Skip to main content
SpringerLink
Log in

A Novel Complete Denoising Solution for Old Malayalam Palm Leaf Manuscripts

  • APPLICATION PROBLEMS
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

Palm leaves were used in ancient culture as writing material for documenting traditional literature, scientific agreements, and history. Such scriptures are an integral part of our community and must be protected in the best way possible. But the extraction of data from palm leaf is a frustrating activity because of numerous challenges such as the enormous collection of noise characters and the difficulties in reading and interpreting the ancient Malayalam script. In this paper a novel denoising technique that eliminates all sorts of noises that can exist in palm leaf manuscript is developed. The major drawback of any palm leaf denoising method is, even after removing the noise in the palm leaves, the punch holes remain intact. Here, with the new technique developed, punch holes were completely eliminated, preserving the information in the manuscripts. Performance of this new denoising method was compared with several existing techniques and found that this new technique produced the best PSNR, SSIM, and MSE values of 19.40 dB, 0.244, and 0.001 respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.
Fig. 9.
Fig. 10.
Fig. 11.
Fig. 12.
Fig. 13.
Fig. 14.
Fig. 15.
Fig. 16.
Fig. 17.
Fig. 18.
Fig. 19.
Fig. 20.
Fig. 21.

Similar content being viewed by others

REFERENCES

  1. B. Bataineh, S. N. H. S. Abdullah, K. Omar, and M. Faidzul, “Adaptive thresholding methods for documents image binarization,” in Pattern Recognition. MCPR 2011, Ed. by J. F. Martínez-Trinidad, J. A. Carrasco-Ochoa, C. Ben-Youssef Brants, and E. R. Hancock, Lecture Notes in Computer Science, vol. 6718 (Springer, Berlin, 2011), pp. 230–239. https://doi.org/10.1007/978-3-642-21587-2_25

    Book  Google Scholar 

  2. T. M. Breuel, “High performance text recognition using a hybrid convolutional-LSTM implementation,” in 14th IAPR Int. Conf. on Document Analysis and Recognition (ICDAR), Kyoto, 2017 (IEEE, 2017), pp. 11–16. https://doi.org/10.1109/ICDAR.2017.12

  3. A. Buades, B. Coll, and J. M. Morel, “Image denoising by non-local averaging,” in Proc. (ICASSP’05) IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Philadelphia, 2005 (IEEE, 2005), pp. 25–28. https://doi.org/10.1109/ICASSP.2005.1415332

  4. Y. Chen and L. Wang, “Broken and degraded document images binarization,” Neurocomputing 237, 272–280 (2017). https://doi.org/10.1016/j.neucom.2016.12.058

    Article  Google Scholar 

  5. K. D. Devi and P. U. Maheswari, “Digital acquisition and character extraction from stone inscription images using modified fuzzy entropy-based adaptive thresholding,” Soft Comput. 23, 2611–2626 (2019). https://doi.org/10.1007/s00500-018-3610-2

    Article  Google Scholar 

  6. P. Ge, P. Yu, Haiyan Li, and Hongsong Li, “Stroke edge based binarization algorithm for the palm leaf manuscripts,” in 2nd Int. Conf. on Image, Vision and Computing (ICIVC), Chengdu, China, 2017 (IEEE, 2017), pp. 778–782. https://doi.org/10.1109/ICIVC.2017.7984660

  7. M. Gogoi and M. Ahmed, “Image quality parameter detection: A study,” Int. J. Comput. Sci. Eng. 4, 110–116 (2016).

    Google Scholar 

  8. G. K. Dhal, A. Das, N. Ghoshal, and S. Das, “Variance based brightness preserved dynamic histogram equalization for image contrast enhancement,” Pattern Recognit. Image Anal. 28, 747–757 (2018). https://doi.org/10.1134/S1054661818040211

    Article  Google Scholar 

  9. G. K. Dhal and S. Das, “Combination of histogram segmentation and modification to preserve the original brightness of the images,” Pattern Recognit. Image Anal. 27, 200–212 (2017). https://doi.org/10.1134/S1054661817020031

    Article  Google Scholar 

  10. A. Guruvareddy, K. S. R. Krishna, and M. N. G. Prasad, “An effective local contrast enhancement technique by blending of local statistics and Genetic Algorithm,” Pattern Recognit. Image Anal. 21, 606–615 (2011). https://doi.org/10.1134/S1054661811040080

    Article  Google Scholar 

  11. S. M. A. Hasan and K. Ko, “Depth edge detection by image-based smoothing and morphological operations,” J. Comput. Des. Eng. 3, 191–197 (2016). https://doi.org/10.1016/j.jcde.2016.02.002

    Article  Google Scholar 

  12. D. U. Kumar, G. V. Sreekumar, and U. A. Athvankar, “Traditional writing system in Southern India—Palm leaf manuscripts,” Des. Thoughts 2, 2–7 (2009).

    Google Scholar 

  13. T. R. V. Lakshmi, “Reduction of features to identify characters from degraded historical manuscripts,” Alexandria Eng. J. 57, 2393–2399 (2018). https://doi.org/10.1016/j.aej.2017.09.009

    Article  Google Scholar 

  14. T. R. V. Lakshmi, P. N. Sastry, and T. V. Rajinikanth, “A novel 3D approach to recognize Telugu palm leaf text,” Eng. Sci. Technol., Int. J. 20, 143–150 (2017). https://doi.org/10.1016/j.jestch.2016.06.006

    Article  Google Scholar 

  15. T. R. V. Lakshmi, P. N. Sastry, and T. V. Rajinikanth, “Feature selection to recognize text from palm leaf manuscripts,” Signal Image Video Process. 12, 223–229 (2018). https://doi.org/10.1007/s11760-017-1149-9

    Article  Google Scholar 

  16. N. V. Mamaev, A. S. Lukin, and D. V. Yurin, “HeNLM-LA3D: A three-dimensional locally adaptive Hermite functions expansion based non-local means algorithm for CT applications,” Pattern Recognit. Image Anal. 25, 658–668 (2015). https://doi.org/10.1134/S105466181504015X

    Article  Google Scholar 

  17. S. Milyaev and I. Laptev, “Towards reliable object detection in noisy images,” Pattern Recognit. Image Anal. 27, 713–722 (2017). https://doi.org/10.1134/S1054661817040149

    Article  Google Scholar 

  18. M. A. Hambbal, P. Zhijun, and L. F. Ishabailu, “Image noise reduction and filtering techniques,” Int. J. Sci. Res. 6, 2033–2038 (2017).

    Google Scholar 

  19. K. Ntirogiannis, B. Gatos, and I. Pratikakis, “Performance evaluation methodology for historical document image binarization,” IEEE Trans. Image Process. 22, 595–609 (2013). https://doi.org/10.1109/TIP.2012.2219550

    Article  MathSciNet  MATH  Google Scholar 

  20. E. Paulus, M. Suryani, S. Hadi, and I. N. Yulita, “A novel scheme for handwritten binarization method on sundanese palm leaf document images,” Second Int. Conf. on Informatics and Computing (ICIC), Jayapura, Indonesia, 2017 (IEEE, 2017), pp. 1–5. https://doi.org/10.1109/IAC.2017.8280586

  21. V. B. S. Prasath, “Image denoising by anisotropic diffusion with inter-scale information fusion,” Pattern Recognit. Image Anal. 27, 748–753 (2017). https://doi.org/10.1134/S1054661817040174

    Article  Google Scholar 

  22. G. P. Renieblas, A. T. Nogués, A. M. González, N. G. León, and E. G. del Castillo, “Structural similarity index family for image quality assessment in radiological images,” J. Med. Imaging 4, 035501 (2017). https://doi.org/10.1117/1.JMI.4.3.035501

    Article  Google Scholar 

  23. U. Sara, M. Akter, and M. S. Uddin, “Image quality assessment through FSIM, SSIM, MSE and PSNR—A comparative study,” J. Comput. Commun. 7, 8–18 (2019). https://doi.org/10.4236/jcc.2019.73002

    Article  Google Scholar 

  24. S. Adheesh, “The public life of Sanskrit manuscripts,” in Traces of Words: Art and Calligraphy from Asia, Ed. by F. Nakamura (2017).

    Google Scholar 

  25. M. Sezgin and S. Bulent, “Survey over image thresholding techniques and quantitative performance evaluation,” J. Electron. Imaging 13, 146–168 (2004). https://doi.org/10.1117/1.1631315

    Article  Google Scholar 

  26. S. Sabeenian, M. E. Paramasivam, and P. M. Dinesh, “Appraisal of localized binarization methods on Tamil palm-leaf manuscripts,” in Int. Conf. on Wireless Communications, Signal Processing and Networking (WiSPNET), Chennai, India, 2016 (IEEE, 2016), pp. 793–797. https://doi.org/10.1109/WiSPNET.2016.7566242

  27. K. Subramani and S. Murugavalli, “A novel binarization method for degraded tamil palm leaf images,” in Eighth Int. Conf. on Advanced Computing (ICoAC), Chennai, India, 2017 (IEEE, 2017), pp. 176–181. https://doi.org/10.1109/ICoAC.2017.7951765

  28. D. Sudarsan, P. Vijayakumar, S. Biju, S. Sanu, S. K. Shivadas, “Digitalization of malayalam palm leaf manuscripts based on contrast-based adaptive binarization,” in IEEE Int. Conf. on Wireless Commun., Signal Process. Networking (WiSPNET), Chennai, India, 2018 (IEEE, 2018), pp. 1–4. https://doi.org/10.1109/WiSPNET.2018.8538588

  29. D. Sudarsan and D. Sankar, “A Novel approach for Denoising palm leaf manuscripts using Image Gradient approximations,” in 3rd Int. Conf. on Electronics, Communications and Aerospace Technology (ICECA), Coimbatore, India, 2019 (IEEE, 2019), pp. 506–511. https://doi.org/10.1109/ICECA.2019.8822224

  30. S. M. Vaidya and P. V. Kulkarnri, “Writing in ancient India and writing materials - In the study of manuscripts,” Int. J. Innovative Res. Adv. Studies 3, 240–246 (2016).

    Google Scholar 

  31. M. Varalakshmamma and T. Venkateswarlu, “Restoration of noisy and noiseless fence occlusion images,” Pattern Recognit. Image Anal. 30, 428–439 (2020). https://doi.org/10.1134/S1054661820030281

    Article  Google Scholar 

  32. E. Vats, A. Hast, and P. Singh, “Automatic document image binarization using Bayesian optimization,” in Proc. of the 4th Int. Workshop on Historical Document Imaging and Processing, Kyoto, 2017 (Association for Computing Machinery, New York, 2017), pp. 89–94. https://doi.org/10.1145/3151509.3151520

  33. J. Yousefie, “Image binarization using Otsu thresholding algorithm,” (2011).

  34. P. Yu, H. Li, P. Ge, and H. Zhou, “A binarization method for palm leaf manuscripts,” in 8th Int. Conf. on Intelligent Human Machine Systems and Cybernetics (IHMSC), Hangzhou, China, 2016 (IEEE, 2016), pp. 174–178. https://doi.org/10.1109/IHMSC.2016.198

  35. X. Zhang, “A modified artificial bee colony algorithm for image denoising using parametric wavelet thresholding method,” Pattern Recognit. Image Anal. 28, 557–568 (2018). https://doi.org/10.1134/S1054661818030215

    Article  Google Scholar 

  36. https://www.mathworks.com/help/images/boundary-tracing-in-images.html.

  37. Stock Photo—detail of a preserved palm leaf manuscripts showing writings about ayurvedic medicines in old Malayalam script from Kerala, India. https://www.123rf.com/.

  38. https://www.dreamstime.com/.

Download references

ACKNOWLEDGMENTS

The authors would like to thank Ms. Sainaba M of the Oriental Institute and Manuscript Library in University of Kerala (Kariavattom campus) for her guidance and help in obtaining the images of Malayalam palm scripts.

Author information

Authors and Affiliations

  1. Division of Electronics Engineering, School of Engineering Cochin University of Science and Technology, 682022, Kochi, India

    Dhanya Sudarsan &  Deepa Sankar

Authors
  1. Dhanya Sudarsan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Deepa Sankar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Dhanya Sudarsan or Deepa Sankar.

Ethics declarations

COMPLIANCE WITH ETHICAL STANDARDS

This article is a completely original work of its authors; it has not been published before and will not be sent to other publications until the PRIA Editorial Board decides not to accept it for publication.

Conflict of Interest

The authors declare that they have no conflicts of interest.

Additional information

Dhanya Sudarsan. Born 1985. Graduated with a Bachelor’s degree from the Department of Information Technology of the School of Engineering, Cochin University of Science and Technology (CUSAT) in 2008 and Master’s degree from Rajagiri School of Engineering and Technology in 2013. Currently pursuing PhD from the Department of Electronics of the School of Engineering, Cochin University of Science and Technology and working as an Assistant Professor in the Department of computer Science of Muthoot Institute of Technology and Science. Scientific interests: image processing, deep learning, and computer networking. Author of more than ten international conference papers and three international journal papers.

Deepa Sankar. Born in 1974. Acquired BTech Degree from Model Engineering College, CUSAT, Kerala in 1995. MTech and PhD Degrees from the Department of Electronics, Cochin University of Science and Technology(CUSAT), Kerala in 2003 and 2013, respectively. Currently working as Professor at School of Engineering, CUSAT, Kerala. Areas of interests: image processing, pattern recognition, and fractals. She has more than 30 publications in various international journals and conferences.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dhanya Sudarsan, Deepa Sankar A Novel Complete Denoising Solution for Old Malayalam Palm Leaf Manuscripts. Pattern Recognit. Image Anal. 32, 187–204 (2022). https://doi.org/10.1134/S1054661822010096

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1054661822010096

Keywords:

Search

Navigation