An evaluation of ensemble methods in handwritten word recognition based on feature selection

Author

Günter, Simon ; Bunke, Horst

Author_Institution

Dept. of Comput. Sci., Bern Univ., Switzerland

Volume

1

fYear

2004

fDate

23-26 Aug. 2004

Firstpage

388

Abstract

Handwritten text recognition is one of the most difficult problems in the field of pattern recognition. The combination of multiple classifiers has been proven to be able to increase the recognition rate in difficult problems when compared to single classifiers. In this paper, several novel methods for the creation of classifier ensembles are compared where the individual classifiers use different feature subsets. The methods are evaluated in the context of handwritten word recognition, using a hidden Markov model recognizer as basic classifier.

Keywords

feature extraction; handwritten character recognition; hidden Markov models; pattern classification; classifier ensemble methods; feature selection; feature subsets; handwritten text recognition; handwritten word recognition; hidden Markov model recognizer; multiple classifiers; pattern recognition; Character recognition; Computer science; Handwriting recognition; Hidden Markov models; Machine learning; Optimization methods; Pattern recognition; Text recognition; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on

ISSN

1051-4651

Print_ISBN

0-7695-2128-2

Type

conf

DOI

10.1109/ICPR.2004.1334133

Filename

1334133