Combining Fisher Vectors in Image Retrieval Using Different Sampling Techniques

Tomás Mardones, Héctor Allende, Claudio Moraga

2015

Abstract

This paper addresses the problem of content-based image retrieval in a large-scale setting. Most works in the area sample image patches using an affine invariant detector or in a dense fashion, but we show that both sampling methods are complementary. By using Fisher Vectors we show how several sampling methods can be combined in a simple fashion inquiring only in a small fixed computational cost while significantly increasing the precision of the image retrieval system. As a second contribution, we show Fisher Vectors using their variance component, normally ignored in image retrieval applications, have better performance than their mean component under certain relevant settings. Experiments with up to 1 million images indicate that the proposed method remains valid in large-scale image search.

Paper Citation

in Harvard Style

Mardones T., Allende H. and Moraga C. (2015). Combining Fisher Vectors in Image Retrieval Using Different Sampling Techniques . In Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM, ISBN 978-989-758-077-2, pages 128-135. DOI: 10.5220/0005179201280135

in Bibtex Style

@conference{icpram15,
author={Tomás Mardones and Héctor Allende and Claudio Moraga},
title={Combining Fisher Vectors in Image Retrieval Using Different Sampling Techniques},
booktitle={Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,},
year={2015},
pages={128-135},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005179201280135},
isbn={978-989-758-077-2},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,
TI - Combining Fisher Vectors in Image Retrieval Using Different Sampling Techniques
SN - 978-989-758-077-2
AU - Mardones T.
AU - Allende H.
AU - Moraga C.
PY - 2015
SP - 128
EP - 135
DO - 10.5220/0005179201280135