Abstract
A character is the smallest unit in every line of a script, the development of the script stretches over millions of inscriptions in Kannada, and these inscriptions play a vital role in the reconstruction of Karnataka’s history and its culture. The Kannada script has evolved for more than 1500 years and many inventions, and variations have taken place in the scripts used by various dynasties. Due to these variations occurred in the script, it has been improved in text and formed in a new different style. The objective of the present paper is to digitize and restore the historical Kannada handwritten scripts by applying image enhancement techniques and recognize the individual characters by extracting the HOG features. The LDA, K-nearest neighbour (K-NN), and SVM classifiers are used to identify the dynasties of the characters, whether it belongs to the dynasty of the Hoysala or Vijayanagara or the Mysore Wodeyar. The average classification accuracy of the historical Kannada handwritten characters from the different regimes is; the LDA classifier has yielded 68.4%, the K-NN classifier achieved 85.7%, and the SVM classifier yielded 87.5%. Based on the experimentation, it is noted that the overall classification accuracy is relatively improved with the SVM classifier compared to LDA and K-NN classifiers. Further, the results are also verified manually obtained by epigraphists and linguistic experts, which proves the efficacy of the proposed approach.
The authors are grateful to the authorities of the Rani Channamma University, Belagavi, Karnataka, India for sanctioning minor research project and provided financial assistance to carry out this research work (RCUB/PMEB/2020-21/37 Dt. 15.05.2020).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cun-Zhao, S., Chun-Heng, W., Bai-Hua, X., Zhang, Y., Song, G.: Multi-scale graph-matching based kernel for character recognition from natural scenes. Acta Automatica Sinica 40(4), 751–756 (2014)
Gaurav, D.D., Ramesh, R.: A feature extraction technique based on character geometry for character recognition (2012). CoRR, vol.abs/1202.3884
Bannigidad, P., Gudada, C.: Identification and classification of historical Kannada handwritten document images using GLCM features. Int. J. Adv. Res. Comput. Sci. 9(1), 686–690 (2018). https://doi.org/10.26483/ijarcs.v9i1.5437
Bannigidad, P., Gudada, C.: Restoration of degraded non-uniformally illuminated historical Kannada handwritten document images. Int. J. Comput. Eng. Appl. XII(I), 1–13 (2018)
Manjunath, M.G., Devarajaswamy, G.K.: Kannada Lipi Vikasa, 1st edn. Jagadhguru Sri Madhvacharya Trust, Sri Raghavendra Swami Matta, Mantralaya (2004)
Narasimha Murthy, A.V.: Kannada Lipiya Ugama Mattu Vikasa. Kannada Adhyayana Samsthe, Mysore University, Mysore (1968)
Reddy, D.: Lipiya Huttu Mattu Belavanige-Origin and Evolution of Script. Kannada Pustaka Pradhikara (Kannada Book Authority), Bangalore (2011)
Bannigidad, P., Gudada, C.: Restoration of degraded historical kannada handwritten document images using image enhancement techniques. In: Proceedings of the Eighth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2016), pp. 498–508. Springer, Cham (2016)
Kamble, P.M., Hegadi, R.S.: Handwritten Marathi character recognition using R-HOG feature. Procedia Comput. Sci. 45, 266–274 (2015). https://doi.org/10.1016/j.procs.2015.03.137
Iamsa-at, S., Horata, P.: Handwritten character recognition using histograms of oriented gradient features in deep learning of artificial neural network. In: Proceedings of the International Conference on IT Convergence and Security (ICITCS), pp. 1–5 (2013). https://doi.org/10.1109/ICITCS.2013.6717840
Surinta, O., Schomaker, L., Wiering, M.: Handwritten character classification using he hotspot feature extraction technique. In: Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods, pp. 261–264 (2012). https://doi.org/10.5220/0003712002610264
Choudharya, A., Rishib, R., Ahlawat, S.: Off-line handwritten character recognition using features extracted from binarization technique. In: AASRI Conference on Intelligent Systems and Control (2013)
Lavrenko, V., Manmath, R.R.: Holistic word recognition for handwritten documents. In: Proceedings of the First International Workshop on Document Image Analysis for Libraries (DIAL-04), p. 278 (2004)
Sanchez, J.A., Bosch, V., Romero, V., Depuydt, K., de Does, J.: A Handwritten text recognition for historical documents in the tranScriptorium Project. In: DATeCH 2014 Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage, pp. 111–117 (2014)
Romero, V., Serrano, N., Toselli, A.H., Sanchez, J.A., Vidal, E.: Handwritten text recognition for historical documents. In: Proceedings of Language Technologies for Digital Heritage and Cultural Heritage Workshop, pp. 90–96 (2011)
Gao, G., Xiangdong, S., Wei, H., Gong, Y.: Classical Mongolian words recognition in historical document. In: ICDAR, vol. 1520–5363, no. 11, pp. 692–697. IEEE (2011)
Mohana, H.S., Navya, K., Srikanth, P.C., Shivakumar, G.: Stone inscribed Kannada character matching Using SIFT. In: Proceeding of IRF International Conference, pp. 126–131 (2014)
Verma, B., Blumenstein, M., Kulkarni, S.: Recent achievements in offline handwriting recognition system. In: International Conference on Computational Intelligence and Multimedia Applications (1998)
Bannigidad, P., Gudada, C.: Age-type identification and recognition of historical Kannada handwritten document images using HOG feature descriptors. In: Proceedings of The International Conference on Computing, Communication and Signal Processing (ICCASP) (2018)
Bannigidad, P., Gudada, C.: Restoration of degraded Kannada handwritten paper inscriptions (hastaprati) using image enhancement techniques. In: Proceedings of the IEEE International Conference on Computer Communication and Informatics (ICCCI -2017), pp. 1–6 (2017). https://doi.org/10.1109/ICCCI.2017.8117697
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bannigidad, P., Gudada, C. (2021). Historical Kannada Handwritten Character Recognition Using Machine Learning Algorithm. In: Abraham, A., et al. Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2020). SoCPaR 2020. Advances in Intelligent Systems and Computing, vol 1383. Springer, Cham. https://doi.org/10.1007/978-3-030-73689-7_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-73689-7_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73688-0
Online ISBN: 978-3-030-73689-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)