Off-line Recognition of Hand-Written Bengali Numerals Using Morphological Features
- 1 November 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 363-368
Abstract
This paper proposes a technique for automatic recognition of Bengali handwritten numerals using multiple feature sets. We discuss about some novel Morphological features and k-curvature feature extraction technique to recognize handwritten scripts. We use different multi-layer perceptron (MLP) classifiers to train this feature spaces and then fuse those classifiers using modified `Naive'-Bayes combination to increase accuracy of recognition result. The individual feature sets give reasonably high accuracy up-to 96.25%, while fused classifier gives accuracy of 97.75%.Keywords
This publication has 12 references indexed in Scilit:
- Handwritten Numeral Databases of Indian Scripts and Multistage Recognition of Mixed NumeralsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Handwritten Bangla numeral recognition system and its application to postal automationPattern Recognition, 2007
- Fuzzy model based recognition of handwritten numeralsPattern Recognition, 2006
- A Complete System for Bangla Handwritten Numeral RecognitionIETE Journal of Research, 2006
- Indian script character recognition: a surveyPattern Recognition, 2004
- Devnagari numeral recognition by combining decision of multiple connectionist classifiersSādhanā, 2002
- Decision templates for multiple classifier fusion: an experimental comparisonPattern Recognition, 2001
- Bengali alpha-numeric character recognition using curvature featuresPattern Recognition, 1993
- Methods of combining multiple classifiers and their applications to handwriting recognitionIEEE Transactions on Systems, Man, and Cybernetics, 1992
- Machine recognition of constrained hand printed devanagariPattern Recognition, 1977