Handwritten bangla digit recognition using classifier combination through DS technique

Authors:
Subhadip Basu;Ram Sarkar;Nibaran Das;Mahantapas Kundu;Mita Nasipuri;Dipak Kumar Basu
Affiliations:
Computer Sc. & Engg. Dept., MCKV Institute of Engineering, Liluah, Howrah, India;Computer Sc. & Engg. Dept., Jadavpur University, Kolkata, India;Computer Sc. & Engg. Dept., Jadavpur University, Kolkata, India;Computer Sc. & Engg. Dept., Jadavpur University, Kolkata, India;Computer Sc. & Engg. Dept., Jadavpur University, Kolkata, India;Computer Sc. & Engg. Dept., Jadavpur University, Kolkata, India
Venue:
PReMI'05 Proceedings of the First international conference on Pattern Recognition and Machine Intelligence
Year:
2005

Citing 2
Cited 4

Uncertainty Management in Expert Systems

IEEE Expert: Intelligent Systems and Their Applications
Recognition of Handprinted Bangla Numerals Using Neural Network Models

AFSS '02 Proceedings of the 2002 AFSS International Conference on Fuzzy Systems. Calcutta: Advances in Soft Computing

A hierarchical approach to recognition of handwritten Bangla characters

Pattern Recognition
Recognition of Numeric Postal Codes from Multi-script Postal Address Blocks

PReMI '09 Proceedings of the 3rd International Conference on Pattern Recognition and Machine Intelligence
A novel framework for automatic sorting of postal documents with multi-script address blocks

Pattern Recognition
A genetic algorithm based region sampling for selection of local features in handwritten digit recognition application

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The work presents an application of Dempster-Shafer (DS) technique for combination of classification decisions obtained from two Multi Layer Perceptron (MLP) based classifiers for optical character recognition (OCR) of handwritten Bangla digits using two different feature sets. Bangla is the second most popular script in the Indian subcontinent and the fifth most popular language in the world. The two feature sets used for the work are so designed that they can supply complementary information, at least to some extent, about the classes of digit patterns to the MLP classifiers. On experimentation with a database of 6000 samples, the technique is found to improve recognition performances by a minimum of 1.2% and a maximum of 2.32% compared to the average recognition rate of the individual MLP classifiers after 3-fold cross validation of results. The overall recognition rate as observed for the same is 95.1% on average.