A Bottom-up Approach to Class-dependent Feature Selection for Material Classification

Pascal Mettes, Robby Tan, Remco Veltkamp

2014

Abstract

In this work, the merits of class-dependent image feature selection for real-world material classification is investigated. Current state-of-the-art approaches to material classification attempt to discriminate materials based on their surface properties by using a rich set of heterogeneous local features. The primary foundation of these approaches is the hypothesis that materials can be optimally discriminated using a single combination of features. Here, a method for determining the optimal subset of features for each material category separately is introduced. Furthermore, translation and scale-invariant polar grids have been designed in this work to show that, although materials are not restricted to a specific shape, there is a clear structure in the spatial allocation of local features. Experimental evaluation on a database of real-world materials indicates that indeed each material category has its own preference. The use of both the class-dependent feature selection and polar grids results in recognition rates which exceed the current state-of-the-art results.

References

  1. Biederman, I. (1987). Recognition-by-components: A theory of human image understanding. Psychological Review, 94(2):115-147.
  2. Blei, D. and McAuliffe, J. (2010). Supervised topic models.
  3. Caputo, B., Hayman, E., Fritz, M., and Eklundh, J. (2010). Classifying materials in the real world. Image and Vision Computing, 28(2):150-163.
  4. Caputo, B., Hayman, E., and Mallikarjuna, P. (2005). Classspecific material categorisation. ICCV, 2:1597-1604.
  5. Chen, S. and Tian, Y. (2011). Evaluating effectiveness of latent dirichlet allocation model for scene classification. WOCC, pages 1-6.
  6. Criminisi, A., Shotton, J., and Konukoglu, E. (2012). Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Foundations and Trends in Computer Graphics and Vision, 7(2):81-227.
  7. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. CVPR, 1:886-893.
  8. Dana, K., Ginneken, B. v., S.K., N., and Koenderink, J. (1999). Reflectance and texture of real-world surfaces. ACM Transactions on Graphics, 18(1):1-34.
  9. Hu, D., Bo, L., and Ren, X. (2011). Toward robust material recognition for everyday objects. BMVC, pages 48.1- 48.11.
  10. Lazebnik, S., Schmid, C., and Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. CVPR, 2:2169-2178.
  11. Liu, C., Sharan, L., Adelson, E., and Rosenholtz, R. (2010). Exploring features in a bayesian framework for material recognition. CVPR, pages 239-246.
  12. Lowe, D. (2004). Distinctive image features from scaleinvariant features. IJCV, 60(2):91-110.
  13. Qi, X., Xiao, R., Guo, J., and Zhang, L. (2012). Pairwise rotation invariant co-occurrence local binary pattern. ECCV, 7577:158-171.
  14. Sharan, L., Liu, C., Rosenholtz, R., and Adelson, E. (2013). Recognizing materials using perceptually inspired features. IJCV, pages 1-24.
  15. Sharan, L., Rosenholtz, R., and Adelson, E. (2009). Material perception: What can you see in a brief glance? [abstract]. Journal of Vision, 9(8):784.
  16. Snoek, C., Worring, M., and Smeulders, A. (2005). Early versus late fusion in semantic video analysis. In ACM international conference on Multimedia, pages 399- 402. ACM.
  17. Varma, M. and Zisserman, A. (2005). A statistical approach to texture classification from single images. IJCV, 62(1):61-81.
  18. Varma, M. and Zisserman, A. (2009). A statistical approach to material classification using image patch exemplars. PAMI, 31(11):2032-2047.
  19. Wang, L., Zhou, N., and Chu, F. (2008). A general wrapper approach to selection of class-dependent features. IEEE Transactions on Neural Networks, 19(7):1267- 1278.
  20. Zhang, E. and Mayo, M. (2010). Enhanced spatial pyramid matching using log-polar-based image subdivision and representation. DICTA, pages 208-213.
Download


Paper Citation


in Harvard Style

Mettes P., Tan R. and Veltkamp R. (2014). A Bottom-up Approach to Class-dependent Feature Selection for Material Classification . 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 494-501. DOI: 10.5220/0004721204940501


in Bibtex Style

@conference{visapp14,
author={Pascal Mettes and Robby Tan and Remco Veltkamp},
title={A Bottom-up Approach to Class-dependent Feature Selection for Material Classification},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={494-501},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004721204940501},
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 - A Bottom-up Approach to Class-dependent Feature Selection for Material Classification
SN - 978-989-758-004-8
AU - Mettes P.
AU - Tan R.
AU - Veltkamp R.
PY - 2014
SP - 494
EP - 501
DO - 10.5220/0004721204940501