Model based odia numeral recognition using fuzzy aggregated features

doi:10.1007/s11704-014-3354-9

Front. Comput. Sci.

2014, Vol. 8

Issue (6) : 916-922 https://doi.org/10.1007/s11704-014-3354-9

RESEARCH ARTICLE

Model based odia numeral recognition using fuzzy aggregated features

Tusar Kanti MISHRA(

),Banshidhar MAJHI,Pankaj K SA,Sandeep PANDA

Department of Computer Science and Engineering, National Institute of Technology, Rourkela 769008, India

Download: PDF(407 KB)
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

In this paper, an efficient scheme for recognition of handwritten Odia numerals using hidden markov model (HMM) has been proposed. Three different feature vectors for each of the numeral is generated through a polygonal approximation of object contour. Subsequently, aggregated feature vector for each numeral is derived from these three primary feature vectors using a fuzzy inference system. The final feature vector is divided into three levels and interpreted as three different states for HMM. Ten different three-state ergodic hidden markov models (HMMs) are thus constructed corresponding to ten numeral classes and parameters are calculated from these models. For the recognition of a probe numeral, its log-likelihood against these models are computed to decide its class label. The proposed scheme is implemented on a dataset of 2500 handwritten samples and a recognition accuracy of 96.3% has been achieved. The scheme is compared with other competent schemes.

Keywords handwritten character recognition HMM pattern recognition Odia numeral OCR

Corresponding Author(s): Tusar Kanti MISHRA

Issue Date: 27 November 2014

Cite this article:

Tusar Kanti MISHRA,Banshidhar MAJHI,Pankaj K SA, et al. Model based odia numeral recognition using fuzzy aggregated features[J]. Front. Comput. Sci., 2014, 8(6): 916-922.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-014-3354-9
https://academic.hep.com.cn/fcs/EN/Y2014/V8/I6/916

1	Ghods V, Kabir E, Razzazi F. Decision fusion of horizontal and vertical trajectories for recognition of online Farsi subwords. Engineering Applications of Artificial Intelligence, 2013, 26: 544-550 https://doi.org/10.1016/j.engappai.2012.05.013
2	Espa?a-Boquera S, Castro-Bleda M J, Gorbe-Moya J, Zamora-Martinez F. Improving offline handwritten text recognition with hybrid hmm/ann models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(4): 767-779 https://doi.org/10.1109/TPAMI.2010.141
3	Wang J, Zhu R. Handwritten nushu character recognition based on hidden markov model. Journal of Computers, 2010, 5(5): 663-670 https://doi.org/10.4304/jcp.5.5.663-670
4	Al-Muhtaseb H A, Mahmoud S A, Qahwaji R S. Recognition of offline printed arabic text using hidden markov models. Signal Processing, 2008, 88(12): 2902-2912 https://doi.org/10.1016/j.sigpro.2008.06.013
5	Wang S, Uchida S, Liwicki M, Feng Y. Part-based methods for handwritten digit recognition. Frontiers of Computer Science, 2013, 7(4): 514-525 https://doi.org/10.1007/s11704-013-2297-x
6	Artieres T, Marukatat S, Gallinari P. Online handwritten shape recognition using segmental hidden markov models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(2): 205-217 https://doi.org/10.1109/TPAMI.2007.38
7	Bhowmik T K, Parui S K, Bhattacharya U, Shaw B. An hmm based recognition scheme for handwritten oriya numerals. In: Proceedings of the 9th International Conference on Information Technology. 2006, 105-110
8	Cavalin P R, Sabourin R, Suen C Y, A S Britto Jr. Evaluation of incremental learning algorithms for hmm in the recognition of alphanumeric characters. Pattern Recognition, 2009, 42(12): 3241-3253 https://doi.org/10.1016/j.patcog.2008.10.012
9	Razzak M I, Anwar F, Husain S, Belaid A, Sher M. Hmm and fuzzy logic: a hybrid approach for online urdu script-based languages character recognition. Knowledge-Based Systems, 2010, 23(8): 914-923 https://doi.org/10.1016/j.knosys.2010.06.007
10	Zeng W, Meng X, Yang C, Huang L. Feature extraction for online handwritten characters using delaunay triangulation. Computers & Graphics, 2006, 30(5): 779-786 https://doi.org/10.1016/j.cag.2006.07.007
11	Theeramunkong T, Wongtapan C. Off-line isolated handwritten thai ocr using island-based projection with n-gram model and hidden markov models. Information Processing &Management, 2005, 41(1): 139-160 https://doi.org/10.1016/j.ipm.2004.04.011
12	Pal U, Wakabayashi T, Kimura F. A system for off-line Oriya handwritten character recognition using curvature feature. IEEE Computer Society, 2007, 227-229
13	Wakabayashi T, Pal U, Kimura F, Miyake Y. F-ratio based weighted feature extraction for similar shape character recognition. In: Proceedings of the International Conference on Document Analysis and Recognition. 2009, 196-200
14	Bag S, Bhowmick P, Harit G. Recognition of Bengali handwritten characters using skeletal convexity and dynamic programming. In: Proceedings of International Conference on Emerging Applications of Information Technology. 2011, 265-268
15	Farooq F, Govindaraju V, Perrone M. Pre-processing methods for handwritten arabic documents. In: Proceedings of the International Conference on Document Analysis and Recognition. 2005, 267-271
16	Pizzi N J, Pedrycz W. Aggregating multiple classification results using fuzzy integration and stochastic feature selection. International Journal of Approximate Reasoning, 2010, 51(8): 883-894 https://doi.org/10.1016/j.ijar.2010.05.003
17	Frigui H, Hwang C. Fuzzy clustering and aggregation of relational data with instance-level constraints. IEEE Transactions on Fuzzy Systems, 2008, 16(6): 1565-1581 https://doi.org/10.1109/TFUZZ.2008.2005692
18	Sonka M, Hlavac V, Boyle R. Image Processing: Analysis andMachine Vision. 2nd ed. Cengage Learning, 2008
19	Perez O, Piccardi M, Garcia J, Patricio M, Molina J. Comparison between genetic algorithms and the baum-welch algorithm in learning hmms for human activity classification. Lecture Notes in Computer Science, 2007, 4448: 399-406 https://doi.org/10.1007/978-3-540-71805-5_44
20	Khotanzad A, Hong Y. Invariant image recognition by Zernike moments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12: 489-497 https://doi.org/10.1109/34.55109

[1]	Gan HUANG, Hee Yong YOUN. Proactive eviction of flow entry for SDN based on hidden Markov model[J]. Front. Comput. Sci., 2020, 14(4): 144502-.
[2]	Wangyang YING, Lei ZHANG, Hongli DENG. Sichuan dialect speech recognition with deep LSTM network[J]. Front. Comput. Sci., 2020, 14(2): 378-387.
[3]	Xudong ZHU, Zhijing LIU. Human behavior clustering for anomaly detection[J]. Front Comput Sci Chin, 2011, 5(3): 279-289.
[4]	Wai-Ki CHING, Ho-Yin LEUNG, Zhenyu WU, Hao JIANG. Modeling default risk via a hidden Markov model of multiple sequences[J]. Front Comput Sci Chin, 2010, 4(2): 187-195.
[5]	Tang Yuanyan. Status of pattern recognition with wavelet analysis[J]. Front. Comput. Sci., 2008, 2(3): 268-294.
[6]	DAI Ruwei, XIAO Baihua, LIU Chenglin. Chinese character recognition: history, status and prospects[J]. Front. Comput. Sci., 2007, 1(2): 126-136.
[7]	LUO Weiqi, QU Zhenhua, PAN Feng, HUANG Jiwu. A survey of passive technology for digital image forensics[J]. Front. Comput. Sci., 2007, 1(2): 166-179.
[8]	Sargur N. Srihari, Xuanshen Yang, Gregory R. Ball. Offline Chinese handwriting recognition: an assessment of current technology[J]. Front. Comput. Sci., 2007, 1(2): 137-155.

Viewed

Full text

Abstract

Cited

Shared

Discussed