Abstract
In the recent years, there has been an increased trend to digitize the historical manuscripts. This, in addition to preservation of these valuable collections, also allows public access to the digitized versions thus providing opportunities for researchers in pattern classification to develop computerized techniques for various applications. A common pre-processing step in such applications is the restoration of missing or broken strokes and makes the subject of our current study. More specifically, we work on isolated Greek characters extracted from handwriting on papyrus and employ a denoising auto-encoder to reconstruct the missing parts of characters. Performance evaluation using multiple evaluation metrics reports promising results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Arun, E., Vinith, J., Pattar, C., George, K.: Improving Kannada OCR using a stroke-based approach. In: TENCON 2019–2019 IEEE Region 10 Conference (TENCON), pp. 1611–1615 (2019). https://doi.org/10.1109/TENCON.2019.8929606
Arvind, K., Kumar, J., Ramakrishnan, A.: Line removal and restoration of handwritten strokes. In: International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007), vol. 3, pp. 208–214. IEEE (2007)
Assael, Y.: Restoring and attributing ancient texts using deep neural networks. Nature 603(7900), 280–283 (2022)
Baird, H.S., Govindaraju, V., Lopresti, D.P.: Document analysis systems for digital libraries: challenges and opportunities. In: Marinai, S., Dengel, A.R. (eds.) DAS 2004. LNCS, vol. 3163, pp. 1–16. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-28640-0_1
Castellanos, F.J., Gallego, A.J., Calvo-Zaragoza, J.: Unsupervised neural domain adaptation for document image binarization. Pattern Recognit. 119, 108099 (2021)
Hanif, M., et al.: Blind bleed-through removal in color ancient manuscripts. Multimed. Tools Appl. 82, 1–15 (2022)
Ho, L.T., Tran, S.T., Dinh, D.: Nom document background removal using generative adversarial network. In: 2021 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), pp. 100–104. IEEE (2021)
Huang, Z., Heng, W., Tao, Y., Zhou, S.: Stroke-based character reconstruction. arXiv preprint arXiv:1806.08990 (2018)
Liu, R., et al.: SCCGAN: style and characters inpainting based on CGAN. Mobile Netw. Appl. 26, 3–12 (2021)
Melnik, G., Yekutieli, Y., Sharf, A.: Deep segmentation of corrupted glyphs. ACM J. Comput. Cult. Heritage (JOCCH) 15(1), 1–24 (2022)
Mohammed, H., Marthot-Santaniello, I., Märgner, V.: GRK-Papyri: a dataset of Greek handwriting on papyri for the task of writer identification. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 726–731. IEEE (2019)
Mosa, Q.O., Nasrudin, M.F.: Broken character image restoration using genetic snake algorithm: deep concavity problem. J. Comput. Sci. 12(2), 81–87 (2016)
Nguyen, K.C., Nguyen, C.T., Hotta, S., Nakagawa, M.: A character attention generative adversarial network for degraded historical document restoration. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 420–425. IEEE (2019)
Raha, P., Chanda, B.: Restoration of historical document images using convolutional neural networks. In: 2019 IEEE Region 10 Symposium (TENSYMP), pp. 56–61. IEEE (2019)
Rani, N.S., Nair, B.B., Chandrajith, M., Kumar, G.H., Fortuny, J.: Restoration of deteriorated text sections in ancient document images using a tri-level semi-adaptive thresholding technique. Automatika 63(2), 378–398 (2022)
Sober, B., Levin, D.: Computer aided restoration of handwritten character strokes. Comput. Aided Des. 89, 12–24 (2017)
Sulaiman, A., Omar, K., Nasrudin, M.F.: Degraded historical document binarization: a review on issues, challenges, techniques, and future directions. J. Imaging 5(4), 48 (2019)
Wadhwani, M., Kundu, D., Chakraborty, D., Chanda, B.: Text extraction and restoration of old handwritten documents. In: Mukhopadhyay, J., Sreedevi, I., Chanda, B., Chaudhury, S., Namboodiri, V.P. (eds.) Digital Techniques for Heritage Presentation and Preservation, pp. 109–132. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-57907-4_6
Xiong, W., Jia, X., Yang, D., Ai, M., Li, L., Wang, S.: DP-LinkNet: a convolutional network for historical document image binarization. KSII Trans. Internet Inf. Syst. (TIIS) 15(5), 1778–1797 (2021)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Amin, J., Siddiqi, I., Moetesum, M. (2023). Reconstruction of Broken Writing Strokes in Greek Papyri. In: Coustaty, M., Fornés, A. (eds) Document Analysis and Recognition – ICDAR 2023 Workshops. ICDAR 2023. Lecture Notes in Computer Science, vol 14193. Springer, Cham. https://doi.org/10.1007/978-3-031-41498-5_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-41498-5_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-41497-8
Online ISBN: 978-3-031-41498-5
eBook Packages: Computer ScienceComputer Science (R0)
