PhotoCluster - A Multi-clustering Technique for Near-duplicate Detection in Personal Photo Collections

Vassilios Vonikakis, Amornched Jinda-Apiraksa, Stefan Winkler

2014

Abstract

This paper presents PhotoCluster, a new technique for identifying non-identical near-duplicate images in personal photo collections. Contrary to existing methods, PhotoCluster estimates the probability that a pair of images may be considered near-duplicate. Its main thrust is a multiple clustering step that produces a non-binary near-duplicate probability for each image pair, which exhibits correlation with the average observer opinion. First, PhotoCluster partitions the photolibrary into groups of semantically similar photos, using global features. Then, the multiple clustering step is applied within the images of these groups, using a combination of global and local features. Computationally expensive comparisons between local features are taking place only on a limited part of the library, resulting in a low overall computational cost. Evaluation with two publicly available datasets show that PhotoCluster outperforms existing methods, especially in identifying ambiguous near-duplicate cases.

Paper Citation

in Harvard Style

Vonikakis V., Jinda-Apiraksa A. and Winkler S. (2014). PhotoCluster - A Multi-clustering Technique for Near-duplicate Detection in Personal Photo Collections . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 153-161. DOI: 10.5220/0004737701530161

in Bibtex Style

@conference{visapp14,
author={Vassilios Vonikakis and Amornched Jinda-Apiraksa and Stefan Winkler},
title={PhotoCluster - A Multi-clustering Technique for Near-duplicate Detection in Personal Photo Collections},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={153-161},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004737701530161},
isbn={978-989-758-004-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - PhotoCluster - A Multi-clustering Technique for Near-duplicate Detection in Personal Photo Collections
SN - 978-989-758-004-8
AU - Vonikakis V.
AU - Jinda-Apiraksa A.
AU - Winkler S.
PY - 2014
SP - 153
EP - 161
DO - 10.5220/0004737701530161