Abstract
Machine learning techniques are presented for automatic recognition of the historical letters (XI–XVIII centuries) carved on the stoned walls of St. Sophia cathedral in Kyiv (Ukraine). A new image dataset of these carved Glagolitic and Cyrillic letters (CGCL) was assembled and pre-processed for recognition and prediction by machine learning methods. The dataset consists of more than 4000 images for 34 types of letters. The explanatory data analysis of CGCL and notMNIST datasets shown that the carved letters can hardly be differentiated by dimensionality reduction methods, for example, by t-distributed stochastic neighbor embedding (tSNE) due to the worse letter representation by stone carving in comparison to hand writing. The multinomial logistic regression (MLR) and a 2D convolutional neural network (CNN) models were applied. The MLR model demonstrated the area under curve (AUC) values for receiver operating characteristic (ROC) are not lower than 0.92 and 0.60 for notMNIST and CGCL, respectively. The CNN model gave AUC values close to 0.99 for both notMNIST and CGCL (despite the much smaller size and quality of CGCL in comparison to notMNIST) under condition of the high lossy data augmentation. CGCL dataset was published to be available for the data science community as an open source resource.
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
Ancelet, J.: The History of Graffiti. University of Central London, London (2006)
Burt, D.: The Online Corpus of the Inscriptions from Ancient North Arabia (OCIANA). http://krc2.orient.ox.ac.uk/ociana. Accessed 30 Aug 2018
Nikitenko, N., Kornienko, V.: Drevneishie Graffiti Sofiiskogosobora v Kieve i Vremya Ego Sozdaniya (Old Graffiti in the St. Sofia Cathedral in Kiev and Time of Its Creation). Mykhailo Hrushevsky Institute of Ukrainian Archeography and Source Studies, Kiev (2012). (in Russian)
Vysotskii, S.A.: Drevnerusskie Nadpisi Sofii Kievskoi XI–XIV vv. (Old Russian Inscriptions in the St. Sofia Cathedral in Kiev, 11th–14th Centuries). Naukova Dumka, Kiev (1966). (in Russian)
Nazarenko, T.: East Slavic visual writing: the inception of tradition. Can. Slavon. Pap. 43(2–3), 209–225 (2001)
Drobysheva, M.: The difficulties of reading and interpretation of Old Rus Graffiti (the inscription Vys. 1 as example). Istoriya 6(6(39)), 10–20 (2015)
Pritsak, O.: An eleventh-century Turkic Bilingual (Turko-Slavic) Graffito from the St. Sophia Cathedral in Kiev. Harv. Ukr. Stud. 6(2), 152–166 (1982)
LeCun, Y., Cortes, C., Burges, C.J.: MNIST Handwritten Digit Database. AT&T Labs. http://yann.lecun.com/exdb/mnist. Accessed 30 Aug 2018
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Hafemann, L.G., Sabourin, R., Oliveira, L.S.: Offline handwritten signature verification—Literature review. In: 2017 Seventh International Conference on Image Processing Theory, Tools and Applications, pp. 1–8. IEEE (2017)
Winter, J.: Preliminary investigations on Chinese ink in far eastern paintings. In: Archaeological Chemistry, pp. 207–225 (1974)
Gang, P., et al.: User-driven intelligent interface on the basis of multimodal augmented reality and brain-computer interaction for people with functional disabilities. In: Proceedings of Future of Information and Communication Conference, 5–6 April 2018, pp. 322–331. IEEE, Singapore (2018)
Gordienko, Yu., et al.: Augmented coaching ecosystem for non-obtrusive adaptive personalized elderly care on the basis of Cloud-Fog-Dew computing paradigm. In: Proceedings of IEEE 40th International Convention on Information and Communication Technology, Electronics and Microelectronics, pp. 387–392. IEEE, Opatija, Croatia (2017)
Nikitenko, N., Kornienko, V.: Drevneishie Graffiti Sofiiskogosobora v Kieve i Ego Datirovka (The Ancient Graffiti of St. Sophia Cathedral in Kiev and Its Dating). Byzantinoslavica 68(1), 205–240 (2010). (in Russian)
Kornienko, V.V.: Korpus Hrafiti Sofii Kyivskoi, XI - pochatok XVIII_st, chastyny I–III (The Collection of Graffiti of St. Sophia of Kyiv, 11th–17th centuries), Parts I–III. Mykhailo Hrushevsky Institute of Ukrainian Archeography and Source Studies, Kiev (2010–2011). (in Ukrainian)
Sinkevic, N., Kornienko, V.: Nowe Zrodla do Historii Kosciola unickiego w Kijowie: Graffiti w Absydzie Glownego Oltarza Katedry Sw. Zofii. Studia Zrodloznawcze 50, 75–80 (2012). http://rcin.org.pl/Content/31104/WA303_44631_B88-SZ-R-50-2012_Sinkevic.pdf
Glyphs of Graffiti in St. Sophia Cathedral of Kyiv. https://www.kaggle.com/yoctoman/graffiti-st-sophia-cathedral-kyiv. Accessed 30 Aug 2018
Bulatov, Y.: notMNIST dataset. Google (Books/OCR), Technical report. http://yaroslavvb.blogspot.it/2011/09/notmnist-dataset.html. Accessed 30 Aug 2018
Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(1), 2579–2605 (2008)
Schmidt, P.: Cervix EDA and model selection. https://www.kaggle.com/philschmidt. Accessed 30 Aug 2018
Gordienko, N., Lodygensky, O., Fedak, G., Gordienko, Yu.: Synergy of volunteer measurements and volunteer computing for effective data collecting, processing, simulating and analyzing on a worldwide scale. In: Proceedings of 38th International Convention on Information and Communication Technology, Electronics and Microelectronics, pp. 193–198. IEEE, Opatija (2015)
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: Advances in Neural Information Processing Systems, pp. 3856–3866 (2017)
Gordienko, N., Kochura, Y., Taran, V., Gang, P., Gordienko, Y., Stirenko, S.: Capsule deep neural network for recognition of historical Graffiti handwriting. In: IEEE Ukraine Student, Young Professional and Women in Engineering Congress, Kyiv, Ukraine, 2–6 October 2018. IEEE (2018, Submitted)
Acknowledgements
The work was partially supported by Huizhou Science and Technology Bureau and Huizhou University (Huizhou, P.R. China) in the framework of Platform Construction for China-Ukraine Hi-Tech Park Project. The glyphs of letters from the graffiti [3] were prepared by students and teachers of National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” and can be used as an open science dataset under CC BY-NC-SA 4.0 license (https://www.kaggle.com/yoctoman/graffiti-st-sophia-cathedral-kyiv).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Gordienko, N. et al. (2018). Open Source Dataset and Machine Learning Techniques for Automatic Recognition of Historical Graffiti. In: Cheng, L., Leung, A., Ozawa, S. (eds) Neural Information Processing. ICONIP 2018. Lecture Notes in Computer Science(), vol 11305. Springer, Cham. https://doi.org/10.1007/978-3-030-04221-9_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-04221-9_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04220-2
Online ISBN: 978-3-030-04221-9
eBook Packages: Computer ScienceComputer Science (R0)