Abstract
In this paper, we exploit the texture feature of local binary pattern (LBP) for handwritten Odia numeral recognition. There are several challenges in the handwritten recognition due to the different writing style of the individuals. The histogram of the block-based LBP is computed considering the block sizes of (4 × 4), (8 × 8) and the whole image and these features are used to classify the numerals. For classification, SVM and single decision tree classifiers have been employed. In this experiment, we evaluated the performance of the block-based LBP on the ISI, Kolkata Odia numeral digital database. The performance of (4 × 4) block-based LBP shows high level of accuracy (97%) for both SVM and single tree classifiers. Single decision tree classifier shows promising results in terms of computational time and hence can be used for real-time applications.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
K. Roy, T. Pal, U. Pal, F. Kimura, Oriya handwritten numeral recognition system, in Proceedings of Eighth International Conference on Document Analysis and Recognition, vol 2 (2005), pp. 770–774.
U. Pal, T. Wakabayashi, F. Kimura, A system for off-line Oriya handwritten character recognition using curvature feature, in 10th International Conference on Information Technology (2007), pp. 227–229
A. Desai, Gujrati handwritten numeral optical character recognition through neural network. Pattern Recogn. 33, 2582–2589 (2010)
M.K. Jindal, R.K. Sharma, G.S. Lehal, Segmentation of horizontally overlapping lines in printed Indian scripts. Int. J. Comput. Intell. Res. 3(4), 277–328 (2007)
N.P. Banashree, D. Andhre, R. Vasanta, P.S. Satyanarayana, OCR for script identification of Hindi (Devanagari) numerals using error diffusion Halftoning Algorithm with neural classifier. Proc. World Acad. Sci. Eng. Technol. 20, 46–50 (2007)
N. Shanthi, K. Duraiswamy, A novel SVM-based handwritten Tamil character recognition. Pattern Anal. Appl. (2009)
T.K. Mishra, B. Majhi, S. Panda, A comparative analysis of image transformation for handwritten Odia numeral recognition, in International Conference on Advances in Computing, Communications and Informatics (ICACCI) (2013)
P. Pushpalata, M. Babita, Recognition of offline handwritten Odia numerals using support vector machine, in International Conference on Computational Intelligence and Networks (2015)
H. Tasnuva, K.A. Haider, Handwritten Bangla numeral recognition using local binary pattern, in 2nd International Conference on Innovations in Science, Engineering and Technology (ICISET) (2015)
T. Ojala, M. Pietikainen, T. Maenpaa, Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. Pattern Anal. Mach. Intell. IEEE Trans. 24(7), 971–987 (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Behera, S., Das, N. (2021). Block-Based Local Binary Pattern for Recognition of Handwritten Odia Numerals. In: Sabut, S.K., Ray, A.K., Pati, B., Acharya, U.R. (eds) Proceedings of International Conference on Communication, Circuits, and Systems. Lecture Notes in Electrical Engineering, vol 728. Springer, Singapore. https://doi.org/10.1007/978-981-33-4866-0_10
Download citation
DOI: https://doi.org/10.1007/978-981-33-4866-0_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-4865-3
Online ISBN: 978-981-33-4866-0
eBook Packages: Computer ScienceComputer Science (R0)