Automatic Query Image Disambiguation for Content-based Image Retrieval

Björn Barz, Joachim Denzler

Abstract

Query images presented to content-based image retrieval systems often have various different interpretations, making it difficult to identify the search objective pursued by the user. We propose a technique for overcoming this ambiguity, while keeping the amount of required user interaction at a minimum. To achieve this, the neighborhood of the query image is divided into coherent clusters from which the user may choose the relevant ones. A novel feedback integration technique is then employed to re-rank the entire database with regard to both the user feedback and the original query. We evaluate our approach on the publicly available MIRFLICKR-25K dataset, where it leads to a relative improvement of average precision by 23% over the baseline retrieval, which does not distinguish between different image senses.

Download


Paper Citation


in Harvard Style

Barz B. and Denzler J. (2018). Automatic Query Image Disambiguation for Content-based Image Retrieval.In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-290-5, pages 249-256. DOI: 10.5220/0006593402490256


in Bibtex Style

@conference{visapp18,
author={Björn Barz and Joachim Denzler},
title={Automatic Query Image Disambiguation for Content-based Image Retrieval},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2018},
pages={249-256},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006593402490256},
isbn={978-989-758-290-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - Automatic Query Image Disambiguation for Content-based Image Retrieval
SN - 978-989-758-290-5
AU - Barz B.
AU - Denzler J.
PY - 2018
SP - 249
EP - 256
DO - 10.5220/0006593402490256