Advertisement

Multilinear Tensor Supervised Neighborhood Embedding Analysis for View-Based Object Recognition

  • Xian-Hua Han
  • Yen-Wei Chen
  • Xiang Ruan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6297)

Abstract

In this paper, we propose a multilinear (N-Dimensional) Tensor Supervised Neighborhood Embedding (called ND-TSNE) for discriminant feature representation, which is used for view-based object recognition. ND-TSNE use a general N th order tensor discriminant and neighborhood-embedding analysis approach for object representation. The benefits of ND-TSNE include: (1) a natural way of representing data without losing structure information, i.e., the information about the relative positions of pixels or regions; (2) a reduction in the small sample size problem which occurs in conventional supervised learning because the number of training samples is much less than the dimensionality of the feature space; (3) a neighborhood structure preserving in tensor feature space for object recognition and a good convergence property in training procedure. With Tensor-subspace features, the random forests as a multi-way classifier is used for object recognition, which is much easier for training and testing compared with multi-way SVM. We demonstrate the performance advantages of our proposed approach over existing techniques using experiments on the COIL-100 and the ETH-80 datasets.

Keywords

Random Forest Object Recognition Recognition Rate Alternative Less Square Average Recognition Rate 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Poggio, T., Edelman, S.: A network that learns to recognize 3D objects. Nature 343, 263–266 (1990)CrossRefGoogle Scholar
  2. 2.
    Murase, H., Nayar, S.K.: Visual learning and recognition of 3D objects from appearance. International Journal of Computer Vision 14, 5–24 (1995)CrossRefGoogle Scholar
  3. 3.
    Gong, S., McKenna, S., Collins, J.: An investigation into face pose distributions. In: AFGR, pp. 265–270 (1996)Google Scholar
  4. 4.
    Roobaert, D., Hulle, M.V.: View-based 3D object recognition with support vector machines. In: IEEE International Workshop on Neural Networks for Signal Processing (1999)Google Scholar
  5. 5.
    Pontil, M., Verri, A.: Support vector machines for 3D object recognition. PAMI, 637–646 (1998)Google Scholar
  6. 6.
    Yang, M.-H., Roth, D., Ahuja, N.: Learning to recognize 3D objects with SNoW. In: Proceedings of the Sixth European Conference on Computer Vision, pp. 439–454 (2000)Google Scholar
  7. 7.
    Wang, Y., Gong, S.: Tensor Discriminant Analysis for View-based Object Recognition. In: Proceedings of ICPR, pp. 439–454 (2006)Google Scholar
  8. 8.
    He, X., Cai, D., Niyogi, P.: Tensor Subspace Analysis. In: Proceedings of ICPR, pp. 439–454 (2006)Google Scholar
  9. 9.
    Amit, Y., Geman, D.: Shape quantization and recognition with randomized trees. Neural Computation 9, 1545–1588 (1997)CrossRefGoogle Scholar
  10. 10.
    Breiman, L.: Random forests. Machine Learning 45, 5–32 (2001)MATHCrossRefGoogle Scholar
  11. 11.
    Lepetit, V., Fua, P.: Keypoint recognition using randomized trees. IEEE PAMI (2006)Google Scholar
  12. 12.
    Moosmann, F., Triggs, B., Jurie, F.: Fast discriminative visual codebooks using randomized clustering forests. In: NIPS (2006)Google Scholar
  13. 13.
    Ozuysal, M., Fua, P., Lepetit, V.: Fast keypoint recognition in ten lines of code. In: CVPR (2007)Google Scholar
  14. 14.
    Winn, J., Shotton, J.: The layout consistent random field for recognizing and segmenting partially occluded objects. In: CVPR (2006)Google Scholar
  15. 15.
    Winn, J., Criminisi, A.: Object class recognition at a glance. In: CVPR (2006)Google Scholar
  16. 16.
    Lathauwer, L.D.: Signal processing based on multilinear algebra, Ph.D. Thesis, Katholike Universiteit Leuven (1997)Google Scholar
  17. 17.
    Nigsch, F., Bender, A., van Buuren, B., Tissen, J., Nigsch, E., Mitchell, J.B.O.: Melting Point Prediction Employing k-nearest Neighbor Algorithms and Genetic Parameter Optimization. Journal of Chemical Information and Modeling 46(6), 2412 (2006)CrossRefGoogle Scholar
  18. 18.
    Leibe, B., Schiele, B.: Analyzing appearance and contour based methods for object categorization. In: CVPR (June 2003)Google Scholar
  19. 19.
    Marée, R., Geurts, P., Piater, J., Wehenkel, L.: Random subwindows for robust image classification. In: CVPR 2005, vol. 1, pp. 34–40 (June 2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Xian-Hua Han
    • 1
  • Yen-Wei Chen
    • 1
  • Xiang Ruan
    • 2
  1. 1.College of Information Science and EngineeringRitsumeikan UniversityKasatsu-shiJapan
  2. 2.Omron CorporationJapan

Personalised recommendations