The University of Queensland Homepage
Go to advanced search page

Hidden Markov Models for Spatio-Temporal Pattern Recognition and Image Segmentation

Lovell, Brian C. (2003). Hidden Markov Models for Spatio-Temporal Pattern Recognition and Image Segmentation. In: Mukherjee, Dipti Prasad and Pal, Srimanta, Proceedings of the International Conference on Advances in Pattern Recognition. International Conference on Advances in Pattern Recognition, Calcutta, (60-65). 10-13 December.

 
Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
icapr.pdf   icapr.pdf application/pdf 403.49KB 1227

Author(s) Lovell, Brian C.
Title of paper Hidden Markov Models for Spatio-Temporal Pattern Recognition and Image Segmentation
Conference name International Conference on Advances in Pattern Recognition
Conference location Calcutta
Conference dates 10-13 December
Proceedings title Proceedings of the International Conference on Advances in Pattern Recognition
Editor(s) Mukherjee, Dipti Prasad
Pal, Srimanta
Place published Kolkata
Publisher Allied Publishers
Publication date 2003
Volume number 1
Issue number 1
ISBN 81-7764-532-3
Start page 60
End page 65
Total pages 6
Language eng
Abstract/Summary Time and again hidden Markov models have been demonstrated to be highly effective in one-dimensional pattern recognition and classification problems such as speech recognition. A great deal of attention is now focussed on 2-D and possibly 3-D applications arising from problems encountered in computer vision in domains such as gesture, face, and handwriting recognition. Despite their widespread usage and numerous successful applications, there are few analytical results which can explain their remarkably good performance and guide researchers in selecting topologies and parameters to improve classification performance.
Subjects 280207 Pattern Recognition
Keyword(s) iris-research
image segmentation
pattern recognition
Additional Notes Invited Paper
 
Versions
Version Filter Type
Access Statistics: 606 Abstract Views, 1227 File Downloads Detailed Statistics
Created: Wed, 25 Feb 2004, 10:00:00 EST by Brian C. Lovell on behalf of School of Information Technol and Elec Engineering. Detailed History