Machine Vision and Applications

, Volume 24, Issue 2, pp 407–418 | Cite as

Embedding class information into local invariant features by low-dimensional retinotopic mapping

  • Bisser RaytchevEmail author
  • Yuta Kikutsugi
  • Toru Tamaki
  • Kazufumi Kaneda
Original Paper


In this paper, we propose a new general framework to obtain more distinctive local invariant features by projecting the original feature descriptors into low-dimensional feature space, while simultaneously incorporating also class information. In the resulting feature space, the features from different objects project to separate areas, while locally the metric relations between features corresponding to the same object are preserved. The low-dimensional feature embedding is obtained by a modified version of classical Multidimensional Scaling, which we call supervised Multidimensional Scaling (sMDS). Experimental results on a database containing images of several different objects with large variation in scale, viewpoint, illumination conditions and background clutter support the view that embedding class information into the feature representation is beneficial and results in more accurate object recognition.


Local invariant features Multidimensional scaling Dimensionality reduction SIFT PCA-SIFT View-invariant object recognition Retinotopic mapping 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lowe D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 12(60), 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    Bay H., Ess A., Tuytelaars T., Van Gool L.: SURF: speeded up robust features. Comput. Vis. Image Underst. (CVIU) 110(3), 346–359 (2008)CrossRefGoogle Scholar
  3. 3.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 20–25 (2005)Google Scholar
  4. 4.
    Tuytelaars T., Mikolajczyk K.: Local invariant feature detectors: a survey. Found. Trends Comput. Graph. Vis. 3(3), 177–280 (2007)CrossRefGoogle Scholar
  5. 5.
    Murase H., Nayar S.: Visual learning and recognition of 3-D objects from appearance. Int. J. Comput. Vis. 14(1), 5–24 (1995)CrossRefGoogle Scholar
  6. 6.
    Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: Proceedings of ECCV Workshop on Statistical Learning in Computer Vision, pp. 1–22 (2004)Google Scholar
  7. 7.
    Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in videos. In: Proceedings of the International Conference on Computer Vision, pp. 1470–1477 (2003)Google Scholar
  8. 8.
    Cox T., Cox M.: Multidimensional Scaling, 2nd edn. Chapman and Hall/CRC, Boca Raton (2000)CrossRefGoogle Scholar
  9. 9.
    Jolliffe I.: Principal Component Analysis. Springer, Berlin (1986)Google Scholar
  10. 10.
    Ke Y., Sukthankar R.: PCA-SIFT: a more distinctive representation for local image descriptors. Proc. IEEE Confer. Comput. Vis. Pattern Recogn. 2, 506–513 (2004)Google Scholar
  11. 11.
    Grauman K., Darrell T.: The pyramid match kernel: discriminative classification with sets of image features. Proc. IEEE Int. Confer. Comput. Vis. 2, 1458–1465 (2005)Google Scholar
  12. 12.
    van Gemert, J.C., Geusebroek, J.M., Veenman, C.J., Smeulders, A.W.M.: Kernel codebooks for scene categorization. In: Proceedings of European Conference Computer Vision (2008)Google Scholar
  13. 13.
    Hua, G., Brown, M., Winder, S.: Discriminant embedding for local image descriptors. In: Proceedings of IEEE International Conference on Computer Vision, pp. 1–8 (2007)Google Scholar
  14. 14.
    Belhumeur P.N., Hespanha J.P., Kriegman D.J.: Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Trans. PAMI 19(7), 711–720 (1997)CrossRefGoogle Scholar
  15. 15.
    Torgeson W.: Multidimensional scaling: I. Theory Method. Psychometrika 17, 401–419 (1952)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Mardia K., Kent J., Bibby J.: Multivariate Analysis. Academic Press, New York (1979)zbMATHGoogle Scholar
  17. 17.
    Wandell B., Brewer A.A., Dougherty R.F.: Visual field map clusters in human cortex. Phil. Trans. R. Soc. Lond. 360, 693–707 (2005)CrossRefGoogle Scholar
  18. 18.
    Gower J.: Adding a point to vector diagrams in multivariate analysis. Biometrica 55, 582–585 (1968)zbMATHCrossRefGoogle Scholar
  19. 19.
    Sammon J.W. Jr: A nonlinear mapping for data structure analysis. IEEE Trans. Comput. C-18(5), 401–409 (1969)CrossRefGoogle Scholar
  20. 20.
    Tipping, M.E.: Topographic Mapping and Feed-Forward Neural Networks. Ph.D. thesis, Aston University, Birmingham, UK (1996)Google Scholar
  21. 21.
    Tipping M.E., Lowe D.: Shadow targets: a novel algorithm for topographic projection by radial basis function network. Proc. Int. Conf. Artif. Neural Netw. 440, 7–12 (1997)CrossRefGoogle Scholar
  22. 22.
    Hartman E.J., Keeler J.D., Kowalski J.W.: Layered neural networks with Gaussian hidden units as universal approximations. Neural Comput. 2(2), 210–215 (1990)CrossRefGoogle Scholar
  23. 23.
    Park J., Sandberg I.W.: Approximation and radial basis function networks. Neural Comput. 5(2), 305–316 (1993)CrossRefGoogle Scholar
  24. 24.
    Nabney I.T.: Netlab—Algorithms for Pattern Recognition. Springer, Berlin (2003)Google Scholar
  25. 25.
    Pinz A.: Object categorization. Found. Trends Comput. Graph. Vis. 1(4), 255–353 (2005)CrossRefGoogle Scholar
  26. 26.
    Yan S., Xu D., Zhang B., Zhang H., Yang Q.: Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans. PAMI 29(1), 40–51 (2007)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  • Bisser Raytchev
    • 1
    Email author
  • Yuta Kikutsugi
    • 1
  • Toru Tamaki
    • 1
  • Kazufumi Kaneda
    • 1
  1. 1.Department of Information EngineeringHiroshima UniversityHigashi HiroshimaJapan

Personalised recommendations