Abstract
This paper proposes an automatic recognition scheme for handprinted Bangla (an Indian script) numerals using neural network models. A Topology Adaptive Self Organizing Neural Network is first used to extract from a numeral pattern a skeletal shape that is represented as a graph. Certain features like loops, junctions etc. present in the graph are considered to classify a numeral into a smaller group. If the group is a singleton, the recognition is done. Otherwise, multilayer perceptron networks are used to classify different numerals uniquely. The system is trained using a sample data set of 1880 numerals and we obtained 90.56% correct recognition rate on a test set of another 3440 samples. The proposed scheme is sufficiently robust with respect to considerable object noise.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bhattacharya U. and Parui S. K.: Self-Adaptive Learning Rates in Backpropagation Algorithm Improve Its Function Approximation Performance. Proc. of the IEEE International Conference on Neural Networks, Australia (1995) 2784–2788.
Bhattacharya U., Chaudhuri B. B. and Parui S. K.: An MLP-based Texture Segmentation Method Without Selecting a Feature Set. Image and Vision Computing. 15 (1997), 937–948.
Datta A., Parui S. K. and Chaudhuri B. B.: Skeletonization by a Topology Adaptive Self-Organizing Neural Network, Pattern Recognition. 34 (2001) 617–629.
Dutta A., Chaudhuri S.: Bengali Alpha-Numeric Character Recognition Using Curvature Features. Pattern Recognition. 26 (1993) 1757–1770.
Garris M. D., Wilson C. L. and Blue J. L.: Neural Network-Based Systems for Handprint OCR Applications, IEEE Transactions on Image Processing, 7 (1998) 1097–1112.
Hecht-Nielson R.: Neurocomputing. New York: Addison-Wesley, 1990, Chapter 5.
Lam L., Suen C. Y.: Structural Classi.cation and Relaxation Matching of Totally Unconstrained Handwritten ZIP-Code Numbers. Pattern Recognition. 21 (1988) 19–31.
Mori S. Suen C. Y., Yamamoto K.: Historical Review of OCR Research and Development. Proceedings of the IEEE. 80 (1992) 1029–1058.
Pal U. and Chaudhuri B. B.: Automatic Recognition of Unconstrained Off-line Bangla Hand-written Numerals, Advances in Multimodal Interfaces, Springer Verlag Lecture Notes on Computer Science (LNCS-1948), Eds. T. Tan, Y. Shi and W. Gao. (2000) 371–378.
Shimura M.: Multicategory Learning Classifiers for Character Reading, IEEE Trans. Syst. Man Cybern. 3 (1973) 74–85.
Suen C. Y.: Computer Recognition of Unconstrained Handwritten Numerals. Proceedings of the IEEE. 80 (1992) 1162–1180.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bhattacharya, U., Das, T.K., Datta, A., Parui, S.K., Chaudhuri, B.B. (2002). Recognition of Handprinted Bangla Numerals Using Neural Network Models. In: Pal, N.R., Sugeno, M. (eds) Advances in Soft Computing — AFSS 2002. AFSS 2002. Lecture Notes in Computer Science(), vol 2275. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45631-7_31
Download citation
DOI: https://doi.org/10.1007/3-540-45631-7_31
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43150-3
Online ISBN: 978-3-540-45631-5
eBook Packages: Springer Book Archive