Feature Selection and Visual Learning

  • Michael S. Lew
Part of the Advances in Pattern Recognition book series (ACVPR)


In many content-based retrieval systems, the user is asked to understand how the computer sees the world. An emerging trend is to try to have the computer understand how people see the world. However, understanding the world is a fundamental computer vision problem which has withstood decades of research. The critical aspect to these emerging methods is that they have modest ambitions. Petkovic [26] has called this finding “simple semantics.” From recent literature, this generally means finding computable image features which are correlated with visual concepts. The key distinction is that we are not trying to fully understand how human intelligence works. This would imply creating a general model for understanding all visual concepts. Instead, we are satisfied to find features which describe some small, but useful domains of visual concepts.


Feature Selection Feature Subset Feature Class Feature Selection Method Visual 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.
    Boekee, D and Van der Lubbe, J, “Some Aspects of Error Bounds in Feature Selection”, Patt Recogn, 11, pp. 353–360, 1979.MATHCrossRefGoogle Scholar
  2. 2.
    Buijs, J and Lew, M, “Learning Visual Concepts”, ACM Multimedia’99, 2, pp. 5–8, 1999.Google Scholar
  3. 3.
    Carson, C, Thomas, M, Belongie, S, Hellerstein, J, and Malik, J, “Blobworld: A System for Region-Based Image Indexing and Retrieval”, Proc. VISUAL’99, Amsterdam, Netherlands, pp. 509-516, June, 1999.Google Scholar
  4. 4.
    Chang, SF, Chen, W, and Sundaram, H, “Semantic Visual Templates — Linking Visual Features to Semantics”, IEEE Int. Conf. on Image Processing, Chicago, IL, October, 1998.Google Scholar
  5. 5.
    Cover, T and Van Campenhout, J, “On the Possible Orderings in the Measurement Selection Problem”, IEEE Trans Syst Man Cybern, 7, pp. 657–661, 1977.MATHCrossRefGoogle Scholar
  6. 6.
    Eakins, J, “Similarity Retrieval of Trademark Images”, IEEE Multimed, 5(2), pp. 53–63, 1998.CrossRefGoogle Scholar
  7. 7.
    Ferri, F, Pudil, P, Hatef, M, and Kittler, J, “Comparative Study of Techniques for Large Scale Feature Selection”, Pattern Recognition in Practice IV, E. Gelsema and L Kanal, eds, pp. 403-413, Elsevier Science, 1994.Google Scholar
  8. 8.
    Flickner, M, Sawhney, H, Niblack, W, Ashley, J, Huang, Q, Dom, B, Gorkani, M, Hafner, J, Lee, D, Petkovic, D, Steele, D, and Yanker, P, “Query by Image and Video Content: The QBIC System”, Computer, IEEE Computer Society, pp. 23-32, September, 1995.Google Scholar
  9. 9.
    Forsyth, D, Malik, J, Fleck, M, Leung, T, Bregler, C, Carson, C, and Greenspan, H, “Finding Pictures of Objects in Large Collections of Images”, International Workshop on Object Recognition, Cambridge, April, 1996.Google Scholar
  10. 10.
    Fung, C and Loe, K, “Learning Primitive and Scene Semantics of Images for Classification and Retrieval”, ACM Multimedia’99, Orlando, Part 2, pp. 9-12, 1999.Google Scholar
  11. 11.
    Goldberg, DE, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley, Reading, MA, 1989.MATHGoogle Scholar
  12. 12.
    Gudivada, VN and Raghavan, VV, “Finding the Right Image, Content-Based Image Retrieval Systems”, Computer, IEEE Computer Society, pp. 18-62, September, 1995.Google Scholar
  13. 13.
    Holland, J, Adaptation in Natural and Artificial Systems, University of Michigan Press, Ann Arbor, Michigan, 1975.Google Scholar
  14. 14.
    Jain, A and Zongker, D, “Feature Selection: Evaluation, Application, and Small Sample Performance”, IEEE Trans Patt Anal Mach Intel, 19(2), pp. 153–158, 1997.CrossRefGoogle Scholar
  15. 15.
    Kittler, J, “Une generalisation de quelques algorithmes sous-optimaux de recherche d’ensembles d’attributs”, Reconnaissance des Formes et Traitement des Images, Paris, pp. 678-686, 1978.Google Scholar
  16. 16.
    Kullback, S, Information Theory and Statistics, Wiley, New York, 1959.MATHGoogle Scholar
  17. 17.
    Lew, M and Huijsmans, N, “Information Theory and Face Detection”, Int. Conf. on Pattern Recognition, Vienna, Austria, pp. 601-605, August 25-30, 1996.Google Scholar
  18. 18.
    Lew, M and Huang, TS, “Optimal Supports for Image Matching”, IEEE Digital Signal Processing Workshop, Loen, Norway, pp. 251-254, September, 1996.Google Scholar
  19. 19.
    Lew, M, Lempinen, K, and Huijsmans, DP, “Webcrawling Using Sketches”, VISUAL’97, San Diego, pp. 77-84, December, 1997.Google Scholar
  20. 20.
    Lewis, P, “The Characteristic Selection Problem in Recognition Systems”, IRE Trans on Inform Theory, 8, pp. 171–178, 1962.MATHCrossRefGoogle Scholar
  21. 21.
    Marill, T and Green, DM, “On the Effectiveness of Receptors in Recognition Systems”, IEEE Trans Inform Theory, 9, pp. 11–17, 1963.CrossRefGoogle Scholar
  22. 22.
    Mao, J, Mohiuddin, K, and Jain, A, “Parsimonious Network Design and Feature Selection Through Node Pruning”, Int. Conf. on Pattern Recognition, Jerusalem, pp. 622-624, 1994.Google Scholar
  23. 23.
    Narendra, PM and Fukunaga, K, “A Branch and Bound Algorithm for Feature Subset Selection”, IEEE Trans Comput, 26, pp. 917–922, 1977.MATHCrossRefGoogle Scholar
  24. 24.
    Novovicova, J, Pudil, P, and Kittler, J, “Divergence Based Feature Selection for Multimodal Class Densities”, IEEE Trans Patt Anal Mach Intel, 18(2), pp. 218–223, February, 1996.CrossRefGoogle Scholar
  25. 25.
    Pentland, A, Picard, R, and Sclaroff, S, “Photobook: Content-Based Manipulation of Image Databases”, Int J Computer Vision, 18, pp. 233–254, 1996.CrossRefGoogle Scholar
  26. 26.
    Petkovic, D, “Challenges and Opportunities for Pattern Recognition and Computer Vision Research in Year 2000 and Beyond”, Int. Conf. on Image Analysis and Processing, September, Florence, 2, pp. 1–5, 1997.MathSciNetCrossRefGoogle Scholar
  27. 27.
    Picard, R, “A Society of Models for Video and Image Libraries”, IBM Syst J, 1996.Google Scholar
  28. 28.
    Pudil, P, Novovicova, J, and Kittler, J, “Automatic Machine Learning of Decision Rule for Classification Problems in Image Analysis”, BMVC’ 93, Fourth British Machine Vision Conf, Vol. 1, pp. 15–24, 1993.Google Scholar
  29. 29.
    Pudil, P, Novovicova, J, and Kittler, J, “Floating Search Methods in Feature Selection” Patt Recogn Lett, pp. 1119-1125, 1994.Google Scholar
  30. 30.
    Ratan, A, Maron, O, Grimson, W, and Perez, T, “A Framework for Learning Query Concepts in Image Classification”, IEEE Conf. on Computer Vision and Pattern Recognition, Fort Collins, Colorado, pp. 423-431, 1999.Google Scholar
  31. 31.
    Raudys, S and Jain, A, “Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners”, IEEE Trans Patt Anal Mach Intell, 13, pp. 252–264, March, 1991.CrossRefGoogle Scholar
  32. 32.
    Rowley, H and Kanade, T, “Neural Network Based Face Detection”, IEEE Trans Patt Anal Mach Intell, 20, pp. 23–38, 1998.CrossRefGoogle Scholar
  33. 33.
    Sung, KK and Poggio, T, “Example-Based Learning for View-Based Human Face Detection”, IEEE Trans. Patt Anal Mach Intell, 20, pp. 39–51, 1998.CrossRefGoogle Scholar
  34. 34.
    Sebestyen, G, Decision Making Processes in Pattern Recognition, Macmillan, New York, 1962.Google Scholar
  35. 35.
    Siedlecki, W and Sklansky, J, “A Note on Genetic Algorithms for Large-Scale Feature Selection”, Patt Recogn Lett, 10, pp. 335–347, 1989.MATHCrossRefGoogle Scholar
  36. 36.
    Stearns, S, “On Selecting Features for Pattern Classifiers”, Int. Conf. on Pattern Recognition, pp. 71-75, 1976.Google Scholar
  37. 37.
    Vailaya, A, Jain, A, and Zhang, H, “On Image Classification: City vs. Landscape”, IEEE Workshop on Content-Based Access of Image and Video Libraries, Santa Barbara, June, 1998.Google Scholar
  38. 38.
    Whitney, A, “A Direct Method of Nonparametric Measurement Selection”, IEEE Trans Comput, 20, pp. 1100–1103, 1971.MathSciNetMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2001

Authors and Affiliations

  • Michael S. Lew

There are no affiliations available

Personalised recommendations