Salient Feature Selection for Visual Concept Learning

  • Feng Xu
  • Lei Zhang
  • Yu-Jin Zhang
  • Wei-Ying Ma
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3767)


Image classification could be treated as an effective solution to enable keyword-based semantic image retrieval. In this paper, we propose a novel image classification framework by learning semantic concepts of image categories. To choose representative features for an image category and meanwhile reduce noisy features, a three-step salient feature selection strategy is proposed. In the feature selection stage, salient patches are first detected and clustered. Then the region of dominance and salient entropy measures are calculated to reduce non-common salient patches for the category. Based on the selected visual keywords, SVM and keyword frequency model categorization method are applied to classification, respectively. The experimental results on Corel image database demonstrate that the proposed salient feature selection approach is very effective in image classification and visual concept learning.


Support Vector Machine Feature Selection Image Category Latent Dirichlet Allocation Semantic Concept 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Vailaya, A., Jain, A., Zhang, H.J.: On Image Classification: City vs. Landscape. Pattern Recognition 31(12), 1921–1935 (1998)CrossRefGoogle Scholar
  2. 2.
    Szummer, M., Picard, R.: Indoor-outdoor image classification. In: IEEE International Workshop on Content-based Access of Image and Video Databases, pp. 42–51 (1998)Google Scholar
  3. 3.
    Fergus, R., Perona, P., Zisserman, A.: Object Class Recognition by Unsupervised Scale-Invariant Learning. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. II/264-II/271 (2003)Google Scholar
  4. 4.
    Fei-Fei, L., Fergus, R., Perona, P.: A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1134–1141 (2003)Google Scholar
  5. 5.
    Fergus, R., Perona, P., Zisserman, A.: A Visual Category Filter for Google Images. In: Proceedings of the 8th European Conference on Computer Vision, pp. 242–256 (2004)Google Scholar
  6. 6.
    Csurka, G., Dance, C.R., Fan, L., Willamowski, J., Bray, C.: Visual Categorization with Bags of Keypoints. In: The 8th European Conference on Computer Vision - ECCV 2004, pp. 11–14 (2004)Google Scholar
  7. 7.
    Benitez, A.B., Chang, S.-F.: Image Classification using Multimedia Knowledge Networks. In: IEEE International Conference on Image Processing, pp. 613–616 (2003)Google Scholar
  8. 8.
    Fan, J., Gao, Y., Luo, H.: Multi-Level Annotation of Natural Scene Using Dominant Image Components and Semantic Concepts. In: MM 2004, pp. 540–547 (2004)Google Scholar
  9. 9.
    Sivic, J., Zisserman, A.: Video Google: A Text Retrieval Approach to Object Matching in Videsos. In: Proceedings of the Ninth IEEE International Conference on Computer Vision, ICCV 2003 (2003)Google Scholar
  10. 10.
    Blei, D.M., Jordan, M.I.: Modeling Annotated Data. In: SIGIR 2003, pp. 127–134 (2003)Google Scholar
  11. 11.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet Allocation. Journal of Machine Learning Research 3, 993–1022 (2003)zbMATHCrossRefGoogle Scholar
  12. 12.
    Vasconcelos, N., Vasconcelos, M.: Scalable Discriminant Feature Selection for Image Retrieval and Recognition. In: CVPR (2004)Google Scholar
  13. 13.
    Liu, Y., Collins, R.T.: A Computational Model for Repeated Pattern Perception using Frieze and Wallpaper Groups. In: CVPR 2000 (2000)Google Scholar
  14. 14.
    Kadir, T., Brady, M.: Scale, saliency and image description. IJCV 45(2), 83–105 (2001)zbMATHCrossRefGoogle Scholar
  15. 15.
    Lowe, D.G.: Object Recognition from Local Scale-Invariant Features. In: Proc. of the International Conference on Computer Vision (1999)Google Scholar
  16. 16.
    Vapnik, V.: Statistical Learning Theory. Wiley, Chichester (1998)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Feng Xu
    • 2
  • Lei Zhang
    • 1
  • Yu-Jin Zhang
    • 2
  • Wei-Ying Ma
    • 1
  1. 1.Microsoft Research AsiaBeijingP.R. China
  2. 2.Department of Electronic EngineeringTsinghua UniversityBeijingP.R. China

Personalised recommendations