Reading Ancient Coin Legends: Object Recognition vs. OCR
This work addresses a domain-specific challenge in archaeology and numismatics by improving text recognition for ancient coins, but it is incremental as it adapts existing scene text recognition techniques.
The paper tackled the problem of recognizing text on ancient coins, where standard OCR fails, by developing a scene text recognition method tailored to coin legends, which outperformed a standard OCR engine on a set of 180 cropped coin legend words.
Standard OCR is a well-researched topic of computer vision and can be considered solved for machine-printed text. However, when applied to unconstrained images, the recognition rates drop drastically. Therefore, the employment of object recognition-based techniques has become state of the art in scene text recognition applications. This paper presents a scene text recognition method tailored to ancient coin legends and compares the results achieved in character and word recognition experiments to a standard OCR engine. The conducted experiments show that the proposed method outperforms the standard OCR engine on a set of 180 cropped coin legend words.