2692-4048ISSN (Online)
2770-0070ISSN (Print)
Volume 19 , Issue 2 , PP: 109-117, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Raed Majeed 1 * , Hiyam Hatem 2 , Wael Abd-Alaziz 3
Doi: https://doi.org/10.54216/FPA.190209
Cuneiform script, among the earliest writing systems, poses a distinct challenge for classification because of its complex symbols and varied linguistic contexts. This study investigates the use of Convolutional Neural Network (CNN) architectures for the classification of cuneiform symbols. The preprocessing includes resizing the cuneiform images to a uniform dimension and categorizing them into training, validation, and testing sets. A modified CNN model has been introduced. The CNN model demonstrates a lower parameter count in comparison to other deep learning models, which frequently necessitate significant storage capacity. The results from the CLI dataset indicate that the proposed CNN model reached an impressive accuracy of 99.55%, This study enhances computational approaches for the analysis of ancient scripts and underscores the significance of utilizing deep learning techniques within the fields of historical linguistics and digital humanities.
Cuneiform classification , Convolutional Neural Networks (CNNs) , Symbol recognition , Ancient script analysis , Deep learning linguistics
[1] S. Mahmood et al., "Classifying cuneiform symbols using machine learning algorithms with unigram features on a balanced dataset," J. Intell. Syst., vol. 32, no. 1, p. 20230087, 2023.
[2] L. Boadt, R. J. Clifford, and D. J. Harrington, Reading the Old Testament: An Introduction. New York, NY, USA: Paulist Press, 2012.
[3] H. Mara, S. Krömker, S. Jakob, and B. Breuckmann, "GigaMesh and Gilgamesh: 3D multiscale integral invariant cuneiform character extraction," in Proc. 11th Int. Conf. Virtual Reality, Archaeol. Cultural Heritage, 2010, pp. 131–138.
[4] N. A. Rasheed and W. L. Nados, "Recognition of cuneiform symbols using neural network," J. Theor. Appl. Inf. Technol., vol. 96, no. 17, 2018.
[5] D. Charpin, Writing, Law, and Kingship in Old Babylonian Mesopotamia. Chicago, IL, USA: Univ. of Chicago Press, 2010.
[6] E. Uchida and R. Watanabe, "Blackening of the surfaces of Mesopotamian clay tablets due to manganese precipitation," Archaeol. Discovery, vol. 2, no. 4, pp. 107–115, 2014.
[7] C. Woods, "Visible language," Spring, vol. 45, no. 1–2, p. 155, 2011, doi: 10.1037/020683.
[8] T. Jauhiainen, H. Jauhiainen, T. Alstola, and K. Lindén, "Language and dialect identification of cuneiform texts," arXiv preprint arXiv:1903.01891, 2019.
[9] M. Zampieri et al., "A report on the third VarDial evaluation campaign," in Workshop on NLP for Similar Languages, Varieties and Dialects, The Association for Computational Linguistics, 2019, pp. 1–16.
[10] B. Al-Khateeb, "Classifying cuneiform symbols using machine learning algorithms with unigram features on a balanced dataset," J. Intell. Syst., vol. 32, no. 1, p. 20230087, 2023, doi: 10.1515/jisys-2023-0087.
[11] E. C. Williams et al., "DeepScribe: Localization and classification of Elamite cuneiform signs via deep learning," arXiv preprint arXiv:2306.01268, 2023.
[12] F. Hagelskjær, "Deep learning classification of large-scale point clouds: A case study on cuneiform tablets," in Proc. IEEE Int. Conf. Image Process. (ICIP), 2022, pp. 826–830.
[13] D. Kapon, M. Fire, and S. Gordin, "Shaping history: Advanced machine learning techniques for the analysis and dating of cuneiform tablets over three millennia," arXiv preprint arXiv:2406.04039, 2024.
[14] E. A. Saeed, A. D. Jasim, and M. A. A. Malik, "Hebrew letters detection and cuneiform tablets classification by using the YOLOv8 computer vision model," arXiv preprint arXiv:2407.06133, 2024.
[15] T. Dencker, P. Klinkisch, S. M. Maul, and B. Ommer, "Deep learning of cuneiform sign detection with weak supervision using transliteration alignment," PLoS One, vol. 15, no. 12, p. e0243039, 2020.
[16] Bernier-Colborne et al., "Automatic classification of cuneiform tablets using convolutional neural networks," in Conf. Proc., 2021.
[17] M. Doost Mohammadi and M. Nassajian, "Hybrid CNN-RNN deep learning models for cuneiform symbol recognition," J. Historical Comput., 2023.
[18] S. Sharma et al., "A review of image preprocessing techniques for deep learning applications," in Proc. Int. Conf. Mach. Learn. Data Eng. (ICMLDE), 2020.
[19] A. Zhang et al., "Image enhancement and feature extraction for convolutional neural networks in biomedical image analysis," J. Vis. Commun. Image Represent., vol. 62, p. 101084, 2019, doi: 10.1016/j.jvcir.2019.101084.
[20] M. Ali, S. Shiaeles, G. Bendiab, and B. Ghita, "MALGRA: Machine learning and N-gram malware feature extraction and detection system," Electronics, vol. 9, no. 11, p. 1777, 2020.
[21] M. Zampieri et al., "A report on the third VarDial evaluation campaign," in Workshop on NLP for Similar Languages, Varieties and Dialects, The Association for Computational Linguistics, 2019, pp. 1–16.
