Ensemble of HMM classifiers based on the clustering validity index for a handwritten numeral recognizer

Authors:
Albert Hung-Ren Ko;Robert Sabourin;Alceu de Souza Britto, Jr.
Affiliations:
University of Quebec, LIVIA, École de Technologie Supérieure, 1100 Notre-Dame West Street, H3C 1K3, Montreal, Quebec, Canada;University of Quebec, LIVIA, École de Technologie Supérieure, 1100 Notre-Dame West Street, H3C 1K3, Montreal, Quebec, Canada;Pontifical Catholic University of Parana, PPGIA, Rua Imaculada Conceicao, 1155, PR 80215-901, Curitiba, Brazil
Venue:
Pattern Analysis & Applications
Year:
2009

Citing 0
Cited 1

LoGID: An adaptive framework combining local and global incremental learning for dynamic selection of ensembles of HMMs

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new scheme for the optimization of codebook sizes for Hidden Markov Models (HMMs) and the generation of HMM ensembles is proposed in this paper. In a discrete HMM, the vector quantization procedure and the generated codebook are associated with performance degradation. By using a selected clustering validity index, we show that the optimization of HMM codebook size can be selected without training HMM classifiers. Moreover, the proposed scheme yields multiple optimized HMM classifiers, and each individual HMM is based on a different codebook size. By using these to construct an ensemble of HMM classifiers, this scheme can compensate for the degradation of a discrete HMM.