Deep Ancient Roman Republican Coin Classification via Feature Fusion and Attention

TL;DR

This paper introduces CoinNet, a novel deep learning model that effectively classifies ancient Roman Republican coins by recognizing reverse motifs despite erosion, orientation, and lighting challenges, achieving over 98% accuracy on a large dataset.

Contribution

The paper presents CoinNet, a new neural network architecture with feature fusion and attention mechanisms, and provides the largest dataset of Roman Republican coins for classification research.

Findings

CoinNet achieves over 98% classification accuracy.

The model outperforms traditional and recent deep learning approaches.

Ablation studies demonstrate the effectiveness of each component.

Abstract

We perform the classification of ancient Roman Republican coins via recognizing their reverse motifs where various objects, faces, scenes, animals, and buildings are minted along with legends. Most of these coins are eroded due to their age and varying degrees of preservation, thereby affecting their informative attributes for visual recognition. Changes in the positions of principal symbols on the reverse motifs also cause huge variations among the coin types. Lastly, in-plane orientations, uneven illumination, and a moderate background clutter further make the classification task non-trivial and challenging. To this end, we present a novel network model, CoinNet, that employs compact bilinear pooling, residual groups, and feature attention layers. Furthermore, we gathered the largest and most diverse image dataset of the Roman Republican coins that contains more than 18,000 images belonging to 228 different reverse motifs. On this dataset, our model achieves a classification accuracy of more than \textbf{98\%} and outperforms the conventional bag-of-visual-words based approaches and more recent state-of-the-art deep learning methods. We also provide a detailed ablation study of our network and its generalization capability. Models and Datasets available at https://github.com/saeed-anwar/CoinNet