SVM-based hierarchical architectures for handwritten Bangla character recognition

Authors:
Tapan Kumar Bhowmik;Pradip Ghanty;Anandarup Roy;Swapan Kumar Parui
Affiliations:
Read-Ink Technologies Pvt. Ltd., Indiranagar, 560 008, Bangalore, India;Praxis Softek Solutions Pvt. Ltd., Module 616, SDF Building, Sector V, 700 091, Salt Lake City, Kolkata, India;Indian Statistical Institute, Computer Vision and Pattern Recognition Unit, 700 108, Kolkata, India;Indian Statistical Institute, Computer Vision and Pattern Recognition Unit, 700 108, Kolkata, India
Venue:
International Journal on Document Analysis and Recognition
Year:
2009

Citing 0
Cited 5

Handwritten character recognition through two-stage foreground sub-sampling

Pattern Recognition
Segmental K-means learning with mixture distribution for HMM based handwriting recognition

PReMI'11 Proceedings of the 4th international conference on Pattern recognition and machine intelligence
Handwriting Recognition in Indian Regional Scripts: A Survey of Offline Techniques

ACM Transactions on Asian Language Information Processing (TALIP)
An efficient way of combining SVMs for handwritten digit recognition

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
Recognition of Bangla compound characters using structural decomposition

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose support vector machine (SVM) based hierarchical classification schemes for recognition of handwritten Bangla characters. A comparative study is made among multilayer perceptron, radial basis function network and SVM classifier for this 45 class recognition problem. SVM classifier is found to outperform the other classifiers. A fusion scheme using the three classifiers is proposed which is marginally better than SVM classifier. It is observed that there are groups of characters having similar shapes. These groups are determined in two different ways on the basis of the confusion matrix obtained from SVM classifier. In the former, the groups are disjoint while they are overlapped in the latter. Another grouping scheme is proposed based on the confusion matrix obtained from neural gas algorithm. Groups are disjoint here. Three different two-stage hierarchical learning architectures (HLAs) are proposed using the three grouping schemes. An unknown character image is classified into a group in the first stage. The second stage recognizes the class within this group. Performances of the HLA schemes are found to be better than single stage classification schemes. The HLA scheme with overlapped groups outperforms the other two HLA schemes.