发表机构
National University of Computer and Emerging Sciences (FAST-NUCES)（国立计算机与新兴科学大学（FAST-NUCES））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对古罗马共和时期硬币字符识别问题，收集大规模数据集并手动标注。采用YOLO多种变体进行识别，其中YOLOv7-Large取得最佳mAP50为90.4%，为古代硬币字符识别提供了有效方法。
AI 中文摘要
在对古代硬币按时间和发行者进行正确分类时，硬币上的文字铭文（即传说）至关重要。这些传说由仍在英语中使用的字母或字符组成。本文通过基于深度学习的目标检测策略解决古罗马共和时期硬币上基于图像的字符识别问题。然而，由于放置不均匀、原始铭文技术以及磨损，这些硬币上的传说具有很大的变化性。其他挑战包括成像条件不一致，如光照、方向和比例。为了适应这些情况，我们收集了一个包含5654张罗马共和时期硬币图像的新型大规模数据集，手动标注了21个字符标签，共计38808个标注。对于识别，我们使用了You Only Look Once（YOLO）变体：YOLOv3、v4、v5、v7和v8。YOLOv7-Large实现了最佳的90.4%的mAP50，其次是YOLOv7-Extended和YOLOv7-xl，分别为90.2%和90.1%。
英文摘要
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.
