Abstract
Handwritten character recognition is one of the most explored branch of optical Character Recognition in the field of research and development for the past many years by many researchers. Although it has gained its importance for its successful outcomes in innumerable applications in recognition system but as a part of our research we have represented a handwritten character recognition for Odia complex alphabets. The proposed method is implemented over 3168 complex Odia characters. Feature selection is a leading principle which is an integral part of OCR in handling the prominent features from the data sets associated with high number of variables as well as features. The rate of accuracy and the efficiency of classification phase depends on the implimenation of a productive feature selection algorithm. The correlation based feature selection algorithm is used in this paper to fulfil the purpose of feature selection method on the extracted features from complex letters. The proposed adaptive Extreme Learning Machine algorithm for single layer feed forward neural network is the fusion of ELM and evolutionary algorithm can able to achieve our objective by accelerating the spontaneous selection of the number of hidden layer neurons and achieving high classification accuracy. The anatomy of the experimental result analysis demonstrates that the above submitted algorithms are coherent for processing odia complex alphabets by yielding high classification accuracy .
Similar content being viewed by others
References
Shrivastava V, Sharma N (2012) Artificial neural network based optical character recognition, ar**v preprint ar**v:1211.4385
Hecht-Nielsen R (1992) Theory of the backpropagation neural network 65–93
Ertuğrul ÖF, Kaya Y (2014) A detailed analysis on extreme learning machine and novel approaches based on elm. Am J Comput Sci Eng 1:43–50
Dash M, Liu H (1997) Feature Selection for Classification, Intelligent Data Analysis, 1:131–56
Jarungthai P, Chiewchanwattana S, Sunat K (2014) Handwritten character recognition using generalized radial basis function extreme learning machine with centers selection 1–5
Chaudhuri A, Mandaviya K, Badelia P, Ghosh SK (2017) Optical character recognition systems for english language 85–107
Kibria MG, et al (2012) Bengali optical character recognition using self organizing map. In: 2012 International Conference on Informatics, Electronics & Vision (ICIEV), IEEE, pp. 764–769
Belagali N, Angadi SA (2016) Ocr for handwritten kannada language script. Int. J. Recent Trends Eng. Res. (IJRTER) 2:190–197
Wang K, ** J, Wang Q (2009) High performance chinese/english mixed ocr with character level language identification, in: 2009 10th International Conference on Document Analysis and Recognition, IEEE, 406–410
Wang G-G, Lu M, Dong Y-Q, Zhao X-J (2016) Self-adaptive extreme learning machine. Neural Comput. Appl. 27:291–303
Sethi RK, Mohanty KK (2020) Optical odia character classification using cnn and transfer learning: A deep learning approach. Int. Res. J. Eng. Technol. (IRJET) 7:3885–3890
Nayak M, Nayak AK (2015) Odia-conjunct character recogntion using evolutionary algorithm, Asian Journal of Applied Sciences 3
Dash B, Pradhan S, Rana D (2016) Odia offline character recognition using dwt features, IOSR J. Electron. Commun. Eng.(IOSR-JECE) 31–37
Jha V, Parvathi K (2020) Feature selection for character recognition of handwritten devanagari and odia scripts. Int. J. Eng. Res. Technol. 13:1974
Pal U, Wakabayashi T, Kimura F (2007) A system for off-line oriya handwritten character recognition using curvature feature, in: 10th international conference on information technology (ICIT 2007), IEEE, 227–229
Cao J, Lin Z, Huang G-B (2012) Self-adaptive evolutionary extreme learning machine. Neural Process. Lett. 36:285–305
Cao J, Zhang K, Luo M, Yin C, Lai X (2016) Extreme learning machine and adaptive sparse representation for image classification. Neural Netw. 81:91–102
Mahmoud SA, Olatunji SO (2009) Automatic recognition of off-line handwritten arabic (indian) numerals using support vector and extreme learning machines, International Journal of. Imaging 2:34–53
Muhammad’Arif Mohamad DN, Hassan H, Haron H (2015) A review on feature extraction and feature selection for handwritten character recognition. Int. J. Adv. Comput. Sci. Appl. 6:204–212
Chouikhi N, Alimi AM (2018) Adaptive extreme learning machine for recurrent beta-basis function neural network training, ar**v preprint ar**v:1810.13135
Sethy A, Patra PK (2019) Off-line odia handwritten character recognition: an axis constellation model based research. Int. J. Innovative Technol. Exploring Eng. (IJITEE) 8:788–793
Singh S, Sarangi PK, Singla C, Sahoo AK (2020) Odia character recognition system: A study on feature extraction and classification techniques, Materials Today: Proceedings
Kumar G, Bhatia PK (2014) A detailed review of feature extraction in image processing systems, in, Fourth international conference on advanced computing & communication technologies. IEEE 2014:5–12
Chandrashekar G, Sahin F (2014) A survey on feature selection methods. Comput. Electr. Eng. 40:16–28
Urbanowicz RJ, Meeker M, La Cava W, Olson RS, Moore JH (2018) Relief-based feature selection: introduction and review. J. Biomed. Informat. 85:189–203
Hall MA (1999) Correlation-based feature selection for machine learning
Soliman OS, Rassem A (2012) Correlation based feature selection using quantum bio inspired estimation of distribution algorithm, in: International Workshop on Multi-disciplinary Trends in Artificial Intelligence, Springer, 318–329
Huang G-B, Chen L (2008) Enhanced random search based incremental extreme learning machine. Neurocomputing 71:3460–3468
**ao C, Dong Z, Xu Y, Meng K, Zhou X, Zhang X (2016) Rational and self-adaptive evolutionary extreme learning machine for electricity price forecast. Memetic Comput. 8:223–233
Ku J, **ng K (2017) Self-adaptive differential evolutionary extreme learning machine and its application in facial age estimation 112–117
Fedorovici LO, Precup RE, Dragan F, Purcaru C (2013) Evolutionary optimization-based training of convolutional neural networks for ocr applications, in: 2013 17th International Conference on System Theory, Control and Computing (ICSTCC), 207–212. https://doi.org/10.1109/ICSTCC.2013.6688961
Mohanty S, Bebartta HND (2011) Performance comparison of svm and k-nn for oriya character recognition, International Journal of Advanced Computer Science and Applications, Special Issue on Image Processing and Analysis, 112–116
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nayak, S., Biswal, P.K., Pradhan, S. et al. Implementation of an integrated classification approach of adaptive extreme learning machine and correlation based feature selection for odia complex characters. Int. j. inf. tecnol. 14, 3739–3749 (2022). https://doi.org/10.1007/s41870-022-01008-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41870-022-01008-6