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.

References

  1. Ke, Y., Sukthankar, R., and Huston, L. (2004). Efficient near-duplicate detection and sub-image retrieval. In Proc. 12th ACM International Conference on Multimedia, pages 869-876.
  2. Kim, S. J., Ng, H., Winkler, S., Song, P., and Fu, C.-W. (2012). Brush-and-drag: A multi-touch interface for photo triaging. In Proc. 14th ACM International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI), pages 59-68.
  3. Loos, A., Paduschek, R., and Kormann, D. (2009). Evaluation of algorithms for the summarization of photo collections. In Proc. Theseus/ImageCLEF Workshop on Visual Information Retrieval Evaluation.
  4. Oliva, A. and Torralba, A. (2001). Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision, 42(3):145-175.
  5. Schaefer, G. (2010). A next generation browsing environment for large image repositories. Multimedia Tools and Applications, 47(1):105-120.
  6. Tang, F. and Gao, Y. (2009). Fast near duplicate detection for personal image collections. In Proc. 17th ACM International Conference on Multimedia, pages 701- 704.
  7. Vonikakis, V. and Winkler, S. (2012). Emotion-based sequence of family photos. In Proc. 20th ACM International Conference on Multimedia, pages 1371-1372.
  8. Wang, M., Ji, D., Tian, Q., and Hua, X.-S. (2012). Intelligent photo clustering with user interaction and distance metric learning. Pattern Recognition Letters, 33(4):462-470.
  9. Wang, Y., Hou, Z., and Leman, K. (2011). Keypoint-based near-duplicate images detection using affine invariant feature and color matching. In Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 1209-1212.
  10. Wu, Z., Ke, Q., Isard, M., and Sun, J. (2009). Bundling features for large scale partial-duplicate web image search. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 25-32.
  11. Zhang, D.-Q. and Chang, S.-F. (2004). Detecting image near-duplicate by stochastic attributed relational graph matching with learning. In Proc. 12th ACM International Conference on Multimedia, pages 877-884.
  12. W.-L. (2013).
  13. http://www.cs.cityu.edu.hk/ [Online; accessed 6-Nov-2013].
  14. Zhao, W.-L. and Ngo, C.-W. (2009). Scale-rotation invariant pattern entropy for keypoint-based near-duplicate detection. IEEE Transactions on Image Processing, 18(2):412-423.
  15. Zheng, L., Qiu, G., Huang, J., and Fu, H. (2011). Salient covariance for near-duplicate image and video detection. In Proc. IEEE International Conference on Image Processing (ICIP), pages 2537-2540.
Download


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