Skip to main content
SpringerLink
Log in
Book cover

International Conference on Neural Information Processing

ICONIP 2012: Neural Information Processing pp 133–140Cite as

The Elastic Net as Visual Category Representation: Visualisation and Classification

  • Conference paper

  • 2810 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 7664))

Abstract

In this paper we use the Elastic Net (EN) [9] as a visual category representation in feature space. We do this by training the EN on the high dimensional Pyramid Histogram of Visual Words (PHOW) features [2] often used in modern visual categorisation. By employing the topography preserving properties of the EN we visualise the features and draw some novel conclusions. We demonstrate how the EN can also be used as a Region of Interest detector [1]. Finally, inspired by biological vision we propose a new Visual Categorisation scheme that uses ENs as visual category representations. Our method shows promising results when tested on the Caltech101 [12] data set with several interesting future directions.

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. Image Processing 5(2), 401–408 (2007)

    Google Scholar 

  2. Bosch, A., Zisserman, A., Munoz, X.: Image Classification using Random Forests and Ferns. In: Proc. ICCV, vol. 21, pp. 1–8 (2007)

    Google Scholar 

  3. Carreira-Perpinan, M.: Generalised elastic nets (2003), http://faculty.ucmerced.edu/mcarreira-perpinan/papers.html

  4. Carreira-Perpiñán, M.Á., Dayan, P., Goodhill, G.J.: Differential Priors for Elastic Nets. In: Gallagher, M., Hogan, J.P., Maire, F. (eds.) IDEAL 2005. LNCS, vol. 3578, pp. 335–342. Springer, Heidelberg (2005)

    Chapter  Google Scholar 

  5. Chatfield, K., Lempitsky, V., Vedaldi, A., Zisserman, A.: The devil is in the details: an evaluation of recent feature encoding methods. In: Proc. BMVC 2011, pp. 1–12 (2011)

    Google Scholar 

  6. Cohen, D., Papliński, A.P.: A comparative evaluation of the Generative Topographic Mapping and the Elastic Net for the formation of Ocular Dominance stripes. In: Proc. WCCI–IJCNN, pp. 3237–3244. IEEE (2012)

    Google Scholar 

  7. Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. Earth 1, 22 (2004)

    Google Scholar 

  8. Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum Likelihood for Incomplete Data via the EM Algorithm. J. Royal Statistical Society B 39(1), 1–38 (1977)

    MathSciNet  MATH  Google Scholar 

  9. Durbin, R., Willshaw, D.: An analogue approach to the travelling salesman problem using an elastic net method. Nature 326(6114), 689–691 (1987)

    Article  Google Scholar 

  10. Durbin, R., Szeliski, R., Yuille, A.: An analysis of the Elastic Net Approach to the Traveling Salesman Problem. Neural Computation 1(3), 348–358 (1989)

    Article  Google Scholar 

  11. Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes (VOC) Challenge. Int. J. Computer Vision 88(2), 303–338 (2010)

    Article  Google Scholar 

  12. Fei-Fei, L., Fergus, R., Perona, P.: Learning Generative Visual Models from Few Training Examples. In: Proc. CVPR (2004, 2008)

    Google Scholar 

  13. Goodhill, G.J.: Contributions of theoretical modeling to the understanding of neural map development. Neuron 56(2), 301–311 (2007)

    Article  Google Scholar 

  14. Gross, C.G.: Coding for visual categories in the human brain. Nature Neuroscience 3(9), 855–856 (2000)

    Article  Google Scholar 

  15. Lazebnik, S., Schmid, C., Ponce, J.: Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. In: Proc. CVPR, vol. 2, pp. 2169–2178 (2006)

    Google Scholar 

  16. Lefebvre, G., Garcia, C.: A probabilistic Self-Organizing Map for facial recognition. In: Proc. ICPR, pp. 1–4 (2008)

    Google Scholar 

  17. MATLAB: R2012a, The MathWorks Inc. (2012)

    Google Scholar 

  18. Mutch, J., Lowe, D.G.: Multiclass Object Recognition with Sparse, Localized Features. In: Proc. CVPR, vol. 1, pp. 11–18 (2006)

    Google Scholar 

  19. Olier, I., Vellido, A.: Variational Bayesian Generative Topographic Mapping. J. Mathematical Modelling and Algorithms 7, 371–387 (2008)

    Article  MathSciNet  MATH  Google Scholar 

  20. Serre, T., Wolf, L., Poggio, T.: Object Recognition with Features Inspired by Visual Cortex. In: Proc. CVPR, vol. 2, pp. 994–1000 (2005)

    Google Scholar 

  21. Sfikas, G., Constantinopoulos, C., Likas, A., Galatsanos, N.P.: An analytic distance metric for Gaussian mixture models with application in image retrieval. Framework, 835–840 (2005)

    Google Scholar 

  22. Utsugi, A.: Density estimation by mixture models with smoothing priors. Neural Computation 10(8), 2115–2135 (1998)

    Article  Google Scholar 

  23. Vedaldi, A., Fulkerson, B.: VLFeat: An Open and Portable Library of Computer Vision Algorithms (2008), http://www.vlfeat.org/

Download references

Author information

Authors and Affiliations

  1. Clayton School of IT, Monash University, Australia

    Dror Cohen & Andrew P. Papliński

Authors
  1. Dror Cohen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andrew P. Papliński
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Texas A&M University at Qatar, Education City, P.O. Box 23874, Doha, Qatar

    Tingwen Huang

  2. Department of Control Science and Engineering, Huazhong University of Science and Technology, 1037 Luoyu Road, 430074, Wuhan, Hubei, China

    Zhigang Zeng

  3. College of Computer Science, Chongqing University, 174 Shazhengjie Street, 400044, Chongqing, China

    Chuandong Li

  4. Department of Electronic Engineering, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, Hong Kong, China

    Chi Sing Leung

Rights and permissions

Reprints and permissions

Copyright information

© 2012 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Cohen, D., Papliński, A.P. (2012). The Elastic Net as Visual Category Representation: Visualisation and Classification. In: Huang, T., Zeng, Z., Li, C., Leung, C.S. (eds) Neural Information Processing. ICONIP 2012. Lecture Notes in Computer Science, vol 7664. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34481-7_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-34481-7_17

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-34480-0

  • Online ISBN: 978-3-642-34481-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation