A novel feature extraction approach for online Bengali and Devanagari character recognition

Author

Ghosh, Rajib ; Roy, Partha Pratim

Author_Institution

CSE Dept., Nat. Inst. of Technol. Patna, Patna, India

fYear

2015

fDate

19-20 Feb. 2015

Firstpage

483

Lastpage

488

Abstract

This paper presents an online handwritten character recognition system for two major Indic scripts-Bengali and Devanagari. In this proposal, a novel approach for feature extractions is described in which each online stroke information of a character is divided into a number of local zones. For each online stroke information different structural and directional features are extracted separately in each of these local zones. Next, these features are concatenated and fed to SVM classifier for recognition. The character recognition accuracy obtained is 87.48% for Bengali script and 84.10% for Devanagari script on 4900 and 5000 test samples respectively.

Keywords

feature extraction; handwritten character recognition; image classification; support vector machines; Devanagari character recognition; SVM classifier; directional feature; feature extraction; major Indic scripts; online Bengali character recognition; online handwritten character recognition; stroke information; structural feature; Accuracy; Character recognition; Feature extraction; Handwriting recognition; Hidden Markov models; Trajectory; Writing; Online handwriting; SVM; character recognition; zone-wise features;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Integrated Networks (SPIN), 2015 2nd International Conference on

Conference_Location

Noida

Print_ISBN

978-1-4799-5990-7

Type

conf

DOI

10.1109/SPIN.2015.7095313

Filename

7095313