Design and Analysis of a novel 2D Edge Preservation Adaptive Wavelet Anisotropic Bilateral Filter for Image Restoration of Palm Leaf Manuscripts

Design and Analysis of a novel 2D Edge Preservation Adaptive Wavelet Anisotropic Bilateral Filter for Image Restoration of Palm Leaf Manuscripts
  IJETT-book-cover           
  
© 2022 by IJETT Journal
Volume-70 Issue-1
Year of Publication : 2022
Authors : T.Jerry Alexander, S.Suresh Kumar, V.Vedanarayanan
DOI :  10.14445/22315381/IJETT-V70I1P238

How to Cite?

T.Jerry Alexander, S.Suresh Kumar, V.Vedanarayanan, "Design and Analysis of a novel 2D Edge Preservation Adaptive Wavelet Anisotropic Bilateral Filter for Image Restoration of Palm Leaf Manuscripts," International Journal of Engineering Trends and Technology, vol. 70, no. 3, pp. 334-341, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I1P238

Abstract
In the ancient olden period, vital information related to medicines, science, grammar, astrology, mathematics was written on the palm leaves because of its easy availability and reliability. These leaves that are a few hundred years of age are preserved in libraries all over the world. Presently, due to age factors and other factors like weather conditions, pests, improper storage and handling factors, etc., these Palm Leaf Manuscripts (PLM) suffer from degradation. Image restoration plays a vital role in the retrieval of characters text written on older manuscripts made from palm leaves which are affected due to physical wear and tear. Image restoration can be performed through various statistical linear and non-linear filters that are available widely. In this research, a novel 2D Edge Preservation Adaptive Wavelet Anisotropic Bilateral Filter (EPAWABF) is proposed for the restoration of palm leaf manuscript images. To prove the eminence of the proposed restoration technique, the proposed 2D EPAWABF filter is compared with different filters such as 2D Adaptive Median Filter, 2D Adaptive Log Filter, 2D Spatial Domain Filter, 2D Adaptive Wiener Filter and 2D Adaptive Bilateral Filter. Performance evaluation using metrics like peak signal to noise ratio (PSNR) and mean square error (MSE) prove the credibility of the proposed filter for the restoration of PLM.

Keywords
Palm-leaf manuscript, restoration, 2D Adaptive Median Filter, 2D Adaptive Wiener Filter, 2D Adaptive Log Filter, 2D Spatial Domain Filter, 2D Adaptive Bilateral Filter.

Reference
[1] M. Suryani, E. Paulus, S. Hadi, U. A. Darsa, and J. C. Burie, The Handwritten Sundanese Palm Leaf Manuscript Dataset from 15th Century in Proceedings of the International Conference on Document Analysis and Recognition, ICDAR 1 (2017) 796–800.
[2] M. W. A. Kesiman, S. Prum, J. C. Burie, and J. M. Ogier, Study on feature extraction methods for character recognition of Balinese script on palm leaf manuscript images in Proceedings - International Conference on Pattern Recognition.0 (2016) 4017–4022.
[3] O. Surinta and R. Chamchong, Image segmentation of historical handwriting from palm leaf manuscripts, IFIP Int. Fed. Inf. Process. 288 (2008) 182–189.
[4] M. W. A. Kesiman, S. Prum, I. M. G. Sunarya, J. C. Burie, and J. M. Ogier, An analysis of ground truth binarized image variability of palm leaf manuscripts in 5th International Conference on Image Processing, Theory, Tools and Applications IPTA. (2015) 229–233.
[5] M. W. A. Kesiman, J. C. Burie, J. M. Ogier, and P. Grangé, Knowledge Representation and Phonological Rules for the Automatic Transliteration of Balinese Script on Palm Leaf Manuscript, Comput. y Sist. 21(4) (2017) 739–747.
[6] D. Valy, M. Verleysen, S. Chhun, and J. C. Burie, Character and text recognition of Khmer historical palm leaf manuscripts, Proc. Int. Conf. Front. Handwrit. Recognition, ICFHR. (2018) 13–18.
[7] P. Lertratanakehakarn, Digital preservation of palm-leaf manuscripts in Thailand, Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics). 8839 (2014) 12–21.
[8] E. Kavallieratou and E. Stamatatos, Improving the quality of degraded document images, in Proceedings - Second International Conference on Document Image Analysis for Libraries, DIAL. (2006) 340–349.
[9] B. Chandramouli and K. Mallikarjuna, Enumeration of various Ayurvedic formulations listed in an ancient palm-leaf manuscript of Rayalaseema region in Andhra Pradesh state, India, J. Ethnopharmacol., 251 (2020).
[10] R. Hedjam and M. Cheriet, Historical document image restoration using a multispectral imaging system, Pattern Recognit. 46(8) (2013) 2297–2312.
[11] T. J. Alexander and S. S. Kumar, A novel binarization technique based on Whale Optimization Algorithm for better restoration of palm leaf manuscript, J. Ambient Intell. Humaniz. Comput. No. (2020) 1-8.
[12] M. W. A. Kesiman and G. A. Pradnyana, Image Patch Extraction in Text Area of Balinese Palm Leaf Manuscripts with Gabor Filters. 394 (2020) 19–23.
[13] M. P. Krishna, A. Sriram, and N. B. Puhan, Clustering-based image binarization in palm leaf manuscripts, Souvenir 2014 IEEE Int. Adv. Comput. Conf. IACC. 1 (2014) 1060–1065.
[14] R. S. Ratheash and M. M. Sathik, A Detailed Survey of Text Line Segmentation Methods in Handwritten Historical Documents and Palm Leaf Manuscripts, 8 (2019) 99–103.
[15] M. W. A. Kesiman et al., Benchmarking of document image analysis tasks for palm leaf manuscripts from southeast Asia, J. Imaging. 4(2) 2018.
[16] N. S. Panyam, V. L. Vijaya, R. K. Krishnan, and K. R. Koteswara, Modeling of palm leaf character recognition system using transform-based techniques, Pattern Recognit. Lett. 84 (2016) 29–34.
[17] D. Valy, M. Verleysen, and K. Sok, Line segmentation for grayscale text images of Khmer palm leaf manuscripts, in Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017, 2018 (2018) 1–6.
[18] M. W. A. Kesiman, S. Prum, J. C. Burie, and J. M. Ogier, An initial study on the construction of ground truth binarized images of ancient palm leaf manuscripts, Proc. Int. Conf. Doc. Anal. Recognition, ICDAR, 2015 (2015) 656–660.
[19] R. Chamchong and C. C. Fung, Optimal selection of binarization techniques for the processing of ancient palm leaf manuscripts, Conf. Proc. - IEEE Int. Conf. Syst. Man Cybern. (2010) 3796–3800.
[20] J. Ramya and B. Parvathavarthini, Feedforward back propagation neural network based character recognition system for Tamil palm leaf manuscripts, J. Comput. Sci. 10(4) (2014) 660–670.
[21] B. Zhang and J. P. Allebach, Adaptive bilateral filter for sharpness enhancement and noise removal, IEEE Trans. Image Process. 17(5) (2008) 664–678.
[22] R. Vanam and Y. Ye, Adaptive bilateral filter for video and image upsampling, Proc. of SPIE, 8499 (2012) 849906.1–849906.8
[23] M.M.Puranik and S.V.Halse, A Review Paper: Study of Various Types of Noises in Digital Images, IJETT, 57(1) (2018) 40–43.
[24] C. Khare and K. Kumar Nagwanshi, Image Restoration Technique with Non-Linear Filters, May to June Issue (2011) 1–5.