Abstract
The digital image processing has got much attention of the researchers towards development of automatic optical character recognition system. The document image analysis mainly focused on printed and handwritten document images. In printed document image analysis, the input image is that of machine printed document, where as in handwritten document image analysis, it is of document, handwritten by different persons on a paper by using pen or pencil. Presently, most of the research work addresses issues related to handwritten document images and the Kannada script. The printed script recognition system is much easier than handwritten script recognition system. In printed documents, font style and size of the characters are standardized, where as handwritten characters vary in size and style of font from person to person and time to time, which is a very tedious job for recognition. In this paper, a new novel approach is proposed for restoration of degraded historical Kannada handwritten documents using the combination of special local and global binarization techniques, by eliminating of non-uniformly illuminated background. The performance evaluation is done by extracting geometric feature values of Pricision, Recall, F-Measure, MSE and PSNR and these results are compared with manual results obtained by the Epigraphists. It is also compared with other standard methods, namely, souvola and niblack in the literature, which demonstrate the efficacy of the proposed method. Restoration of degraded historical Kannada handwritten documents plays an important role in age identification, Kannada character recognition and classification for the Kannada handwritten documents.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ranganath, D., Holi, G.: Hybrid binarization technique for degraded document images. In: IACC, pp. 893–898. IEEE (2015)
Kundal, N., Anantdeep: Performance evaluation of novel historical documents restoration algorithm. IJCSET 5(7), 278–282 (2015)
Ranganath, D., Holi, G.: Historical document enhancement using shearlet transform and mathematical morphological operations. In: IACC, pp. 303–307. IEEE (2015)
Soumya, A., Hemanth Kumar, G.: Preprocessing of camera captured inscription and segmentation of handwritten Kannada text. IJARCCE 3(5), 6794–6803 (2014)
Saxena, L.: Effective thresholding of ancient degraded manuscript folio image. IJCET 4(5), 285–291 (2013)
Su, B., Lu, S., Tan, C.L.: Robust document image binarization technique for degraded document images. IEEE Trans. Image Process. 22(4), 1408–1417 (2013)
Gangamma, B., Srikanta Murthy, K.: Enhancement of degraded historical Kannada documents. IJCA 29(11), 1–6 (2011)
Gangamma, B., Srikanta Murthy, K., Singh, A.V.: Restoration of degraded historical document image. J. Emerg. Trends Comput. Inf. Sci. 3(5), 792–798 (2012)
Gangamma, B., Srikanta Murthy, K.: An effective technique using non local means and morphological operations to enhance degraded historical document. (IJEECS) Int. J. Electr. Electron. Comput. Syst. 4(2), 335–344 (2011)
Gangamma, B., Srikanta Murthy, K.: A Combined approach for degraded historical documents denoising using curvelet and mathematical morphology. IEEE (2010)
Fadoua, D.: Towards restoring historic document degraded over time. In: DIAL 2006. IEEE, August 2006
Yan, C., Leedham, G.: Decompose threshold approach to handwriting extraction in degraded historical document images. In: IWFHR-9. IEEE (2004)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979). doi:10.1109/TSMC.1979.4310076
Zheng, D., Wang, J., Xiao, Z.: Image enhancement based on local standard deviation. J. Inf. Comput. Sci. 2(2), 429–437 (2005)
Acknowledgments
The authors are indebted to The Chairman, Department of P.G. Studies and Research in Kannada, Gulbarga University, Kalaburgi, for providing degraded Kannada handwritten document images and visualizing the computed results. The authors are also grateful to Bickley diary and H-DIBCO series datasets.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Bannigidad, P., Gudada, C. (2018). Restoration of Degraded Historical Kannada Handwritten Document Images Using Image Enhancement Techniques. In: Abraham, A., Cherukuri, A., Madureira, A., Muda, A. (eds) Proceedings of the Eighth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2016). SoCPaR 2016. Advances in Intelligent Systems and Computing, vol 614. Springer, Cham. https://doi.org/10.1007/978-3-319-60618-7_49
Download citation
DOI: https://doi.org/10.1007/978-3-319-60618-7_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-60617-0
Online ISBN: 978-3-319-60618-7
eBook Packages: EngineeringEngineering (R0)