A MLP Classifier for Both Printed and Handwritten Bangla Numeral Recognition
This paper concerns automatic recognition of both printed and handwritten Bangla numerals. Such mixed numerals may appear in documents like application forms, postal mail, bank checks etc. Some pixel-based and shape-based features are chosen for the purpose of recognition. The pixel-based features are normalized pixel density over 4 X 4 blocks in which the numeral bounding-box is partitioned. The shape-based features are normalized position of holes, end-points, intersections and radius of curvature of strokes found in each block. A multi-layer neural network architecture was chosen as classifier of the mixed class of handwritten and printed numerals. For the mixture of twenty three different fonts of printed numerals of various sizes and 10,500 handwritten numerals, an overall recognition accuracy of 97.2% has been achieved.
KeywordsHide Layer Optical Character Recognition Handwritten Character Scaled Conjugate Gradient Postal Mail
Unable to display preview. Download preview PDF.
- 2.Le Cun, Y., Boser, B., Denker, J.S., Howard, R.E., Habbard, W., Jackel, L.D., Henderson, D.: Handwritten digit recognition with a back-propagation network. Advances in neural information processing systems, 396–404 (1990)Google Scholar
- 4.Bhattacharya, U., Chaudhuri, B.B.: A majority voting scheme for multiresolution recognition of handprinted numerals. In: International Conference on Document Analysis and Recognition, vol. 1, p. 16 (2003)Google Scholar
- 5.Bhattacharya, U., Das, T.K., Datta, A., Parui, S.K., Chaudhuri, B.B., Pal, N.R., Pal, S.: A hybrid scheme for handprinted numeral recognition based on a self-organizing network and MLP classifiers. International Journal for Pattern Recognition and Artificial Intelligence 16(7), 845–864 (2002)CrossRefGoogle Scholar
- 6.On the choice of training set, architecture and combination rule of multiple MLP classifiers for multiresolution recognition of handwritten characters, Frontiers in Handwriting Recognition, IWFHR-9 2004. pp. 419–424 (2004)Google Scholar
- 11.Basu, S., Chaudhuri., C., Kundu, M., Nasipuri, M., Basu, D.K., Pal, N.R., Kasabov, N., Mudi, R.L., Pal, S., Parui, S.K.: A two-pass approach to pattern classification. In: Kaynak, O., Alpaydın, E., Oja, E., Xu, L. (eds.) ICANN 2003 and ICONIP 2003. LNCS, vol. 2714, pp. 781–786. Springer, Heidelberg (2003)Google Scholar
- 13.Niblack, W.: An Introduction to Digital Image Processing, pp. 115–116. Prentice-Hall, Englewood Cliffs (1986)Google Scholar
- 14.He, X.C., Yung, N.H.C.: Curvature scale space corner detector with adaptive threshold and dynamic region of support. In: Proceedings of the 17th International Conference on Pattern Recognition. ICPR 2004, August 23-26, 2004, vol. 2, pp. 791–794 (2004); Tang,Y. , Cheng, H.D., Suen, C.Y.: Transformation-Ring-Projection (TRP) Algorithm and Its VLSI Implementation, Character & Handwriting Recognition: Expanding Frontiers, World Scientific Publishing Co. Pte. Ltd., Singapore (1991)Google Scholar
- 15.Hornik, K., Stinchombe, M., White, H.: Neural Networks 2, 359 (1990)Google Scholar
- 16.Heaton, J.: Introduction to Neural Networks with Java, ch. 5. Heaton Research Inc.Google Scholar
- 18.Chester, D.L.: Why Two Hidden Layers are Better than One. In: IJCNN-90-WASH-DC, vol. 1, pp. 265–268. Lawrence Erlbaum, Mahwah (1990)Google Scholar
- 19.Ostafe, D.: Neural Network Hidden Layer Number Determination Using Pattern Recognition Techniques. In: 2nd Romanian-Hungarian Joint Symposium on Applied Computational Intelligence, SACI 2005 (2005)Google Scholar
- 20.Verma, B.: A Contour Code Feature Based Segmentation For Handwriting Recognition. In: Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003) (2003)Google Scholar