NPIC: Hierarchical Synthetic Image Classification Using Image Search and Generic Features

  • Fei Wang
  • Min-Yen Kan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4071)


We introduce NPIC, an image classification system that focuses on synthetic (e.g., non-photographic) images. We use class-specific keywords in an image search engine to create a noisily labeled training corpus of images for each class. NPIC then extracts both content-based image retrieval (CBIR) features and metadata-based textual features for each image for machine learning. We evaluate this approach on three different granularities: 1) natural vs. synthetic, 2) map vs. figure vs. icon vs. cartoon vs. artwork 3) and further subclasses of the map and figure classes. The NPIC framework achieves solid performance (99%, 97% and  85% in cross validation, respectively). We find that visual features provide a significant boost in performance, and that textual and visual features vary in usefulness at the different levels of granularities of classification.


Textual Feature Visual Feature Color Histogram Synthetic Image Content Base Image Retrieval 
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.
    Lienhart, R., Hartmann, A.: Classifying images on the web automatically. Journal of Electronic Imaging 11 (2002)Google Scholar
  2. 2.
    Swain, M.J., Frankel, C., Athitsos, V.: Webseer: An image search engine for the world wide web. In: International Conference on Computer Vision and Pattern Recognition (1997)Google Scholar
  3. 3.
    Huang, W., Tan, C. L., Leow, W. K.: Model-based chart image recognition. In: Lladós, J., Kwon, Y.-B. (eds.) GREC 2003. LNCS, vol. 3088, pp. 87–99. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  4. 4.
    Carberry, S., Elzer, S., Green, N., McCoy, K., Chester, D.: Extending document summarization to information graphics. In: Proceedings of the ACL 2004 Workshop, pp. 3–9 (2004)Google Scholar
  5. 5.
    Hu, J., Bagga, A.: Functionality-based web image categorization. In: Proceedings of WWW 2003 (2003)Google Scholar
  6. 6.
    Cao, R., Tan, C.L.: Separation of overlapping text from graphics. In: Proc. of the 6th International Conference on Document Analysis and Recognition (ICDAR 2001), p. 44 (2001)Google Scholar
  7. 7.
    Zhong, Y., Karu, K., Jain, A.K.: Locating text in complex color images. Pattern Recognition 29, 1523–1535 (1995)CrossRefGoogle Scholar
  8. 8.
    Zhou, J., Lopresti, D.: Extracting text from www images. In: Proc. of the 4th International Conference on Document Analysis and Recognition, vol. 1, pp. 248–252 (1997)Google Scholar
  9. 9.
    Munson, E., Tsymbalenko, Y.: To search for images on the web, look at the text, then look at the images. In: Proc. of the 1st international workshop on Web Document Analysis (WDA 2001) (2001)Google Scholar
  10. 10.
    Carson, C., Belongie, S., Greenspan, H., Malik, J.: Blobworld: Image segmentation using expectation-maximization and its application to image querying. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 1026–1038 (2002)CrossRefGoogle Scholar
  11. 11.
    Ma, W.Y., Manjunath, B.: NaTra: A toolbox for navigating large image databases. In: Proc. IEEE International Conference on Image Processing, pp. 568–571 (1997)Google Scholar
  12. 12.
    Smith, J.R., Chang, S.F.: Quad-tree segmentation for texture-based image query. In: Proceedings of the 2nd Annual ACM Multimedia Conference, San Francisco, CA (1994)Google Scholar
  13. 13.
    Wang, J.Z., Li, J., Chan, D., Wiederhold, G.: Semantics-sensitive retrieval for digital picture libraries. D-Lib Magazine 5 (1999)Google Scholar
  14. 14.
    Tian, Q., Sebe, N., Lew, M.S., Loupias, E., Huang, T.S.: Image retireval using wavelet-based salient points. J. of Electronic Imaging 10, 835–849 (2001)CrossRefGoogle Scholar
  15. 15.
    Getty Institute: Art and architecture thesaurus (2006),
  16. 16.
    Rubner, Y., Tomasi, C., Guibas, L.J.: The earth mover’s distance as a metric for image retrieval. International Journal of Computer Vision 40, 99–121 (2000)MATHCrossRefGoogle Scholar
  17. 17.
    Qin, L., Charikar, M., Li, K.: Image similarity search with compact data structures. In: Proc. of the 13th ACM conference on Information and knowledge management, Washington, D.C. (2004)Google Scholar
  18. 18.
    Schapire, R.E., Singer, Y.: Boostexter: A boosting-based system for text categorization. Machine Learning 39, 135–168 (2000)MATHCrossRefGoogle Scholar
  19. 19.
    Ng, T.T., Chang, S.F., Hsu, J., Xie, L., Tsui, M.P.: Physics-motivated features for distinguishing photographic images and computer graphics. In: Proc. of the ACM Int’l. Conf. on Multimedia, Singapore, pp. 239–248 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Fei Wang
    • 1
  • Min-Yen Kan
    • 1
  1. 1.Department of Computer Science, School of ComputingNational University of SingaporeSingapore

Personalised recommendations