Rotation Equivariance for Diamond Identification

Floris De Feyter, Bram Claes, Toon Goedemé

2023

Abstract

To guarantee integrity when trading diamonds, a certified company can grade the diamonds and give them a unique ID. While this is often done for high-valued diamonds, it is economically less interesting to do this for lower-valued diamonds. While integrity could be checked manually as well, this involves a high labour cost. Instead, we present a computer vision-based technique for diamond identification. We propose to apply a polar transformation to the diamond image before passing the image to a CNN. This makes the network equivariant to rotations of the diamond. With this set-up, our best model achieves an mAP of 100% under a stringent evaluation regime. Moreover, we provide a custom implementation of the polar warp that is multiple orders of magnitude faster than the frequently used implementation of OpenCV.

Paper Citation

in Harvard Style

De Feyter F., Claes B. and Goedemé T. (2023). Rotation Equivariance for Diamond Identification. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 115-123. DOI: 10.5220/0011658400003417

in Bibtex Style

@conference{visapp23,
author={Floris De Feyter and Bram Claes and Toon Goedemé},
title={Rotation Equivariance for Diamond Identification},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={115-123},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011658400003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Rotation Equivariance for Diamond Identification
SN - 978-989-758-634-7
AU - De Feyter F.
AU - Claes B.
AU - Goedemé T.
PY - 2023
SP - 115
EP - 123
DO - 10.5220/0011658400003417
PB - SciTePress