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.
@article{arxiv.1304.7184,
title = {Reading Ancient Coin Legends: Object Recognition vs. OCR},
author = {Albert Kavelar and Sebastian Zambanini and Martin Kampel},
journal= {arXiv preprint arXiv:1304.7184},
year = {2013}
}
Comments
Part of the OAGM/AAPR 2013 proceedings (arXiv:1304.1876)