Key-point Detection with Multi-layer Center-surround Inhibition

Foti Coleca, Sabrina Zîrnovean, Thomas Käster, Thomas Martinetz, Erhardt Barth

2014

Abstract

We present a biologically inspired algorithm for key-point detection based on multi-layer and nonlinear centersurround inhibition. A Bag-of-Visual-Words framework is used to evaluate the performance of the detector on the Oxford III-T Pet Dataset for pet recognition. The results demonstrate an increased performance of our algorithm compared to the SIFT key-point detector. We further improve the recognition rate by separately training codebooks for the ON- and OFF-type key points. The results show that our key-point detection algorithms outperform the SIFT detector by having a lower recognition-error rate over a whole range of different key-point densities. Randomly selected key-points are also outperformed.

Paper Citation

in Harvard Style

Coleca F., Zîrnovean S., Käster T., Martinetz T. and Barth E. (2014). Key-point Detection with Multi-layer Center-surround Inhibition . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-003-1, pages 386-393. DOI: 10.5220/0004743103860393

in Bibtex Style

@conference{visapp14,
author={Foti Coleca and Sabrina Zîrnovean and Thomas Käster and Thomas Martinetz and Erhardt Barth},
title={Key-point Detection with Multi-layer Center-surround Inhibition},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={386-393},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004743103860393},
isbn={978-989-758-003-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)
TI - Key-point Detection with Multi-layer Center-surround Inhibition
SN - 978-989-758-003-1
AU - Coleca F.
AU - Zîrnovean S.
AU - Käster T.
AU - Martinetz T.
AU - Barth E.
PY - 2014
SP - 386
EP - 393
DO - 10.5220/0004743103860393