CAA2023 Conference Proceedings
Published May 13, 2024 | Version v4
Conference paper Open

Supporting the analysis of a large coin hoard with AI-based methods

Creators

  • 1. Goethe Universität Frankfurt am Main - Germany
  • 2. Römisch-Germanische Kommission – Germany

Description

In the project "Classifications and Representations for Networks: From types and characteristics to linked open data for Celtic coinages" (ClaReNet) we had access to image data for one of the largest Celtic coin hoards ever found: Le Câtillon II with nearly 70,000 coins. Our aim was not to develop new processes, but rather to demonstrate how existing tools can be used to support the numismatic task of processing and analysing large complexes of coins, thus validating the enormous potential of IT-based methods. The main steps involved are the pre-sorting of coins by size (denomination), the attribution of individual coins to classes or types, and finally the identification of which coins were struck by individual dies.

The process from digitisation of a hoard as images to an actual die study is lengthy and work-intensive. In testing methods to support each of the steps, we focussed  particularly on methods that do not need any prior knowledge of the material, in order  to explore whether these methods can be applied to a dataset for which there is no more information than the images themselves. The different steps were evaluated against information provided by the numismatist working on the hoard (class and die attributions of the coins), who was also involved in different stages of the process. 


The result is a workflow that can be used in future work on large coin finds, thus supporting numismatists and significantly speeding up the work of identification and analysis. 


This paper also presents tools, visualisation methods and extensions that proved useful, both for the individual processes, as well as for communicating with the numismatists and integrating their expertise. Earlier phases of our work were presented at CAA 2022 in Oxford.

Files

CAA_Supporting the analysis of a large coin hoard with AI.pdf

Files (1.2 MB)

Additional details

Related works

Is supplemented by
Software: 10.5281/zenodo.8301158 (DOI)

References

  • Bay, Herbert, Tinne Tuytelaars, Luc Van Gool. 2006. SURF: Speeded Up Robust Features. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3951. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744023_3
  • Caron, Mathilde, Piotr Bojanowski, Armand Joulin, Matthijs Douze. 2018. Deep Clustering for Unsupervised Learning of Visual Features. https://doi.org/10.48550/arXiv.1807.0552
  • Colbert de Beaulieu, Jean-Baptiste. 1957. Le trésor de Jersey-11 et la numismatique celtique des deux Bretagnes. Revue Belge de Numismatique Vol. 103. 47-88.
  • Duan, Kaiwen, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang and Qi Tian. 2019. CenterNet: Keypoint Triplets for Object Detection. https://doi.org/10.48550/arXiv.1611.10012
  • Heinecke, Andreas, Emanuel Mayer, Abhinav Natarajan, Yoonju Jung, Unsupervised Statistical Learning for Die Analysis in Ancient Numismatics. Computer Vision and Pattern Recognition 2021. https://doi.org/10.48550/arXiv.2112.0290
  • Huang, Jonathan, Vivek Rathod, Chen Sun, Menglong Zhu, Anoop Korattikara, Alireza Fathi, Ian Fischer, Zbigniew Wojna, Yang Song, Sergio Guadarrama and Kevin Murphy. 2017. Speed/accuracy trade-offs for modern convolutional object detectors. https://doi.org/10.48550/arXiv.1611.10012
  • Kampel, Martin, Maia Zaharieva, Recognizing Ancient Coins Based on Local Features. In: G. Bebis/R. Boyle/B. Parvin (Hrsg.), Advances in Visual Computing. ISVC 2008. Lecture Notes in Computer Science, vol 5358. (Berlin / Heidelberg 2008) 11-22. https://doi.org/10.1007/978-3-540-89639-5_2
  • Karami, Ebrahim, Siva Prasad, Mohamed Shehata. 2017. Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images. https://doi.org/10.48550/arXiv.1710.02726
  • Lowe, David G. 2017.Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 60, 91–110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  • Lundberg Scott M., Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems 30 (NIPS 2017)
  • Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra. 2019. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. https://doi.org/10.1007/s11263-019-01228-7
  • Ribeiro, Marco Tulio, Sameer Singh, and Carlos Guestrin. Why should i trust you?: Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016.
  • Rublee, Ethan, Vincent Rabaud, Kurt Konolige and Gary Bradski. 2011. ORB: An efficient alternative to SIFT or SURF. 2011 International Conference on Computer Vision, Barcelona, Spain, pp. 2564-2571, doi: https://doi.org/10.1109/ICCV.2011.6126544.
  • Taylor, Zachary McCord, The Computer-Aided Die Study (CADS): A Tool for Conducting Numismatic Die Studies with Computer Vision and Hierarchical Clustering (2020). Computer Science Honors Theses. 54.
  • Tzutalin. LabelImg. Git code (2015).
  • Anwar H, Anwar S, Zambanini S, Porikli F. Deep ancient Roman Republican coin classification via feature fusion and attention. Pattern Recognition. 2021 Jun 1;114:107871
  • Shatrughan, Modi and Seema Bawa. Image Processing Based Systems and Techniques for the Recognition of Ancient and Modern Coins (2012)