Adapted SIFT Descriptor for Improved Near Duplicate Retrieval

Afra'a Ahmad Alyosef, Andreas Nürnberger

2016

Abstract

The scale invariant feature transformation algorithm (SIFT) has been designed to detect and characterize local features in images. It is widely used to find similar regions in affine transformed images, to recognize similar objects or to retrieve near-duplicates of images. Due to the computational complexity of SIFT based matching operations several approaches have been proposed to speed up this process. However, most approaches lack significant decrease of matching accuracy compared to the original descriptor. We propose an approach that is optimized for near-duplicate image retrieval tasks by a dimensionality reduction process that differs from other methods by preserving the information around the keypoints of any region patches of the original descriptor. The computation of the proposed Region Compressed (RC) SIFT−64D descriptors is therefore faster and requires less memory for indexing. Most important, the obtained features show at the same time a better retrieval performance and seem to be even more robust. In order to prove this, we provide results of a comparative performance analysis using the original SIFT−128D, reduced SIFT versions, SURF−64D and the proposed RC-SIFT−64D in image near-duplicate retrieval using large scale image benchmark databases.

Paper Citation

in Harvard Style

Alyosef A. and Nürnberger A. (2016). Adapted SIFT Descriptor for Improved Near Duplicate Retrieval . In Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-173-1, pages 55-64. DOI: 10.5220/0005694800550064

in Bibtex Style

@conference{icpram16,
author={Afra'a Ahmad Alyosef and Andreas Nürnberger},
title={Adapted SIFT Descriptor for Improved Near Duplicate Retrieval},
booktitle={Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2016},
pages={55-64},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005694800550064},
isbn={978-989-758-173-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Adapted SIFT Descriptor for Improved Near Duplicate Retrieval
SN - 978-989-758-173-1
AU - Alyosef A.
AU - Nürnberger A.
PY - 2016
SP - 55
EP - 64
DO - 10.5220/0005694800550064