Utilizing Structural Context for Region Classification

  • Zhiyong Wang
  • David D. Feng
Conference paper
Part of the IFIP International Federation for Information Processing book series (IFIPAICT, volume 228)


In this paper, we propose to take structural context of image regions into account for region classification through a structural neural network. Firstly, a tree structure of each region is formed to characterize the relationship among the region and its neighbours. Such structures integrate both visual attributes of regions and their structural contexts. Then the structural representations are learned through a Back-propagation Through Structure (BPTS) training algorithm. Comprehensive experimental results demonstrate that our proposed approach has a great potential in region classification.


Region Classification Structural Context Neural Networks 


  1. Barnard, K., Duygulu, P., de Freitas, N., Forsyth, D., Blei, D., and Jordan, M. (2003a). Matching words and pictures. Journal of Machine Learning Research, 3:1107–1135.zbMATHCrossRefGoogle Scholar
  2. Barnard, K., Duygulu, P., Guru, R., Gabbur, P., and Forsyth, D. (2003b). The effects of segmentation and feature choice in a translation model of object recognition. In The IEEE International Conference on Computer Vision and Pattern Recognition, volume 2, pages 675–682. Wisconsin, USA.Google Scholar
  3. Campbell, N. W., Mackeown, W. P. J., Thomas, B. T., and Troscianko, T. (1997). Interpreting image databases by region classification. Pattern Recognition, 30(4);555–563.CrossRefGoogle Scholar
  4. Chang, R.-F., Chen, C.-J., and Liao, C.-H. (2004). Region-based image retrieval using edge-flow segmentation and regioin adjacency graph. In The IEEE International Conference on Multimedia and Expo (ICME2004), volume 1, pages 1883–1886. Taiwan.Google Scholar
  5. Frasconi, P., Gori, M., and Sperduir, A. (1998). A general framework for adaptive processing of data structures. IEEE Trans, on Neural Networks, 9(5): 768–786.CrossRefGoogle Scholar
  6. Ma, W.-Y. and Manjunath, B. S. (2000). EdgeFlow: a technique for boundary detection and image segmentation. IEEE Trans, on Image Processing, 9(8): 1375–1388.zbMATHCrossRefMathSciNetGoogle Scholar
  7. Mori, Y., Takahashi, H., and Oka, R. (1999). Image-to-word transformation based on dividing and vector quantizing images with words. In The First International Workshop on Multimedia Intelligent Storage and Retrieval Management (MISRM99). Florida, USA.Google Scholar
  8. Scarselii, F. and Tsoi, A. C. (1998). Universal approximation using feedforward neural networks: a survey of some existing methods, and some new results. Neural Networks, 11(1): 15–38.CrossRefGoogle Scholar
  9. Singhal, A., Luo, J., and Zhang, W. (2003). Probabilistic spatial context models for scene content understanding. In The IEEE International Conference on Computer Vision and Pattern Recognition, volume 1, pages 235–241. Wisconsin, USA.Google Scholar
  10. Smeulders, A. W. M., Worring, M., Santini, S., Gupta, A., and Jain, R. (2000). Content-based image retrieval at the end of the early years. IEEE Trans, on Pattern Analysis and Machine Intelligence, 22(12): 1349–1380.CrossRefGoogle Scholar
  11. Sperduti, A. and Starita, A. (1997). Supervised neural networks for the classification of structures. IEEE Trans, on Neural Networks, 8(3):714–735.CrossRefGoogle Scholar
  12. Tsoi, A. C. (1998). Adaptive processing of data structures:an expository overview and comments. Technique report, Faculty of Informatics, University of Wollongong, Australia.Google Scholar
  13. Vailaya, A., Figueiredo, M. A. T., Jain, A. K., and jiang Zhang, H. (2001). Image classification for content-based indexing. IEEE Trans. on Image Processing, 10(1): 117–130.zbMATHCrossRefGoogle Scholar
  14. Wang, Z., Feng, D., and Chi, Z. (2004). Comparison of image partition methods for adaptive image categorization based on structural image representation. In The 8th International Conference on Control, Automation, Robotics, and Vision, pages 676–680. Kunming, China.Google Scholar
  15. Wang, Z., Hargenbuchner, M., Tsoi, A. C., Cho, S. Y., and Chi, Z. (2002). Image classification with structured self-organizing map. In IEEE International Joint Conference on Neural Networks (IJCNN2002), Hawaii, USA.Google Scholar

Copyright information

© International Federation for Information Processing 2006

Authors and Affiliations

  • Zhiyong Wang
    • 1
  • David D. Feng
    • 1
    • 2
  1. 1.School of Information TechnologiesThe University of SydneyAustralia
  2. 2.Department of Electronic and Information EngineeringHong Kong Polytechnic UniversityHong Kong

Personalised recommendations