Evaluation of Different Strategies to Optimize an HMM-Based Character Recognition System

Author

Santos, Murilo ; Ko, Albert ; Oliveira, Luis S. ; Sabourin, Robert ; Koerich, Alessandro L. ; Britto, Alceu S.

Author_Institution

Pontificia Univ. Catolica do Parana (PUCPR), Curitiba, Brazil

fYear

2009

Firstpage

666

Lastpage

670

Abstract

Different strategies for combination of complementary features in an HMM-based method for handwritten character recognition are evaluated. In addition, a noise reduction method is proposed to deal with the negative impact of low probability symbols in the training database. New sequences of observations are generated based on the original ones, but considering a noise reduction process. The experimental results based on 52 classes of alphabetic characters and more than 23,000 samples have shown that the strategies proposed to optimize the HMM-based recognition method are very promising.

Keywords

handwritten character recognition; hidden Markov models; image denoising; image sequences; probability; HMM-based handwritten character recognition system; alphabetic character; noise reduction method; observation sequence; optimization; probability symbol; Character recognition; Handwriting recognition; Hidden Markov models; Neural networks; Noise reduction; Optimization methods; Spatial databases; Stochastic processes; Text analysis; Text recognition; HMM-based method; character recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2009. ICDAR '09. 10th International Conference on

Conference_Location

Barcelona

ISSN

1520-5363

Print_ISBN

978-1-4244-4500-4

Electronic_ISBN

1520-5363

Type

conf

DOI

10.1109/ICDAR.2009.230

Filename

5277474