HIERARCHICAL CONDITIONAL RANDOM FIELD FOR MULTI-CLASS IMAGE CLASSIFICATION

Michael Ying Yang, Wolfgang Förstner, Martin Drauschke

2010

Abstract

Multi-class image classification has made significant advances in recent years through the combination of local and global features. This paper proposes a novel approach called hierarchical conditional random field (HCRF) that explicitly models region adjacency graph and region hierarchy graph structure of an image. This allows to set up a joint and hierarchical model of local and global discriminative methods that augments conditional random field to a multi-layer model. Region hierarchy graph is based on a multi-scale watershed segmentation.

References

  1. Barnard, K., Duygulu, P., Freitas, N. D., Forsyth, D., Blei, D., and Jordan, M. (2003). Matching Words and Pictures. In JMLR, volume 3, pages 1107-1135.
  2. Drauschke, M. (2009). An Irregular Pyramid for Multiscale Analysis of Objects and their Parts. In 7th IAPRTC-15 Workshop on Graph-based Representations in Pattern Recognition, pages 293-303.
  3. Drauschke, M., Schuster, H.-F., and Förstner, W. (2006). Detectability of Buildings in Aerial Images over Scale Space. In PCV'06, IAPRS 36 (3), pages 7-12.
  4. Gould, S., Rodgers, J., Cohen, D., Elidan, G., and Koller, D. (2008). Multi-Class Segmentation with Relative Location Prior. IJCV, 80(3):300-316.
  5. He, X., Zemel, R., and Carreira-Perpin, M. (2004). Multiscale Conditional Random Fields for Image Labeling. In CVPR, pages 695-702.
  6. Kohli, P., Kumar, M. P., and Torr, P. (2007). P3 & Beyond: Solving Energies with Higher Order Cliques. In CVPR, pages 1-8.
  7. Kohli, P., Ladicky, L., and Torr, P. (2009). Robust Higher Order Potentials for Enforcing Label Consistency. IJCV, 82(3):302-324.
  8. Korc?, F. and Förstner, W. (2008). Interpreting Terrestrial Images of Urban Scenes using Discriminative Random Fields. In 21st ISPRS Congress, IAPRS 37 (B3a), pages 291-296.
  9. Kumar, S. and Hebert, M. (2003). Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification. In ICCV, pages 1150- 1157.
  10. Ladicky, L., Russell, C., and Kohli, P. (2009). Associative Hierarchical CRFs for Object Class Image Segmentation. In ICCV, pages 1-8.
  11. Lafferty, J., McCallum, A., and Pereira, F. (2001). Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In ICML, pages 282-289.
  12. Lazaridis, G. and Petrou, M. (2006). Image Registration using the Walsh Transform. Image Processing, 15(8):2343-2357.
  13. McCallum, A., Rohanimanesh, K., and Sutton, C. (2003). Dynamic Conditional Random Fields for Jointly Labeling Multiple Sequences. In NIPS Workshop on Syntax, Semantics and Statistic.
  14. Pearl, J. (1988). Probabilistic reasoning in intelligent systems. Morgan Kaufmann.
  15. Petrou, M. and Bosdogianni, P. (1999). Image Processing: The Fundamentals. Wiley.
  16. Plath, N., Toussaint, M., and Nakajima, S. (2009). MultiClass Image Segmentation using Conditional Random Fields and Global Classification. In ICML, pages 817- 824.
  17. Reynolds, J. and Murphy, K. (2007). Figure-ground segmentation using a hierarchical conditional random field. In 4th Canadian Conference on Computer and Robot Vision, pages 175-182.
  18. Schnitzspan, P., Fritz, M., Roth, S., and Schiele, B. (2009). Discriminative Structure Learning of Hierarchical Representations for Object Detection. In CVPR, pages 2238-2245.
  19. Schnitzspan, P., Fritz, M., and Schiele, B. (2008). Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features. In ECCV, pages 527-540.
  20. Shotton, J., Winnand, J., Rother, C., and Criminisi, A. (2006). Textonboost: Joint Appearance, Shape and Context Modeling for Multi-Class Object Recognition and Segmentation. In ECCV, pages 1-15.
  21. Sutton, C. and McCallum, A. (2005). Piecewise Training for Undirected Models. In 21th Ann. Conf. on Uncertainty in AI, pages 568-575.
  22. Toyoda, T. and Hasegawa, O. (2008). Random Field Model for Integration of Local Information and Global Information. PAMI, 30(8):1483-1489.
  23. Vishwanathan, S. V. N., Schraudolph, N. N., Schmidt, M. W., and Murphy, K. P. (2006). Accelerated Training of Conditional Random Fields with Stochastic Gradient Methods. In ICML, pages 969-976.
  24. Yang, L., Meer, P., and Foran, D. J. (2007). Multiple Class Segmentation using a Unified Framework over MeanShift Patches. In CVPR, pages 1-8.
Download


Paper Citation


in Harvard Style

Ying Yang M., Förstner W. and Drauschke M. (2010). HIERARCHICAL CONDITIONAL RANDOM FIELD FOR MULTI-CLASS IMAGE CLASSIFICATION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 464-469. DOI: 10.5220/0002877404640469


in Bibtex Style

@conference{visapp10,
author={Michael Ying Yang and Wolfgang Förstner and Martin Drauschke},
title={HIERARCHICAL CONDITIONAL RANDOM FIELD FOR MULTI-CLASS IMAGE CLASSIFICATION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={464-469},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002877404640469},
isbn={978-989-674-029-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)
TI - HIERARCHICAL CONDITIONAL RANDOM FIELD FOR MULTI-CLASS IMAGE CLASSIFICATION
SN - 978-989-674-029-0
AU - Ying Yang M.
AU - Förstner W.
AU - Drauschke M.
PY - 2010
SP - 464
EP - 469
DO - 10.5220/0002877404640469