Texture Classification with Fisher Kernel Extracted from the Continuous Models of RBM

Tayyaba Azim, Mahesan Niranjan

2014

Abstract

In this paper, we introduce a novel technique of deriving Fisher kernels from the Gaussian Bernoulli restricted Boltzmann machine (GBRBM) and factored 3-way restricted Boltzmann machine (FRBM) to yield better texture classification results. GBRBM and FRBM, both, are stochastic probabilistic models that have already shown their suitability for modelling real valued continuous data, however, they are not efficient models for classification based on their likelihood performances (Jaakkola and Haussler, 1999; Azim and Niranjan, 2013). We induce discrimination in these models with the help of Fisher kernel that is constructed from the gradients of the parameters of the generative model. From the empirical results shown on two different texture data sets, i.e. Emphysema and Brodatz, we demonstrate how a useful texture classifier could be built from a very compact generative model that represents the data in the Fisher score space discriminately. The proposed discriminative technique allows us to achieve competitive classification performance on texture data sets, without expanding the size of the generative model with large number of hidden units. Also, comparative analysis shows that factored 3-way RBM is a good representative model of textures, giving rise to a Fisher score space that is less sparse and efficient for classification.

References

  1. Azim, T. and Niranjan, M. (2013). Inducing Discrimination in Biologically Inspired Models of Visual Scene Recognition. In MLSP.
  2. Chen, J., Kellokumpu, V., and Pietikinen, G. Z. . M. (2013). RLBP: Robust Local Binary Pattern. In BMVC 2013, Bristol, UK.
  3. Cho, K., Alexander, A., and R.Tapani (2011). Improved Learning of Gaussian-Bernoulli Restricted Boltzmann Machines. In ANN - Volume Part I, ICANN, pages 1017, Berlin, Heidelberg. Springer-Verlag.
  4. Cristani, M., Bicego, M., and Murino, V. (2002). Integrated Region and Pixel Based Approach to Background Modelling. In Workshop on MVC, pages 3-8.
  5. Hangarge, M., Santosh, K., Doddamani, S., and Pardeshi, R. (2013). Statistical Texture Features Based Handwritten and Printed Text Classification in South Indian Documents. CoRR, 1(32).
  6. Haralick, R., Shanmugam, K., and Dinstein, I. (1973). Textural Features for Image Classification. SMC, 3(6):610-621.
  7. Hinton, G. (2002). Training products of experts by minimizing contrastive divergence. Neural Computation, 14:1771-1800.
  8. Hinton, G. and Salakhutdinov, R. (2009). Semantic Hashing. IJAR, 50(7):969-978.
  9. Jaakkola, T. and Haussler, D. (1999). Exploiting Generative Models in Discriminative Classifiers. NIPS, pages 487-493.
  10. Kivinen, J. and Williams, C. (2012). Multiple Texture Boltzmann Machines. In AISTATS, volume 22, pages 638-646.
  11. Krizhevsky, A. (2009). Learning Multiple Layers of Features from Tiny Images. Master's thesis.
  12. Marr, D. and Vaina, L. (1982). Representation and Recognition of the Movements of Shapes. Proceedings of the Royal Society of London. Series B. Biological Sciences, 214(1197):501524.
  13. Matheron, G. (1967). Representation and Recognition of the Movements of Shapes. Proceedings of the Royal Society of London. Series B. Biological Sciences, 214(1197):501-524.
  14. Mohamed, A., Dahl, G., and Hinton, G. (2010). Deep Belief Networks for Phone Recognition. In NIPS.
  15. Neal, R. (1996). Bayesian Learning for Neural Networks. Springer-Verlag New York, Inc., Secaucus, NJ, USA.
  16. Poggio, T., Voorhees, H., and Yuille, A. (1988). A Regularized Solution to Edge Detection. Journal of Complexity, 4(2):106 123
  17. Ranzato, M., Krizhevsky, A., and Hinton, G. (2010). Factored 3-Way Restricted Boltzmann Machines for Modeling Natural Images. In AISTATS.
  18. Serra, J. (1983). Image Analysis and Mathematical Morphology. Academic Press, Inc., Orlando, FL, USA.
  19. Sørensen, L., Shaker, S., and de Bruijne, M. (2010). Quantitative Analysis of Pulmonary Emphysema Using Local Binary Patterns. Medical Imaging, 29(2):559-569.
  20. Taylor, J. and Cristianini, N. (2004). Kernel Methods for Pattern Analysis. Cambridge University Press, New York, USA.
  21. Tomita, F. and Tsuji, S. (1990). Computer Analysis of Visual Textures. Kluwer Academic Publishers, Norwell, MA, USA.
  22. Tuceryan, M. and Jain, A. (1998). Handbook of Pattern Recognition & Computer Vision. Chapter Texture Analysis, pages 235276. River Edge, NJ, USA
  23. Valkealahti, K. and Oja, E. (1998). Reduced Multidimensional Co-occurrence Histograms in Texture Classification. PAMI, 20(1):90-94.
  24. Weszka, J., Dyer, C., and Rosenfeld, A. (1976). A Comparative Study of Texture Measures for Terrain Classification. SMC, 6(4):269-285.
  25. Zhang, Y., X. Jian and J. Han (2005). Texture Feature-based Image Classification Using Wavelet Package Transform. In AIC, volume 3644 of LNCS, pages 165 173. Springer Berlin Heidelberg.
Download


Paper Citation


in Harvard Style

Azim T. and Niranjan M. (2014). Texture Classification with Fisher Kernel Extracted from the Continuous Models of RBM . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 684-690. DOI: 10.5220/0004857506840690


in Bibtex Style

@conference{visapp14,
author={Tayyaba Azim and Mahesan Niranjan},
title={Texture Classification with Fisher Kernel Extracted from the Continuous Models of RBM},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={684-690},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004857506840690},
isbn={978-989-758-004-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Texture Classification with Fisher Kernel Extracted from the Continuous Models of RBM
SN - 978-989-758-004-8
AU - Azim T.
AU - Niranjan M.
PY - 2014
SP - 684
EP - 690
DO - 10.5220/0004857506840690