THE STRUCTURAL FORM IN IMAGE CATEGORIZATION

Juha Hanni, Esa Rahtu, Janne Heikkilä

2010

Abstract

In this paper we show an unsupervised approach how to find the most natural organization of images. Previous methods which have been proposed to discover the underlying categories or topics of visual objects create no structure or at least the structure, usually tree-shaped, is defined in advance. This causes a problem since the most relevant structure of the data is not always known. It is worthwhile to consider a generic way to find the most suitable structure of images. For this, we apply the model of finding the structural form (among eight natural forms) to automatically discover the best organization of objects in visual domain. The model simultaneously finds the structural form and an instance of that form that best explains the data. In addition, we present a generic structural form, so called meta structure, which can result in even more natural connections between clusters of images. We show that the categorization results are competitive with the state-of-the-art methods while giving more generic insight to the connections between different categories.

References

  1. Ahuja, N. and Todorovic, S. (2007). Learning the taxonomy and models of categories present in arbitrary images. In Proc. ICCV.
  2. Bart, E., Porteous, I., Perona, P., and Welling, M. (2008). Unsupervised learning of visual taxonomies. In Proc. ICPR.
  3. Blei, D., Ng, A., and Jordan, M. (2003). Latent Dirichlet allocation. Journal of Machine Learning Research, 3:993-1022.
  4. Bosch, A., Zisserman, A., and Muoz, X. (2006). Scene classification via plsa. In Proc. ECCV.
  5. Graham, D. and Allinson, N. (1998). Characterizing virtual eigensignatures for general purpose face recognition. Face Recognition: From Theory to Applications, NATO ASI Series F, Computer and Systems Sciences, 163:446-456.
  6. Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning. Springer, New York.
  7. Hoffmann, T. (2001). Unsupervised learning by probabilistic latent semantic analysis. Machine Learning, 42(1):177-196.
  8. Kemp, C. and Tenenbaum, J. (2008). covery of structural form. ings of the National Academy http://www.psy.cmu.edu/˜ckemp/.
  9. Lowe, D. (2004). Distinctive image features from scaleinvariant keypoints. International Journal of Computer Vision, 60(2):91-110.
  10. Marszalek, M. and Schmid, C. (2008). Constructing category hierarchies for visual recognition. In Proc. ECCV.
  11. Parikh, D. and Chen, T. (2007). Unsupervised learning of hierarchical semantics of objects (hSOs). In Proc. CVPR.
  12. Shi, J. and Malik, J. (2002). Normalized cuts and image segmentation. IEEE TPAMI, 22(8):888-905.
  13. Sivic, J., Russell, B., Efros, A., Zisserman, A., and Freeman, W. (2005). Discovering object categories in image collections. In Proc. ICCV.
  14. Sivic, J., Russell, B., Zisserman, A., Freeman, W., and Efros, A. (2008). Unsupervised discovery of visual object class hierarchies. In Proc. CVPR.
  15. van de Sande, K., Gevers, T., and Snoek, C. (2010). Evaluating color descriptors for object and scene recognition. IEEE TPAMI, (in press).
  16. Winn, J., Criminisi, A., and Minka, T. (2005). Object categorization by learned universal visual dictionary. In Proc. ICCV.
Download


Paper Citation


in Harvard Style

Hanni J., Rahtu E. and Heikkilä J. (2010). THE STRUCTURAL FORM IN IMAGE CATEGORIZATION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 345-350. DOI: 10.5220/0002821403450350


in Bibtex Style

@conference{visapp10,
author={Juha Hanni and Esa Rahtu and Janne Heikkilä},
title={THE STRUCTURAL FORM IN IMAGE CATEGORIZATION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={345-350},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002821403450350},
isbn={978-989-674-029-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)
TI - THE STRUCTURAL FORM IN IMAGE CATEGORIZATION
SN - 978-989-674-029-0
AU - Hanni J.
AU - Rahtu E.
AU - Heikkilä J.
PY - 2010
SP - 345
EP - 350
DO - 10.5220/0002821403450350