R.A. Kochkarov1, A.D. Borodina2
1,2 Financial University under the Government of the Russian Federation (Moscow, Russia)
1 rkochkarov@fa.ru, 2 aborodinasty@gmail.com

The recognition of Orkhon-Yenisei runic inscriptions is an important yet highly challenging task due to the poor quality of source materials, the visual heterogeneity of runes, and the limited availability of annotated data. The deciphering process performed by archaeologists is prone to errors and subjectivity. The most difficult stage involves the segmentation and interpretation of symbols under conditions of artifact degradation and complex visual contexts.

Objective. To develop and train a computer vision model for the automatic detection and classification of characters from the Kül Tegin runic alphabet on monument images, including both black-and-white copies and real color photographs.

A prototype system was developed, combining two models: YOLOv11 for symbol detection and a convolutional neural network for classification. The detection model achieved mAP@0.5 = 0.825, recall = 0.801, and precision = 0.75. The classifier achieved 90.23% accuracy and an F1-score of 0.884. Feature visualization using t-SNE demonstrated clear clustering for most classes. Limitations were identified, including overfitting and class imbalance-especially when working with rare or unknown runes. The model can be adapted to other runic systems.

The results can be applied in digital epigraphy and historical-linguistic research to enhance the speed and accuracy of ancient text analysis. The work lays the foundation for the development of more scalable and robust recognition systems for inscriptions under low-quality data conditions.

Kochkarov R.A., Borodina A. D. Detection of Orkhon-Yenisei runic inscriptions. Nonlinear World. 2025. V. 23. № 3. P. 96–106. DOI: https:// doi.org/10.18127/ j20700970-202503-12 (In Russian)

1. Kormushin I.V. Drevnie tyurkskie yazyki. M.: Vostochnaya literatura. 2006. 30 s. (In Russian)
2. Kormushin I.V. Tyurkskie enisejskie epitafii. M.: Vostochnaya literatura. 2008. 5 s. (In Russian)
3. Kyzlasov I.L. Runicheskie pis'mennosti evrazijskih stepej. M.: Nauka. 1994. 318 s. (In Russian)
4. Deshifrovka orhonskih i enisejskih nadpisej. Zapiski Vostochnogo otdeleniya IV RAN. M. 1995. Vyp. 25. S. 289–318 (In Russian).
5. Kruglov E.V. Formirovanie istochnikovoj bazy pamyatnikov Sokolovskoj Balki. Nizhnevolzhskij arheologicheskij vestnik. 2002. № 2. S. 69–72 (In Russian).
6. Kyzlasov I.L. Runic Scripts of the Eurasian Steppes. M.: Russian Academy of Sciences. 1994. 180 p.
7. Proposal for encoding the Khazarian Rovas script in the SMP of the UCS. ISO/IEC JTC1/SC2/WG2 N3999. 2011-01-21.
8. Vasil'ev D.D. Graficheskij fond pamyatnikov tyurkskoj runicheskoj pis'mennosti aziatskogo areala. M.: Nauka. 1983. 192 s. (In Russian).
9. Bajchorov S.Ya. Drevnetyurkskie runicheskie pamyatniki Evropy. Stavropol': Stavropol'skoe knizhnoe izd-vo. 1989. 150 s. (In Russian).
10. Tishin V.V. Novye soobrazheniya o vozmozhnosti rasshifrovki nadpisej na runicheskih dirhemah na osnove materiala tyurkskih yazykov. Vestnik BNC SO RAN. 2018. № 30. S. 46–56 (In Russian).
11. Kononov A.N. Grammatika yazyka tyurkskih runicheskih pamyatnikov VII–IX vv. L.: Nauka. 1980. 260 s. (In Russian).
12. Lebedev Yu.S., Popov P.V. Pogrebenie VIII–IX vv. iz Astrahanskoj oblasti i gorshok s runicheskoj nadpis'yu. Rossijskaya arheologiya. 2023. № 1. S. 178–186 (In Russian).
13. Problemy arheologii Kavkaza. Vyp. 1. M.: TAUS. 2012. 248 s. (In Russian).
14. Voprosy tyurkologii. M.: Institut tyurkologii. 2010. № 1. 188 s. (In Russian).
15. Kyzlasov I.L. K poznaniyu nerasshifrovannogo pis'ma. Hazarskij al'manah. M. 2020. № 28–29 (In Russian).
16. Hazarskij al'manah. T. 15. M.: Institut slavyanovedeniya RAN. 2017. 228 s. (In Russian).
17. Povolzhskaya arheologiya. 2014. № 3 (9) (In Russian).
18. Tyurkologicheskie issledovaniya. 2018. T. 1. № 2 (In Russian).
19. Arheologicheskoe nasledie. Pod red. A.N. Golovtina. Lipeck: Argamach. 2018. PI № TU48-00362 (In Russian).
20. Narody i religii Evrazii. Barnaul: Izd-vo Altajskogo gos. un-ta, 2019. № 4 (21) (In Russian).
21. Nizhnevolzhskij arheologicheskij vestnik. Volgograd: Volgogradskij gos. un-t. 2018. T. 17. № 1 (In Russian).
22. Kochkarov U.Yu., Belyaeva V.N., Kochkarov R.A., Kochkarov A.A. Podgotovka nabora vizual'nyh dannyh dlya mashinnogo raspoznavaniya runicheskoj pis'mennosti. Problematika i metodologiya sovremennyh tyurkologicheskih issledovanij: Kollektivnaya monografiya. otv. red. E.A. Oganova. M.: OOO «Izdatel'stvo MBA». 2025. S. 162–73 (In Russian).
23. Ultralytics. YOLOv11 Documentation [Electronic resource]. URL: https://docs.ultralytics.com/ru/models/yolo11/. Date of access: 10.04.2025.