ILAC (Image-based cLassification of Ancient Coins) is a research project in an interdisciplinary topic, computer vision together with numismatics. Numismatics is at a point where it can benefit greatly from the application of computer vision methods, and in turn provides a large number of new, challenging and interesting conceptual problems and data for computer vision. In ILAC competencies from both fields are brought together: the Computer Vision Lab at the Vienna University of Technology and the Department of Coins and Medals at the Museum of Fine Arts, Vienna. The project’s goal is to build anapplication for automatic image-based classification of historical coins in large-scale databases.
The broad use of digital cameras has led to an exploding number of digitally recorded coins. While computers are extensively used for storing and working on numismatic data, no computer aided classification system for ancient coins,which is based on images, has been investigated so far. Since specialists are usually able to classify coins from 2D image information only, computer vision methods can be applied to coin images to support numismatists on the examination of coinages as well as to speed up the overall processes significantly. The classification system of ILAC will initially focus on gold and silver issues of the Roman Republic period, but its groundwork is applicable to every other period and can be filled with different sets of coin images, allowing further scientific challenges to be tackled in the future.
During the project, various techniques and concepts of computer vision will be investigated and integrated in the classification system, such as symbol recognition, optical character recognition and content-based image retrieval. In the presented coin classification process three main stages are passed: coin segmentation, feature extraction and classification. The most crucial part of the system will be the feature extraction, as it has to extract only those features that are class-specific, i.e. with high separability and globalization power. In the case of ancient coins finding such features is challenging since ancient coins usually show both high intra-class variability and low inter-class variability. Robust feature extraction is further hampered by the partially high degradations of the coins. In respect to that, local image features will provide a powerful mechanism to detect similarities between coins. Furthermore, the coin inscription obtained using optical character recognition methods and the recognition of certain symbols can restrict the set of possible classes to a great extent.
- Report about the ILAC project in the science show “Newton” of the ORF (Austrian national TV channel) at March 29th, 2014.
- Participation at the “Lange Nacht der Forschung” (“Long Night of Research”) in the Museum of Fine Arts, Vienna, at April 4th, 2014.
- Source code for LIDRIC: A Local Image Descriptor Robust to Illumination Changes
- SIDIRE: Synthetic Image Dataset for Illumination Robustness Evaluation
- Coin Image Dataset
Anwar H., Zambanini S., Kampel M., Vondrovec K. “Ancient Coin Classification Using Reverse Motif Recognition”, IEEE Signal Processing Magazine – Special Issue on Signal Processing for Art Investigation, to appear.
Anwar H., Zambanini S., Kampel M. “Coarse-Grained Ancient Coin Classification Using Image-Based Reverse Side Motif Recognition“, Machine Vision and Applications, 26(2-3):295-304, April 2015.
Hödlmoser S., Zambanini S., Kampel, M. “Multi-Image Morphing: Summarizing Visual Information from Similar Ancient Coin Image Regions”, Proc. of 20th International Conference on Virtual System and Multimedia (VSMM), Hong Kong, China, to appear. (BEST CONFERENCE PAPER AWARD)
Zambanini S., Kampel M. “A Large-Scale Evaluation of Correspondence-Based Coin Classification on Roman Republican Coinage” In EUROGRAPHICS Workshop on Graphics and Cultural Heritage (GCH), Darmstadt, Germany, October 2014. (pdf)
Anwar H., Zambanini S., Kampel M. “A Rotation-Invariant Bag of Visual Words Model for Symbols based Ancient Coin Classification“, Proc. of 21st International Conference on Image Processing (ICIP), pp. 3032 – 3037, Paris, France, October 2014. (TOP 10% PAPER AWARD)
Anwar H., Zambanini S., Kampel M. “Encoding Spatial Arrangements of Visual Words for Rotation-invariant Image Classification“, Proc. of 36th German Conference on Pattern Recognition (GCPR), pp. 443-452, Münster, Germany, September 2014.
Zambanini S., Kavelar A., Kampel M. “Classifying Ancient Coins by Local Feature Matching and Pairwise Geometric Consistency Evaluation” Proc. of 22nd International Conference on Pattern Recognition (ICPR), pp. 3032-3037, Stockholm, Sweden, August 2014. (pdf)
Kavelar A., Zambanini S., Kampel M. “Reading the Legends of Roman Republican Coins“, Journal on Computing and Cultural Heritage, 7(1), 2014.
Siegl K., “Der Schatzfund von Großpold”, Mitteilungen der Österreichischen Numismatischen Gesellschaft 53(2):81-87, 2013.
Zambanini S., Kavelar A., Kampel M. “Improving Ancient Roman Coin Classification by Fusing Exemplar-Based Classification and Legend Recognition“, International Workshop on Multimedia for Cultural Heritage, pp. 149-158, Naples, Italy, September 2013. (pdf)
Zambanini S., Kampel M. “Evaluation of Low-Level Image Representations for Illumination-Insensitive Recognition of Textureless Objects“, International Conference on Image Analysis and Processing – ICIAP’13, pp. 71-80, Naples, Italy, September 2013.
(pdf,dataset, supplementary material)
Kavelar A., Zambanini S., Kampel M. “The ILAC-Project: Supporting Ancient Coin Classification by Means of Image Analysis”, XXIV International CIPA Symposium Strasbourg, France, September 2013, to appear.
Anwar H., Zambanini S., Kampel M. “Supporting Ancient Coin Classification by Image-Based Reverse Side Symbol Recognition“, 15th International Conference on Computer Analysis of Images and Patterns, pp. 17-25, York, UK, August 2013.
Zambanini S., Kampel M. “A Local Image Descriptor Robust to Illumination Changes“, Scandinavian Conferences on Image Analysis – SCIA 2013, pp. 11-21, Espoo, Finland, June 2013. (pdf, poster, source code)
Anwar H., Zambanini S., Kampel M. “A Bag of Visual Words Approach for Symbols-Based Coarse-Grained Ancient Coin Classification“, ÖAGM/AAPR 2013 – The 37th Annual Workshop of the Austrian Association for Pattern Recognition, Innsbruck, Austria, May 2013.
Kavelar A., Zambanini S., Kampel M. “Reading Ancient Coin Legends: Object Recognition vs. OCR“, ÖAGM/AAPR 2013 – The 37th Annual Workshop of the Austrian Association for Pattern Recognition, Innsbruck, Austria, May 2013.
Zambanini S., Kampel M. “Coarse-to-Fine Correspondence Search for Classifying Ancient Coins“, 2nd ACCV Workshop on e-Heritage, pp. 25-36, Daejeon, South Korea, November 2012. (pdf, dataset)
Kavelar A., Zambanini S., Kampel M. “Word Detection Applied to Images of Ancient Roman Coins“, 18th International Conference on Virtual Systems and Multimedia – VSMM 2012, pp. 577 – 580, Milan, Italy, September 2012.
Huber-Mörk R., Nölle M., Rubik M., Hödlmoser M., Kampel M., Zambanini S. “Automatic Coin Classification and Identification“, Advances in Object Recognition Systems, Dr. Ioannis Kypraios (Ed.), ISBN: 978-953-51-0598-5, InTech, 2012.
Kavelar A., Zambanini S., Kampel M. “Automatically Recognizing the Legends of Ancient Roman Imperial Coins”, 40th Annual International Conference on Computer Applications and Quantitative Methods in Archaeology – CAA2012, Southampton, UK, March 2012, to appear.
Zambanini S., Kampel M. “Using Image Analysis to Match a Coin to a Database”, Archaeology in the Digital Era – Papers from the 40th Annual Conference of Computer Applications and Quantitative Methods in Archaeology (CAA), Southampton, UK, March 2012, pp. 195-199.
Zambanini S., Kampel M., “Automatic Coin Classification by Image Matching“, International Symposium on Virtual Reality, Archaeology and Cultural Heritage (VAST 2011), pp. 65-72, Prato, Italy, October 2011.
Zambanini S., Kampel M., Vondrovec K. “The ILAC Project – An Automatic Image-Based Classification System for Historical Coins”, 39th Annual International Conference on Computer Applications and Quantitative Methods in Archaeology – CAA2011, Beijing, China, April 2011, to appear.