Advertisement

Evaluating Feature Combination in Object Classification

  • Jian Hou
  • Bo-Ping Zhang
  • Nai-Ming Qi
  • Yong Yang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6939)

Abstract

Feature combination is used in object classification to combine the strength of multiple complementary features and yield a more powerful feature. While some work can be found in literature to calculate the weights of features, the selection of features used in combination is rarely touched. Different researchers usually use different sets of features in combination and obtain different results. It’s not clear to which degree the superior combination results should be attributed to the combination methods and not the carefully selected feature sets. In this paper we evaluate the impact of various feature-related factors on feature combination performance. Specifically, we studied the combination of various popular descriptors, kernels and spatial pyramid levels through extensive experiments on four datasets of diverse object types. As a result, we provide some empirical guidelines on designing experimental setups and combination algorithms in object classification.

Keywords

Recognition Rate Powerful Feature Feature Combination Multiple Kernel Weak Feature 
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.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide-baseline stereo from maximally stable extremal regions. In: British Machine Vision Conference, vol. 1, pp. 384–393.Google Scholar
  3. 3.
    Dalal, N., Triggs, B.: Histogram of oriented graidents for human detection. In: IEEE International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886–893 (2005)Google Scholar
  4. 4.
    Yang, J.J., Li, Y.N., Tian, Y.H., Duan, L.Y., Gao, W.: Group-sensitive multiple kernel learning for object categorization. In: IEEE International Conference on Computer Vision, pp. 436–443 (2009)Google Scholar
  5. 5.
    Lanckriet, G., Cristianini, N., Bartlett, P., Ghaoui, L., Jordan, M.: Learning the kernel matrix with semidefinite programming. Journal of Machine Learning Research 5, 27–72 (2004)MathSciNetzbMATHGoogle Scholar
  6. 6.
    Kumar, A., Sminchisescu, C.: Support kernel machines for object recognition. In: IEEE International Conference on Computer Vision, pp. 1–8 (2007)Google Scholar
  7. 7.
    Lin, Y.Y., Liu, T.L., Fuh, C.S.: Local ensemble kernel learning for object category recognition. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)Google Scholar
  8. 8.
    Varma, M., Ray, D.: Learning the discriminative power-invariance trade-off. In: IEEE International Conference on Computer Vision, pp. 1–8 (2007)Google Scholar
  9. 9.
    Gehler, P., Nowozin, S.: On feature combination for multiclass object classification. In: IEEE International Conference on Computer Vision, pp. 221–228 (2009)Google Scholar
  10. 10.
    Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. In: CVPR, Workshop on Generative-Model Based Vision, p. 178 (2004)Google Scholar
  11. 11.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. International Journal of Computer Vision 42, 145–175 (2001)CrossRefzbMATHGoogle Scholar
  12. 12.
    Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: IEEE International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 524–531 (2005)Google Scholar
  13. 13.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: IEEE International Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 2169–2178 (2006)Google Scholar
  14. 14.
    Jia, L.L., Fei-Fei, L.: What, where and who? classifying event by scene and object recognition. In: IEEE International Conference on Computer Vision, pp. 1–8 (2007)Google Scholar
  15. 15.
    Nilsback, M.E., Zisserman, A.: A visual vocabulary for flower classification. In: IEEE International Conference on Computer Vision, pp. 1447–1454 (2006)Google Scholar
  16. 16.
    Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: ACM International Conference on Image and Video Retrieval, pp. 401–408 (2007)Google Scholar
  17. 17.
    Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transaction on Pattern Analsis and Machine Intelligence 24, 971–987 (2002)CrossRefzbMATHGoogle Scholar
  18. 18.
    Shechtman, E., Irani, M.: Matching local self-similarities across imagesn and videos. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)Google Scholar
  19. 19.
    Varma, M., Zisserman, A.: A statistical approach to texture classification from single images. Image and Vision Computing 62, 61–81 (2005)CrossRefGoogle Scholar
  20. 20.
    Schuffler, P., Fuchs, T., Ong, C., Roth, V., Buhmann, J.: Computational tma analysis and cell nucleus classification of renal cell carcinoma. In: 32 Annual Symposium of the German Pattern Recognition Society, pp. 202–211 (2010)Google Scholar
  21. 21.
    Ulas, A., Duin, R., Castellani, U., Loog, M., Bicego, M., Murino, V., Bellani, M., Cerruti, S., Tansella, M., Brambilla, P.: Dissimilarity-based detection of schizophrenia. In: ICPR Workshop on Pattern Recognition Challenges in FMRI Neuroimaging, pp. 32–35 (2010)Google Scholar
  22. 22.
    Barla, A., Odone, F., Verri, A.: Histogram intersection kernel for image classification. In: International Conference on Image Processing, pp. 513–516 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Jian Hou
    • 1
  • Bo-Ping Zhang
    • 1
  • Nai-Ming Qi
    • 2
  • Yong Yang
    • 2
  1. 1.School of Computer Science and TechnologyXuchang UniversityChina
  2. 2.School of AstronauticsHarbin Institute of TechnologyHarbinChina

Personalised recommendations