Ninth International Workshop on Frontiers in Handwriting Recognition (2004)

Kokubunji, Tokyo, Japan

Oct. 26, 2004 to Oct. 29, 2004

ISSN: 1550-5235

ISBN: 0-7695-2187-8

pp: 100-105

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/IWFHR.2004.68

Richard I. A. Davis , University of Queensland

Peter J. Kootsookos , University of Queensland

Nianjun Liu , University of Queensland

Brian C. Lovell , University of Queensland

ABSTRACT

Hidden Markov models using the Fully-Connected, Left-Right and Left-Right Banded model structures are applied to the problem of alphabetical letter gesture recognition. We examine the effect of training techniques, in particular the Baum-Welch and Viterbi Path Counting techniques, on each of the model structures. We show that recognition rates improve when moving from a Fully-Connected model to a Left-Right model and a Left-Right Banded ?staircase? model with peak recognition rates of 84.8%, 92.31% and 97.31% respectively. The Left-Right Banded model in conjunction with the Viterbi Path Counting present the best performance. Direct calculation of model parameters from analysis of the physical system was also tested, yielding a peak recognition rate of 92%, but the simplicity and efficiency of this approach is of interest.

INDEX TERMS

null

CITATION

Richard I. A. Davis,
Peter J. Kootsookos,
Nianjun Liu,
Brian C. Lovell,
"Model Structure Selection and Training Algorithms for an HMM Gesture Recognition System",

*Ninth International Workshop on Frontiers in Handwriting Recognition*, vol. 00, no. , pp. 100-105, 2004, doi:10.1109/IWFHR.2004.68SEARCH