Published July 30, 2025 | Version CC-BY-NC-ND 4.0
Journal article Open

Effectiveness of Generative AI in Processing Antique Coin Imagery: A Quantitative Study

Creators

  • 1. XUVI Technology Labs, Chennai (Tamil Nadu), India.

Description

Abstract: This study quantitatively evaluates the effectiveness of five prominent generative AI platforms—Google Gemini (2.0 Flash), OpenAI ChatGPT (GPT-4.1), Microsoft Copilot, Ola Krutrim, and X Grok (Grok 3)—in processing and classifying antique coin imagery. Moving beyond qualitative assessments, this research provides a rigorous quantitative analysis of their capabilities in accurately extracting key identifying information from images of historical artefacts. Utilising a carefully curated dataset of ten distinct antique coins spanning diverse historical periods and geographical origins, we assess each platform's ability to correctly identify the coin (denomination or type), its country of origin, and the constituent material based solely on images of their obverse and reverse. The methodology employed, emphasising controlled conditions and objective accuracy metrics, along with the results obtained, offers a valuable comparative benchmark of current generative AI capabilities in this specialised numismatic domain. This research contributes to the broader understanding of AI's potential in augmenting and potentially transforming workflows within cultural heritage and historical studies.

Files

C368015030725.pdf

Files (524.9 kB)

Name Size Download all
md5:4e5de6049791510f0220cedf640f491a
524.9 kB Preview Download

Additional details

Identifiers

DOI
10.35940/ijsce.C3680.15030725
EISSN
2231-2307

Dates

Accepted
2025-07-15
Manuscript Received on 26 May 2025 | First Revised Manuscript Received on 08 June 2025 | Second Revised Manuscript Received on 17 June 2025 | Manuscript Accepted on 15 July 2025 | Manuscript published on 30 July 2025.

References

  • Lee, K. T., Chee, P. S., Lim, E. H., & Lim, C. C. (2022). Artificial intelligence (AI)-driven smart glove for object recognition application. Materials Today: Proceedings, 64, 1563-1568. DOI: https://doi.org/10.1007/s13735-017-0141-z
  • Guo, Y., Liu, Y., Georgiou, T., & Lew, M. S. (2018). A review of semantic segmentation using deep neural networks. International journal of multimedia information retrieval, 7, 87-93. DOI: https://doi.org/10.1016/j.matpr.2021.12.473
  • Wang, W., Bao, J., Zhou, W., Chen, D., Chen, D., Yuan, L., & Li, H. (2022). Semantic image synthesis via diffusion models. arXiv preprint arXiv:2207.00050. DOI: https://doi.org/10.48550/arXiv.2207.00050
  • Gîrbacia, F. (2024). An Analysis of Research Trends for Using Artificial Intelligence in Cultural Heritage. Electronics, 13(18), 3738. DOI: https://doi.org/10.3390/electronics13183738
  • Kemmers, F., & Myrberg, N. (2011). Rethinking numismatics. The archaeology of coins. Archaeological Dialogues, 18(1), 87-108. DOI: https://doi.org/10.1017/S1380203811000146
  • Cirillo, S., Solimando, G., & Virgili, L. (2024). A deep learning approach to classify the country and value of modern coins. Neural Computing and Applications, 36(20), 11759-11775. DOI: https://doi.org/10.1007/s00521-023-09355-6
  • Singh, G., Srivastava, V., Kumar, S., Bhatnagar, V., & Dhondiyal, S. A. (2024, August). Exploring the Creative Capacities of Generative AI: A Comparative Study. In 2024 5th International Conference on Electronics and Sustainable Communication Systems (ICESC) (pp. 1809-1813). IEEE. DOI: https://doi.org/10.1109/ICESC60852.2024.10689966