Reading Legends on Ancient Coins: An Object Detection Approach for Character Recognition on a Novel Roman Republican Dataset

2026-07-28

AI Summary

This study addresses the significant challenges in recognizing inscriptions on Roman Republican coinage, which arise from irregular layouts, primitive engraving styles, severe wear, and variable imaging conditions. To tackle this problem, the work presents the first systematic application of modern object detection frameworks to ancient coin inscription recognition, introducing a large-scale dataset comprising 5,654 images with 38,808 annotated characters. Building upon the YOLO architecture, the authors propose a tailored enhancement of YOLOv7, termed YOLOv7-Large, which achieves a mean average precision (mAP50) of 90.4%—substantially outperforming other model variants. These results demonstrate the effectiveness and considerable potential of object detection methodologies for ancient script recognition tasks.

Abstract

When it comes to the proper classification of ancient coins with respect to their time and issuer, the textual inscriptions on these coins, also known as legends, are of paramount importance. These legends consist of alphabets or characters still used in English. This paper addresses image based character recognition on ancient Roman Republican coins via a deep learning based object detection strategy. However, legends on these coins pose high variation due to non-uniform placement, primitive inscription techniques, and wear and tear. Additional challenges include inconsistent imaging conditions such as illumination, orientation, and scale. To accommodate these, we gathered a novel large-scale dataset of 5,654 Roman Republican coin images, manually annotated with 21 character labels, totaling 38,808 annotations. For recognition, we use You Only Look Once (YOLO) variants: YOLOv3, v4, v5, v7, and v8. YOLOv7-Large achieves the best mAP50 of 90.4%, followed by YOLOv7-Extended and YOLOv7-xl with 90.2% and 90.1%, respectively.

Problem

• ancient coins
• character recognition
• legends
• Roman Republican
• object detection

Innovation

• object detection
• ancient coin legends
• YOLO
• character recognition
• Roman Republican dataset