SCENE CLASSIFICATION USING SPATIAL RELATIONSHIP BETWEEN LOCAL POSTERIOR PROBABILITIES

Tetsu Matsukawa, Takio Kurita

Abstract

This paper presents scene classification methods using spatial relationship between local posterior probabilities of each category. Recently, the authors proposed the probability higher-order local autocorrelations (PHLAC) feature. This method uses autocorrelations of local posterior probabilities to capture spatial distributions of local posterior probabilities of a category. Although PHLAC achieves good recognition accuracies for scene classification, we can improve the performance further by using crosscorrelation between categories. We extend PHLAC features to crosscorrelations of posterior probabilities of other categories. Also, we introduce the subtraction operator for describing another spatial relationship of local posterior probabilities, and present vertical/horizontal mask patterns for the spatial layout of auto/crosscorrelations. Since the combination of category index is large, we compress the proposed features by two-dimensional principal component analysis. We confirmed the effectiveness of the proposed methods using Scene-15 dataset, and our method exhibited competitive performances to recent methods without using spatial grid informations and even using linear classifiers.

References

  1. Battiato, S., Farinella, G., Gallo, G., and Ravi, D. (2009). Spatial hierarchy of textons distributions for scene classification. In MMM, pages 333-343.
  2. Bosch, A., Munoz, X., and Freixenet, J. (2007). Segmentation and description of natural outdoor scenes. Image and Vision Computing, 25:727-740.
  3. Bosch, A., Zisserman, A., and Munoz, X. (2008). Scene classification using a hybrid generative/discriminative approach. IEEE Trans. on PAMI, 30(4):712-727.
  4. Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., and Lin, C.-J. (2008). LIBLINEAR: A library for large linear classification. JMLR, 9:1871-1874.
  5. Farinella, G., Battiato, S., Gallo, G., and Cipolla, R. (2008). Natural versus artificial scene classification by ordering discrete fourier power spectra. In SSPR&SPR.
  6. FeiFei, L. and Perona, P. (2005). A bayesian hierarchical model for learning natural scene categories. In CVPR.
  7. Gorkani, M. and Picard, R. (1994). Texture orientation for sorting phots at a glance. In ICPR.
  8. Hotta, K. (2009). Scene classification based on local autocorrelation of similarities with subspaces. In ICIP.
  9. Kobayashi, T. and Otsu, N. (2008). Image feature extraction using gradient local auto-correlations. In ECCV.
  10. Ladret, P. and Gue'rin-Dugue', A. (2001). Categorisation and retrieval of scene photographs from a jpeg compressed database. Pattern Analysis & Applications, 4:185 - 199.
  11. Lazebnik, S., Schmid, C., and Ponece, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In CVPR.
  12. Matsukawa, T. and Kurita, T. (2009). Image classification using probability higher-order local auto-correlations. In ACCV.
  13. Oliva, A. and Torralba, A. (2001). Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV, 42(3):145-175.
  14. Otsu, N. and Kurita, T. (1988). A new scheme for practical flexible and intelligent vision systems. In IAPR Workshop on Computer Vision, pages 431-435.
  15. Quattoni, A. and Torralba, A. (2009). Recognizing indoor scenes. In CVPR, pages 413-420.
  16. Rasiwasia, N. and Vasconcelos, N. (2008). Scene classification with low-dimensional semantic spaces and weak supervision. In CVPR, pages 1 - 8.
  17. Renninger, L. and Malik, J. (2004). When is scene identification just texture recognition? Vision Research, 44(19):2301-2311.
  18. Shotton, J., Johnson, M., and Cipolla, R. (2008). Semantic texton forests for image categorization and segmentation. In CVPR, pages 1 - 8.
  19. Szummer, M. and Picard, R. (1998). Indoor-outdoor image classification. In IEEE Intl. Workshop on ContentBased Access of Image and Video Databases.
  20. Torralba, A. (2003). Contextual priming for object detection. IJCV, 53:169 - 191.
  21. Torralba, A. and Oliva, A. (2003). Statistics of natural image categories. Network: Computing in Nueral Systems, 14:391 - 412.
  22. Toyoda, T. and Hasegawa, O. (2007). Extension of higher order local autocorrelation features. Pattern Recognition, 40:1466-1477.
  23. Vogel, J. and Schiele, B. (2007). Semantic modeling of natural scenes for content-based image retrieval. IJCV, 72(2):133-157.
  24. Wu, J. and Rehg, J. (2008). Where am i: Place instance and category recognition using spatial pact. In CVPR.
  25. Yang, J., Yu, K., Gong, Y., and Huang, T. (2009). Linear spatial pyramid matching using sparse coding for image classification. In CVPR.
  26. Yang, J., Zhang, D., Frangi, A., and Yang, J. (2004). Twodimensional pca: a new approach to appearance-based face representation and recognition. IEEE Trans. on PAMI, 26(1):131-137.
  27. Yao, B., Niebles, J., and Fei-Fei, L. (2009). Mining discriminative adjectives and prepositions for natural scene recognition. In The joint VCL-ViSU 2009 workshop.
  28. Zheng, Y., Lu, H., Jin, C., and Xue, X. (2009). Incorporating spatial correlogram into bag-of-features model for scene categorization. In ACCV.
  29. Zheng, Y.-T., Zhao, M., Neo, S.-Y., Chua, T.-S., and Tian, Q. (2008). Visual synset: towards a higher-level visual representation. In CVPR, pages 1 - 8.
Download


Paper Citation


in Harvard Style

Matsukawa T. and Kurita T. (2010). SCENE CLASSIFICATION USING SPATIAL RELATIONSHIP BETWEEN LOCAL POSTERIOR PROBABILITIES . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 325-332. DOI: 10.5220/0002819903250332


in Bibtex Style

@conference{visapp10,
author={Tetsu Matsukawa and Takio Kurita},
title={SCENE CLASSIFICATION USING SPATIAL RELATIONSHIP BETWEEN LOCAL POSTERIOR PROBABILITIES},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={325-332},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002819903250332},
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 - SCENE CLASSIFICATION USING SPATIAL RELATIONSHIP BETWEEN LOCAL POSTERIOR PROBABILITIES
SN - 978-989-674-029-0
AU - Matsukawa T.
AU - Kurita T.
PY - 2010
SP - 325
EP - 332
DO - 10.5220/0002819903250332