Advertisement

Scene Categorization Using Boosted Back-Propagation Neural Networks

  • Xueming Qian
  • Zhe Yan
  • Kaiyu Hang
  • Guizhong Liu
  • Huan Wang
  • Zhe Wang
  • Zhi Li
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6297)

Abstract

Scene categorization plays an important role in computer vision, image content understanding, and image retrieval. In this paper, back-propagation neural network (BPN) is served as the basic classifier for multi-class scene/image categorization. Four features, namely, SPM (spatial pyramid appearance descriptor represented by scale invariant feature transform), PHOG (pyramid histogram of oriented gradient), GIST, and HWVP (hierarchical wavelet packet transform) are selected as the basic inputs of BPNs. They are the appearance, shape and texture descriptors respectively. For an M (M>2) classes scene categorization problem, we cascade M one-versus-all BPNs to determine the accurate label of an image. An offline multi-class Adaboost algorithm is proposed to fuse multiple BPN classifiers trained with complementary features to improve scene categorization performance. Experimental results on the widely used Scene-13 and Sport Event datasets show the effectiveness of the proposed boosted BPN based scene categorization approach. Scene categorization performances of BPN classifiers with input features: SPM, PHOG, GIST and HWVP, boosted BPN classifiers of each of the four features, and the boosted classifiers of all the four features are given. Relationships of boosted classifiers number and the scene categorization performance are also discussed. Comparisons with some existing scene categorization methods using the authors’ datasets further show effectiveness of the proposed boosted BPN based approach.

Keywords

Scene Categorization back-propagation neural network adaboost 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Monay, F., Gatica-Perez, D.: PLSA-based image auto-annotation:constraining the latent space. In: Proc. ACM Multimedia (2004)Google Scholar
  2. 2.
    Sudderth, E., Torralba, A., Freeman, W., Willsky, A.: Describing visual scenes using transformed dirichlet processes. In: NIPS (2005)Google Scholar
  3. 3.
    Li, F., Perona, P.: A Bayesian hierarchy model for learning natural scene categories. In: Proc. CVPR (2005)Google Scholar
  4. 4.
    Sivic, J., Russell, B., Efros, A., Zisserman, A., Freeman, W.: Discovering object categories in image collections. In: Proc. ICCV (2005)Google Scholar
  5. 5.
    Zheng, Y., Zhao, M., Neo, S., Chua, T., Tian, Q.: Visual synset: towards a higher-level visual representation. In: Proc. CVPR (2008)Google Scholar
  6. 6.
    Zhang, J., MarszaÃlek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: a comprehensive study. International Journal of Computer Vision (2007)Google Scholar
  7. 7.
    Bosch, A., Zisserman, A., Munoz, X.: Scene classification using a hybrid generative/discriminative approach. IEEE TPAMI 30(4), 712–727 (2008)Google Scholar
  8. 8.
    Li, J., Wang, J.: Automatic linguistic indexing of pictures by a statistical modeling approach. IEEE Trans. Pattern Anal. Mach. Intell. 25(9), 1075–1088 (2003)CrossRefGoogle Scholar
  9. 9.
    Bi, J., Chen, Y., Wang, J.: A Sparse Support Vector Machine Approach to Region-Based Image Categorization. In: Proc. CVPR (2005)Google Scholar
  10. 10.
    Larlus, D., Jurie, F.: Combining appearance models and markov random fields for category level object segmentation. In: Proc. CVPR (2008)Google Scholar
  11. 11.
    Quattoni, A., Collins, M., Darrell, T.: Conditional random fields for object recognition. In: NIPS (2004)Google Scholar
  12. 12.
    Galleguillos, C., Rabinovich, A., Belongie, S.: Object categorization using co-occurrence, location and appearance. In: Proc. CVPR (2008)Google Scholar
  13. 13.
    Cao, L., Li, F.: Spatially coherent latent topic model for concurrent object segmentation and classification. In: Proc. ICCV (2007)Google Scholar
  14. 14.
    Holub, A., Perona, P.: A discriminative framework for modeling object classes. In: Proc. ICCV (2005)Google Scholar
  15. 15.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV (2) (2004)Google Scholar
  16. 16.
    Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Proc. ECCV (2004)Google Scholar
  17. 17.
    Crandall, D., Felzenszwalb, P., Huttenlocher, D.: Spatial priors for part-based recognition using statistical models. In: Proc. CVPR (2005)Google Scholar
  18. 18.
    Wang, G., Zhang, Y., Li, F.: Using dependent regions for object categorization in a generative framework. In: Proc. CVPR 2006 (2006)Google Scholar
  19. 19.
    Savarese, S., Winn, J., Criminisi, A.: Discriminative object class models of appearance and shape by correlations. In: Proc. CVPR 2006, pp. 2033–2040 (2006)Google Scholar
  20. 20.
    Teh, Y., Jordan, M., Beal, M., Blei, D.: Hierarchical Dirichlet processes. Journal of the American Statistical Association (2006)Google Scholar
  21. 21.
    Gosselin, P., Cord, M., Philipp-Foliguet, S.: Combining visual dictionary, kernel-based similarity and learning strategy for image category retrieval. Computer Vision and Image Understanding 110, 403–417 (2008)CrossRefGoogle Scholar
  22. 22.
    Wu, L., Hu, Y., Li, M., Yu, N., Hua, X.: Scale-invariant visual language modeling for object categorization. IEEE Trans. Multimedia 11(2), 286–294 (2009)CrossRefGoogle Scholar
  23. 23.
    Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: Proc. CIVR (2007)Google Scholar
  24. 24.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proc. CVPR (2006)Google Scholar
  25. 25.
    Torralba, A., William, K., Freeman, T., Rubin, M.: Context-based vision system for place and object recognition. In: Proc. ICCV 2003 (2003)Google Scholar
  26. 26.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. IJCV 42(3), 145–175 (2001)zbMATHCrossRefGoogle Scholar
  27. 27.
    Qian, X., Liu, G., Guo, D., Li, Z., Wang, Z., Wang, H.: Object categorization using hierarchical wavelet packet texture descriptors. In: Proc. ISM 2009, pp. 44–51 (2009)Google Scholar
  28. 28.
    Zhang, H., Berg, A., Maire, M., Malik, J.: Svm-knn: Discriminative nearest neighbor classification for visual category recognition. In: Proc. CVPR (2006)Google Scholar
  29. 29.
    Ou, G., Murphey, Y.: Multi-class pattern classification using neural networks. Pattern Recognition 40, 4–18 (2007)zbMATHCrossRefGoogle Scholar
  30. 30.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
  31. 31.
    Freud, Y., Schapire, R.: Experiments with a new boosting algorithms. In: Machine Learning: Proceedings of the 13th International Conference (1996)Google Scholar
  32. 32.
    Li, L., Li, F.: What, where and who? Classifying events by scene and object recognition. In: Proc. ICCV (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Xueming Qian
    • 1
  • Zhe Yan
    • 1
  • Kaiyu Hang
    • 1
  • Guizhong Liu
    • 1
  • Huan Wang
    • 1
  • Zhe Wang
    • 1
  • Zhi Li
    • 1
  1. 1.Department of Information and Communication EngineeringXi’an Jiaotong UniversityXi’anChina

Personalised recommendations