Shape Representation and Recognition of Bangla Characters using Fourier Descriptor
|
10.5120/3995-5658 |
M A Naser, Abdur Raquib Ridwan and Md.Murad Hossain. Article: Shape Representation and Recognition of Bangla Characters using Fourier Descriptor. International Journal of Computer Applications 33(2):35-40, November 2011. Full text available. BibTeX
@article{key:article,
author = {M. A. Naser and Abdur Raquib Ridwan and Md.Murad Hossain},
title = {Article: Shape Representation and Recognition of Bangla Characters using Fourier Descriptor},
journal = {International Journal of Computer Applications},
year = {2011},
volume = {33},
number = {2},
pages = {35-40},
month = {November},
note = {Full text available}
}
Abstract
Fourier descriptors are used for representing the shapes as well as extracting the features of the characters. It has the advantage of being invariant to the affine transforms. It possesses the ability to reconstruct the original shape. Moreover, all the descriptors are not required to describe the character. Hence huge reduction in feature size is possible. K-nearest neighbor classifier is used to recognize the characters and the accuracy is 98.4% for training set while it is 89.3% for a test set. A case wise in-depth analysis is provided for each misclassified character at the end of the result.
Reference
- Gonzalez, R, C & Woods R, E. ‘Digital Image Processing’, Second Edition, Prentice-Hall of India Private Limited, 2006.
- Pal, U & Tripathy, N. ‘A contour distance-based approach for multi-oriented and multi-sized character recognition’. Journal of Sadhana. Vol 34, pp. 755-765, October, 2009.
- Sharma, N, Pal, U, Kimura, F & Pal, S. ‘Recognition of Off-Line Handwritten Devnagari Characters Using Quadratic Classifier’, Computer Vision, Graphics and Image Processing. ICVGIP , LNCS 4338, pp. 805 – 816, 2006.
- Persoon, E, & Fu, K, S. ‘Shape discrimination using Fourier descriptors’. In the Proceedings of the IEEE Trans., SMC-7, No.3. pp. 170-179, March 1977.
- Richard, C, W & Hemami, H. ‘Identification of three- dimensional objects using Fourier descriptors of the boundary curve’ In the Proceedings of the IEEE Trans., SMC4. pp. 371-378, July 1974.
- Wallace, T, P & Wintz, P, A. ‘An efficient three- dimensional aircraft recognition algorithm using normalized Fourier descriptors’, Computer Graphics Image Processing. Vol 13. pp. 99-126, 1980.
- 7 Zahn, C, T & Roskies, R, Z. ‘Fourier descriptors for plane closed curves’, In the Proceedings of the IEEE Trans. Computer. Vol.21. pp. 269-281, 1972.
- Knyrak, A & Buaeshi, H, E. ‘Classification of digitized curves represented by signatures and Fourier Descriptors’. In Computer Vision and Shape Recognition, Krzyzak and Kasvand, Eds, World Scientific. pp. 241-259, 1989.
- Granlund, G,H. ‘Fourier preprocessing for hand print character recognition’, In the Proceedings of the IEEE Trans. Computers, Vol.21, pp. 195-201, 1972.
- Shridhar, M & Badreldin A. ‘High accuracy character recognition algorithm using Fourier and topological descriptors", Pattern Recognition, Vo1.17, NOS, pp. 515-524, 1984.
- Datta, S, Chaudhury, S & Parthasarathy G. ‘On recognition of Bengali numerals with backpropagation learning’, In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Vol.1, pp. 94 - 99, 1992, USA.