Abstract
Greek literary papyri, which are unique witnesses of antique literature, do not usually bear a date. They are thus currently dated based on palaeographical methods, with broad approximations which often span more than a century. We created a dataset of 242 images of papyri written in “bookhand” scripts whose date can be securely assigned, and we used it to train machine and deep learning algorithms for the task of dating, showing its challenging nature. To address the data scarcity problem, we extended our dataset by segmenting each image to the respective text lines. By using the line-based version of our dataset, we trained a Convolutional Neural Network, equipped with a fragmentation-based augmentation strategy, and we achieved a mean absolute error of 54 years. The results improve further when the task is cast as a multiclass classification problem, predicting the century. Using our network, we computed and provided precise date estimations for papyri whose date is disputed or vaguely defined and we undertake an explainability-based analysis to facilitate future attribution.
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
Notes
- 1.
There is a very small number of exceptions which reflect the complexity of our documentation: one text is in Coptic, a few don’t come from Egypt but the Near-East and another few are written on parchment, not papyrus. In this study, we collectively call them ‘papyri’.
- 2.
- 3.
- 4.
More reliable compilations are promised by current projects, but are still work-in-progress for the time being.
- 5.
Datings usually come from one expert, the editor of the text. Sometimes another expert makes a case that the dating should be modified and the correction may be accepted or provided as alternative dating.
- 6.
https://www.trismegistos.org/text/59375 (accessed: May 25, 2023).
- 7.
The Photographic Archive of Papyri in the Cairo Museum (accessed: May 25, 2023).
- 8.
https://papyri.info/ddbdp/p.flor;2;120 (accessed: May 25, 2023).
References
Brink, A.A., Smit, J., Bulacu, M.L., Schomaker, L.R.B.: Writer identification using directional ink-trace width measurements. Pattern Recogn. 45(1), 162–171 (2012). https://doi.org/10.1016/j.patcog.2011.07.005
Bulacu, M., Schomaker, L., Vuurpijl, L.: Writer identification using edge-based directional features. In: Proceedings of the Seventh International Conference on Document Analysis and Recognition 2003, pp. 937–941 (2003). https://doi.org/10.1109/ICDAR.2003.1227797
Choat, M.: Dating papyri: familiarity, instinct and guesswork. J. Study New Testament 42(1), 58–83 (2019). https://doi.org/10.1177/0142064X19855580
Cilia, N.D., De Stefano, C., Fontanella, F., Marthot-Santaniello, I., Scotto di Freca, A.: PapyRow: a dataset of row images from ancient Greek papyri for writers identification. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12667, pp. 223–234. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-68787-8_16
Fernández-Delgado, M., Sirsat, M.S., Cernadas, E., Alawadi, S., Barro, S., Febrero-Bande, M.: An extensive experimental survey of regression methods. Neural Netw. 111, 11–34 (2019)
Fiel, S., Sablatnig, R.: Writer identification and retrieval using a convolutional neural network. In: Azzopardi, G., Petkov, N. (eds.) CAIP 2015. LNCS, vol. 9257, pp. 26–37. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-23117-4_3
Hamid, A., Bibi, M., Moetesum, M., Siddiqi, I.: Deep learning based approach for historical manuscript dating. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 967–972. IEEE (2019)
He, S., Samara, P., Burgers, J., Schomaker, L.: Discovering visual element evolutions for historical document dating. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 7–12. IEEE (2016)
He, S., Sammara, P., Burgers, J., Schomaker, L.: Towards style-based dating of historical documents. In: 2014 14th International Conference on Frontiers in Handwriting Recognition, pp. 265–270. IEEE (2014)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kumar, A., Baldridge, J., Lease, M., Ghosh, J.: Dating texts without explicit temporal cues. arXiv preprint arXiv:1211.2290 (2012)
Mazza, R.: Dating early Christian papyri: old and new methods -introduction. J. Study New Testament 42(1), 46–57 (2019). https://doi.org/10.1177/0142064X19855579
Nasir, S., Siddiqi, I.: Learning features for writer identification from handwriting on papyri. In: Djeddi, C., Kessentini, Y., Siddiqi, I., Jmaiel, M. (eds.) MedPRAI 2020. CCIS, vol. 1322, pp. 229–241. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-71804-6_17
Nguyen, H.T., Nguyen, C.T., Ino, T., Indurkhya, B., Nakagawa, M.: Text-independent writer identification using convolutional neural network. Pattern Recogn. Lett. 121, 104–112 (2019)
Nongbri, B.: The limits of palaeographic dating of literary papyri: Some observations on the date and provenance of P.Bodmer II (P66). Mus. Helveticum 71(1), 1–35 (2014)
Nongbri, B.: Palaeographic analysis of codices from the early Christian period: a point of method. J. Study New Testament 42(1), 84–97 (2019). https://doi.org/10.1177/0142064X19855582
Omayio, E.O., Indu, S., Panda, J.: Historical manuscript dating: traditional and current trends. Multimed. Tools Appl. 81(22), 31573–31602 (2022)
Paparrigopoulou, A., Kougia, V., Konstantinidou, M., Pavlopoulos, J.: Greek literary papyri dating benchmark (2023). https://doi.org/10.21203/rs.3.rs-2272076/v2
Papavassiliou, V., Stafylakis, T., Katsouros, V., Carayannis, G.: Handwritten document image segmentation into text lines and words. Pattern Recogn. 43(1), 369–377 (2010)
Rahiche, A., Hedjam, R., Al-Maadeed, S., Cheriet, M.: Historical documents dating using multispectral imaging and ordinal classification. J. Cult. Herit. 45, 71–80 (2020)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
Stokes, P.A.: Computer-aided palaeography, present and future. In: Rehbein, M., Schaßan, T., Sahle, P. (eds.) Kodikologie und Paläographie im digitalen Zeitalter - Codicology and Palaeography in the Digital Age, vol. 2, pp. 309–338. BoD, Norderstedt (2009). https://kups.ub.uni-koeln.de/2978/
Stokes, P.A.: Scribal attribution across multiple scripts: a digitally aided approach. Speculum 92(S1), S65–S85 (2017). https://doi.org/10.1086/693968
Turner, E.G.: Greek Manuscripts of the Ancient World. (P. J. Parsons, Ed.; Revised and Enlarged ed.). Institute of Classical Studies, London (1987)
Wahlberg, F., Wilkinson, T., Brun, A.: Historical manuscript production date estimation using deep convolutional neural networks. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 205–210. IEEE (2016)
Author information
Authors and Affiliations
Corresponding author
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
Pavlopoulos, J. et al. (2023). Explaining the Chronological Attribution of Greek Papyri Images. In: Bifet, A., Lorena, A.C., Ribeiro, R.P., Gama, J., Abreu, P.H. (eds) Discovery Science. DS 2023. Lecture Notes in Computer Science(), vol 14276. Springer, Cham. https://doi.org/10.1007/978-3-031-45275-8_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-45275-8_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45274-1
Online ISBN: 978-3-031-45275-8
eBook Packages: Computer ScienceComputer Science (R0)