Two sides of the same coin: Improved ancient coin classification using Graph Transduction Games

Abstract In this work we tackle the problem of automatic recognition of ancient coin types using a semisupervised learning method, namely Graph Transduction Games. Such problem is complex, mainly due to the low inter-class and large intra-class variations and the task becomes even more complex due to lack of labeled large datasets from certain ancient ages. In this paper we propose a new dataset which is chiefly the extension of a previous one both in terms of quantity and diversity. Moreover, we propose a game-theoretic model that exploits both sides of a coin to achieve higher classification accuracy. We experimentally demonstrate that proposed approach brings performance improvement in this complex task even when few number of labelled images are available.

[1]  Pietro Perona,et al.  Self-Tuning Spectral Clustering , 2004, NIPS.

[2]  Michael H. Crawford,et al.  Roman Republican coinage , 1975 .

[3]  Martin Kampel,et al.  Coarse-grained ancient coin classification using image-based reverse side motif recognition , 2015, Machine Vision and Applications.

[4]  Ognjen Arandjelovic,et al.  Towards computer vision based ancient coin recognition in the wild — Automatic reliable image preprocessing and normalization , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[5]  Marcello Pelillo,et al.  Ancient Coin Classification Using Graph Transduction Games , 2018, 2018 Metrology for Archaeology and Cultural Heritage (MetroArchaeo).

[6]  Antonio Torralba,et al.  SIFT Flow: Dense Correspondence across Scenes and Its Applications , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Ognjen Arandjelovic,et al.  Ancient Roman Coin Recognition in the Wild Using Deep Learning Based Recognition of Artistically Depicted Face Profiles , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[9]  J. Nash.  NON-COOPERATIVE GAMES , 1951, Classics in Game Theory.

[10]  Xingyu Pan,et al.  Image analysis and deep learning for aiding professional coin grading , 2018, Other Conferences.

[11]  Jörgen W. Weibull,et al.  Evolutionary Game Theory , 1996 .

[12]  Martin Kampel,et al.  Ancient Coin Classification Using Reverse Motif Recognition: Image-based classification of Roman Republican coins , 2015, IEEE Signal Processing Magazine.

[13]  Alexander Zien,et al.  Semi-Supervised Learning , 2006 .

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Martin Kampel,et al.  Recognizing Ancient Coins Based on Local Features , 2008, ISVC.

[16]  Martin Kampel,et al.  Classifying Ancient Coins by Local Feature Matching and Pairwise Geometric Consistency Evaluation , 2014, 2014 22nd International Conference on Pattern Recognition.

[17]  Marcello Pelillo,et al.  Transductive Label Augmentation for Improved Deep Network Learning , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[18]  Ognjen Arandjelovic,et al.  Understanding Ancient Coin Images , 2019, INNSBDDL.

[19]  Martin Kampel,et al.  Coarse-to-Fine Correspondence Search for Classifying Ancient Coins , 2012, ACCV Workshops.

[20]  Martin Kampel,et al.  Identification of ancient coins based on fusion of shape and local features , 2011, Machine Vision and Applications.

[21]  Martin Kampel,et al.  Image Based Recognition of Ancient Coins , 2007, CAIP.

[22]  Giorgio Valentini,et al.  Protein function prediction as a graph-transduction game , 2020, Pattern Recognit. Lett..

[23]  Ognjen Arandjelovic,et al.  Automatic attribution of ancient Roman imperial coins , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[24]  Vladimir Pavlovic,et al.  Discovering characteristic landmarks on ancient coins using convolutional networks , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[25]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[26]  Martin Kampel,et al.  Automatic Coin Classification by Image Matching , 2011, VAST.

[27]  Mohammad Mahdi Dehshibi,et al.  Statistical Feature Fusion for Sassanian Coin Classification , 2015 .

[28]  Aykut Erdem,et al.  Graph Transduction as a Noncooperative Game , 2012, Neural Computation.

[29]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Marcello Pelillo,et al.  A Game-Theoretic Probabilistic Approach for Detecting Conversational Groups , 2014, ACCV.

[31]  Marcello Pelillo,et al.  The Dynamics of Nonlinear Relaxation Labeling Processes , 1997, Journal of Mathematical Imaging and Vision.

[32]  Elena Marchiori,et al.  Unsupervised Domain Adaptation using Graph Transduction Games , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).