 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%.enHidden Markov modelsPersonal computer (PC)South African Sign Language (SASL)Recognition and AnimationUniversity of the Western Cape (UWC)Gesture Recognition (GR)University of the Western Cape