Inscription and Ancient Script Recognition Using OCR
DOI:
https://doi.org/10.32628/CSEIT26121310Keywords:
Optical Character Recognition (OCR), Script Extraction, Information Retrieval, Convolutional Neural Networks (CNNs), OpenCV (Computer Vision) python library, Image ProcessingAbstract
Ancient scripts & inscriptions often offer vital and important understandings to the preceding societies, and separate them effectively that is essential for conservation of cultural remains, decrypting scripts, and protecting the cultural heritage. Usual research generally pay attention on identification of ancient script data in a secluded way, like exemption of old age inscriptions like hand-written scripts. Nonetheless, ancient inscriptions and scripts derive in several arrangements across different mediums, which then creates various challenges for Optical Character Recognition (OCR). Things like erosion, disruption, and inscriptional fragmentation may mis- perceive the process of recognition of ancient inscriptions engravings. To handle this issue, we suggest an ancient inscription recognition framework that can handle different inputs such as stone inscriptions and handwritten scripts. Offering a proportional analysis of various OCR tools & techniques for evaluate how much these are effective and operative in terms of accuracy, recognition of characters, and its processing speed. It plays an important role in inscriptional studies, that consists the inscriptional studies that are crafted on various materials like stones, metal and pottery. This is mostly essential for preserving and digitalizing ancient scripts.
Downloads
References
F. Ahmed, A. Das, and J. Choi, “MobileNet- Transformer for Edge-Based Ancient Text Recognition,” IEEE Internet of Things Journal, vol. 12, no. 3, pp. 2517–2528, 2025.
E. Cho and K. Park, “Low-Light Image Enhancement for OCR in Archaeological Inscriptions,” IEEE Sensors Journal, vol. 25, no. 6, pp. 8574–8585, 2025.
A. Singh, R. Mehta, and P. Garg, “Diffusion Models for Restoration of Ancient Scripts,” IEEE Conf. Computer Vision for Cultural Heritage (CVCH), pp. 201–210, 2025.
O. Hassan and S. El-Masry, “DeepOCRNet: Multi- Layer Attention Model for Hieroglyphic Text Decoding,” Journal of Computational Vision and AI Heritage, vol. 6, no. 1, pp. 1-10, 2025.
N. Wang, L. Zhou, and M. Li, “Multi-Modal Ancient Script Recognition via Deep Learning with Data Homogenization,” npj Heritage Science, vol, no. 3, pp. 1-13, 2025. DOI: https://doi.org/10.1038/s40494-025-02095-x
Y. Liu and H. Zhang, “Hybrid Deep Learning Framework for Epigraphic Text Recognition,” IEEE Access, vol. 13, pp. 11245-11258, 2025.
K. A. Guangul, “Character Recognition of Ancient Ethiopic Ge’ez Script Using Deep Learning,” Springer Journal of Pattern Analysis and Machine Intelligence, vol 12, no. 4, pp. 118-129,2025.
Y. Tang, S. Ho, and F. Ren, “Swin-ViT OCR: Hierarchical Transformer Models for Degraded Heritage Text Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 1, pp. 221–234, 2025.
B. Kang and L. Zhou, “Robust OCR for Archaeological Artifacts Using Dual-Branch CNN–Transformer Fusion,” Journal of Cultural Heritage Informatics, vol. 9, no. 2, pp. 44–59, 2025.
T. Arai and M. Suzuki, “Self-Supervised Vision Models for Low-Resource Epigraphic Script Recognition,” Pattern Recognition and Artificial Intelligence, vol. 58, no. 4, pp. 1–15, 2025.
P. Mukherjee, R. Sen, and A. Kumar, “CTC-Free Transformer Decoder for Ancient Document Transcription,” Neural Information Processing Systems (NeurIPS) Workshops, pp. 1–12, 2025.
L. D. Silva and R. Thomas, “GAN-Based Texture Restoration for Stone Tablet Inscription OCR,” Computer Vision and Image Understanding, vol. 241,pp. 103082, 2025.
J. Jain and J. Ahn, “InscriberNet: CNN and Swin Transformer for Chinese Character Recognition in Stone Inscriptions,” ISPRS Archives, vol. XL VIII-M- 9-2025, pp.45-52,2025. DOI: https://doi.org/10.5194/isprs-archives-XLVIII-M-9-2025-629-2025
M. Gupta and F. Rahman, “Explainable Attention Maps for OCR-Based Heritage Digitization,” ACM Journal on Computing and Cultural Heritage (JOCCH), vol. 18, no. 1, pp. 1–12, 2025.
D. Zhao, L. Xu, and W. Tang, “Transformer-Based Vision Models for Multilingual OCR,” ACM Trans. on Asian and Low-Resource Language Information Processing, vol. 24, no. 2, pp. 1–14, 2025. DOI: https://doi.org/10.1145/3711827
H. Patel and M. Banerjee, “Integrating CNN– Transformer Networks for Degraded Text Recognition,” Pattern Recognition and Image Analysis, Springer, vol. 34, no. 1, pp. 59–71, 2024.
L. Santos and T. Kim, “Self-Supervised Pretraining for Handwritten Heritage Document OCR,” Information Sciences, vol. 658, pp. 119418, 2024.
R. Bansal and S. Verma, “Cross-Script OCR Using Transformer Encoder–Decoder Networks,” Neural Computing and Applications, Springer, vol. 36, pp. 21259–21273, 2024.
S. Yadav, P. N. Jaiswal, and T. Kumar, “Benchmarking OCR Models for Multilingual Ancient Texts,” IEEE Access, vol. 12, pp. 47890– 47905, 2024.
Y. Agrawal, P. Singh, and R. Patel, “OCR Using CNN for Ashokan Brahmi Inscriptions” arXiv preprint arXiv:2501.01981, 2024.
S. Ahmed, “Explainable Machine Learning Models for Cultural Data Analysis,” Organization Technology and Management Journal, vol. 17, no. 2,pp. 65-72, 2024.
R. Kumar and H. Lee, “Transfer Learning in Multilingual OCR Systems,” IEEE Transactions on Artificial Intelligence, vol. 5, no. 1, pp. 13-24, 2024.
M. Chen and Q. Zhao, “Contrastive Learning for Handwritten Historical OCR,” Pattern Recognition, vol. 145, 109935, 2024.
S. Patel, A. Pandey, and R. Joshi, “Federated Learning Frameworks for Cultural Heritage Image Processing,” Sensors, vol. 24, no. 8, pp. 3721–3730, 2024.
FNU Pawan Kumar. Developing SOA architecture web services for high throughput systems. International Journal of Science and Research Archive, 2025, 15(02), 1897–1906. Article DOI: https://doi.org/10.30574/ijsra.2025.15.2.1511. DOI: https://doi.org/10.30574/ijsra.2025.15.2.1511
Mishra, Chandan. (2025). PeopleSoft and cloud integration: Opportunities and challenges in the future of financial management systems. International Journal of Science and Research Archive. 16. 008-016. 10.30574/ijsra.2025.16.2.2271. DOI: https://doi.org/10.30574/ijsra.2025.16.2.2271
R. Rajithkumar, B. Uma, and H. Mohana, “Hybrid CNN–RNN Model for Automated Recognition of Kannada Inscriptions,” ETASR Journal, vol. 12, no. 4,pp. 220–228, 2024.
M. Okamoto and Y. Saito, “Cross-Language Pretraining for Multiscript Historical OCR,” IEEE Transactions on Artificial Intelligence, vol. 6, no. 2, pp. 201–214, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Scientific Research in Computer Science, Engineering and Information Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
