Improving Ancient Roman Coin Recognition with Alignment and Spatial Encoding
Abstract
Roman coins play an important role to understand the Roman empire because they convey rich information about key historical events of the time. Moreover, as large amounts of coins are daily traded over the Internet, it becomes necessary to develop automatic coin recognition systems to prevent illegal trades. In this paper, we describe a new large annotated database of over 2800 Roman coin images and propose an effective automated system for recognition of coins that leverages this new coin image set. As the use of succinct spatial-appearance relationships is critical for accurate coin recognition, we suggest two competing methods, adapted for the coin domain, to accomplish this task.
Cite
Text
Kim and Pavlovic. "Improving Ancient Roman Coin Recognition with Alignment and Spatial Encoding." European Conference on Computer Vision Workshops, 2014. doi:10.1007/978-3-319-16178-5_10Markdown
[Kim and Pavlovic. "Improving Ancient Roman Coin Recognition with Alignment and Spatial Encoding." European Conference on Computer Vision Workshops, 2014.](https://mlanthology.org/eccvw/2014/kim2014eccvw-improving/) doi:10.1007/978-3-319-16178-5_10BibTeX
@inproceedings{kim2014eccvw-improving,
title = {{Improving Ancient Roman Coin Recognition with Alignment and Spatial Encoding}},
author = {Kim, Jongpil and Pavlovic, Vladimir},
booktitle = {European Conference on Computer Vision Workshops},
year = {2014},
pages = {149-164},
doi = {10.1007/978-3-319-16178-5_10},
url = {https://mlanthology.org/eccvw/2014/kim2014eccvw-improving/}
}