Journal article
Handwritten Bangla character recognition using a soft computing paradigm embedded in two pass approach
Pattern recognition, Vol.48(6), pp.2054-2071
06/2015
DOI: 10.1016/j.patcog.2014.12.011
Abstract
The work presented here mainly involves recognition of handwritten Bangla characters using a soft computing paradigm embedded within the framework of previously developed Two pass approach. Bangla script, which has nearly 400 character symbols, is used by a vast majority of population in India and Bangladesh. Considering the large number of character classes, Two pass approach is chosen here with some important extensions. Typically, Two pass approach coarsely classifies an unknown sample pattern in a group of pattern classes in first-pass. In second pass, it makes finer classification of the sample by determining its membership to a class within the group. Two major aspects of extensions made with Two pass approach here are development of an algorithmic approach for grouping of various pattern classes needed for the second pass and a soft computing methodology for optimal selection of local regions of character images for extraction of features, specific to each grouping of pattern classes. To test the performances of the method, benchmark databases of handwritten Bangla characters are also developed. A methodology for reading filled in forms of handwritten Bangla characters is also presented here. The experimental results show significant improvement of recognition rates on handwritten Bangla characters compared to traditionally followed Single pass approach.
[Display omitted]
•A soft computing paradigm is designed within the framework of Two pass approach.•The technique is used to evaluate the recognition of handwritten Bangla characters.•The handwritten Bangla characters consist of Basic and Compound and Allographs.•An algorithmic methodology is developed for formation of pattern groups.•GA based local region selection method is used to improve recognition accuracies.
Details
- Title: Subtitle
- Handwritten Bangla character recognition using a soft computing paradigm embedded in two pass approach
- Creators
- Nibaran Das - Computer Science and Engineering Department, Jadavpur University, Kolkata 700032, IndiaRam Sarkar - Computer Science and Engineering Department, Jadavpur University, Kolkata 700032, IndiaSubhadip Basu - Computer Science and Engineering Department, Jadavpur University, Kolkata 700032, IndiaPunam K Saha - Department of Electrical and Computer Engineering, Department of Radiology, The University of Iowa, Iowa City, IA 52242, USAMahantapas Kundu - Computer Science and Engineering Department, Jadavpur University, Kolkata 700032, IndiaMita Nasipuri - Computer Science and Engineering Department, Jadavpur University, Kolkata 700032, India
- Resource Type
- Journal article
- Publication Details
- Pattern recognition, Vol.48(6), pp.2054-2071
- Publisher
- Elsevier Ltd
- DOI
- 10.1016/j.patcog.2014.12.011
- ISSN
- 0031-3203
- eISSN
- 1873-5142
- Language
- English
- Date published
- 06/2015
- Academic Unit
- Electrical and Computer Engineering; Radiology
- Record Identifier
- 9984051749202771
Metrics
24 Record Views