Abstract
Degraded Character Recognition (DCR) is an important area of research in the field of Document Image Analysis and Recognition (DIAR). The degradation of characters poses lot of challenges like broken characters, characters mixed with noise etc. Kannada language script has curves and complex patterns, which makes recognizing these characters very difficult. The degradation in the document can introduce gaps in these patterns, which complicates the recognition problem. In this paper, the importance of Kannada DCR system for printed scripts is addressed and also it proposes a framework consisting of four stages namely preprocessing, rebuilding, feature extraction and classification. This framework is also supported with an efficient implementation that achieved a recognition accuracy of 99% in characters with degradation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sandhya, N., Krishnan, R., Ramesh Babu, D.R.: A language independent characterization of document image noises in historical scripts. Int. J. Comput. Appl. 50(9), 11–18 (2012)
Sandhya, N., Krishnan, R., Ramesh Babu, D.R., Das, P.: A comprehensive pre-processing approach for digital preservation of documents. In: Elsevier Proceedings of International Conference on Emerging Research in Computing, Information, Communication and Applications-(ERCICA-14). ELSEVIER (2014)
Sandhya, N., Krishnan, R., Ramesh Babu, D.R.: A novel local enhancement technique for rebuilding broken characters in a degraded Kannada script. In: IEEE International Advance Computing Conference (2015)
Sandhya, N., Krishnan, R., Ramesh Babu, D.R., Rao, B.: An efficient approach for handling degradation in character recognition. Int. J. Adv. Imaging Paradigms 14, 14–29 (2019)
Sandhya, N., Madhusudan, N., Krishnan, R., Ramesh Babu, D.R.: Handwritten Kannada character recognition using zonal features and multi-class SVM. Int. J. Appl. Eng. Res. (IJAER), 9(20) (2014). ICPRMSP’15, Special Issues
Website for fit discriminate analysis. http://in.mathworks.com/help/stats/fitcdiscr.html
Manjunath Aradhya, V.N., Hemantha Kumar, G., Noushath, S., Shivakumara, P.: Fisher linear discriminant analysis based technique useful for efficient character recognition. In: Fourth International Conference on Intelligent Sensing and Information Processing (2006)
Wei, C., Lin, C.-J.: A comparison of methods for multiclass support vector machines. IEEE Trans. Nueral Netw. 13(2), 1045–1052 (2002)
Barekat, S., Sarrafzadeh, A., Shanbehzadeh, J.: Skew detection of scanned document images. In: Proceedings of the International MultiConference of Engineers and Computer Scientists 2013 vol I, IMECS 2013, 13–15 March 2013, Hong Kong (2013)
Silva, G.F.P., Lins, R.D., Silva, J.M.: Enhancing the filtering-out of the back-to-front interference in color documents with a neural classifier. IEEE (2010)
Website for otsu’s binarization. http://en.wikipedia.org/wiki/Otsu%27s_method
Website for weiner filter. http://www.owlnet.rice.edu/~elec539/Projects99/BACH/proj2/wiener.html
Shafait, F., Breuel, T.M.: A simple and effective approach for border noise removal from document images. In: IEEE 13th International Multitopic Conference, INMIC 2009 (2009)
Pletschacher, S., Hu, J., Antonocopoulos, A.: A new framework for recognition of heavily degraded characters in historical typewritten documents based on semi-supervised clustering. In: ICDAR 2009 (2009)
Nayak, M.R., Nayak, S.: Automatic recognition of handwritten Bengali Broken Characters (BBC): simulating human pattern matching. Int. J. Comput. Appl. 59(9), 27–32 (2012). (0975–8887)
Manoharan, S.: A smart image processing algorithm for text recognition information extraction and vocalization for the visually challenged. J. Innov. Image Process. (JIIP) 1(01), 31–38 (2019)
Gangamma, B., Murthy, K.S., Singh, A.V.: Restoration of degraded historical document image. J. Emerg. Trends Comput. Inf. Sci. 3(5), 792–798 (2012)
Website of Kaleido software & services Kannada OCR. http://kannadaocr.com/downloads/KanScanUserGuide_v10b.pdf
Jindal, M.K., Lehal, G.S., Sharma, R.K.: On segmentation of touching characters and overlapping lines in degraded printed Gurumukhi script. Int. J. Image Graph. 9(3), 321–353 (2009)
Sachan, D., Dutta, S., Naveen, T.S., Jawahar, C.V.: Segmentation of degraded Malayalam words: methods and evaluation. In: Third National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (2011)
Rajashekararadhya, S.V., Vanaja Ranjan, P.: Support vector machine based handwritten numeral recognition of Kannada script. In: IEEE International Advance Computing Conference 2009 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sandhya, N., Krishnan, R., Babu, D.R.R. (2021). A Framework for Degraded Kannada Character Recognition. In: Chen, J.IZ., Tavares, J.M.R.S., Shakya, S., Iliyasu, A.M. (eds) Image Processing and Capsule Networks. ICIPCN 2020. Advances in Intelligent Systems and Computing, vol 1200. Springer, Cham. https://doi.org/10.1007/978-3-030-51859-2_67
Download citation
DOI: https://doi.org/10.1007/978-3-030-51859-2_67
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-51858-5
Online ISBN: 978-3-030-51859-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)