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: 51-56

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/IWFHR.2004.26

C. Y. Suen , Concordia University

K. T. Abou-Moustafa , Concordia University and Ecole de Technologie Superieure

M. Cheriet , Ecole de Technologie Superieure

ABSTRACT

Classification of Time-Series data using discriminative models such as SVMs is very hard due to the variable length of this type of data. On the other hand generative models such as HMMs have become the standard tool for modeling Time-Series data due to their efficiency. This paper proposes a general generative/discriminative hybrid that uses HMMs to map the variable length Time-Series data into a fixed P-dimensional vector that can be easily classified using any discriminative model. The hybrid system was tested on the MNIST database for unconstrained handwritten numerals and has achieved an improvement of 1.23% (on the test set) over traditional 2D discrete HMMs.

INDEX TERMS

Generative Models, Discriminative Models, HMMs, SVMs

CITATION

C. Y. Suen,
K. T. Abou-Moustafa,
M. Cheriet,
"Classification of Time-Series Data Using a Generative/Discriminative Hybrid",

*Ninth International Workshop on Frontiers in Handwriting Recognition*, vol. 00, no. , pp. 51-56, 2004, doi:10.1109/IWFHR.2004.26