A CORTICAL FRAMEWORK FOR SCENE CATEGORISATION

J. M. F. Rodrigues, J. M. H. du Buf

2011

Abstract

Human observers can very rapidly and accurately categorise scenes. This is context or gist vision. In this paper we present a biologically plausible scheme for gist vision which can be integrated into a complete cortical vision architecture. The model is strictly bottom-up, employing state-of-the-art models for feature extractions. It combines five cortical feature sets: multiscale lines and edges and their dominant orientations, the density of multiscale keypoints, the number of consistent multiscale regions, dominant colours in the double-opponent colour channels, and significant saliency in covert attention regions. These feature sets are processed in a hierarchical set of layers with grouping cells, which serve to characterise five image regions: left, right, top, bottom and centre. Final scene classification is obtained by a trained decision tree.

References

  1. Bar, M. (2004). Visual objects in context. Nature Rev.: Neuroscience, 5:619-629.
  2. Bosch, A., Zisserman, A., and Munoz, X. (2009). Scene classification via pLSA. Proc. Europ. Conf. on Computer Vision, 4:517-530.
  3. Fei-Fei, L. and Perona, P. (2005). A Bayesian hierarchical model for learning natural scene categories. Proc. IEEE Comp. Vis. Patt. Recogn., 2:524-531.
  4. Greene, M. and Oliva, A. (2009). The briefest of glances: the time course of natural scene understanding. Cognitive Psychology, 20(4):137-179.
  5. Grossberg, S. and Huang, T. (2009). Artscene: A neural system for natural scene classification. Journal of Vision, 9(4):1-19.
  6. Lowe, D. (2004). Distinctive image features from scaleinvariant keypoints. Int. J. Comp. Vision, 2(60):91- 110.
  7. Martins, J., Rodrigues, J., and du Buf, J. (2009). Focus of attention and region segregation by low-level geometry. Proc. Int. Conf. on Computer Vision Theory and Applications, Lisbon, Portugal, Feb. 5-8, 2:267-272.
  8. Oliva, A. and Torralba, A. (2001). Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. of Computer Vision, 42(3):145175.
  9. Oliva, A. and Torralba, A. (2006). Building the gist of a scene: the role of global image features in recognition. Progress in Brain Res.: Visual Perception, 155:23-26.
  10. Rodrigues, J. and du Buf, J. (2006). Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection. BioSystems, 2:75- 90.
  11. Rodrigues, J. and du Buf, J. (2009a). A cortical framework for invariant object categorization and recognition. Cognitive Processing, 10(3):243-261.
  12. Rodrigues, J. and du Buf, J. (2009b). Multi-scale lines and edges in v1 and beyond: brightness, object categorization and recognition, and consciousness. BioSystems, 95:206-226.
  13. Ross, M. and Oliva, A. (2010). Estimating perception of scene layout properties from global image features. Journal of Vision, 10(1):1-25.
  14. Tailor, D., Finkel, L., and Buchsbaum, G. (2000). Coloropponent receptive fields derived from independent component analysis of natural images. Vision Research, 40(19):2671-2676.
  15. Vogel, J., Schwaninger, A., Wallraven, C., and Bülthoff, H. (2006). Categorization of natural scenes: Local vs. global information. Proc. 3rd Symp. on Applied Perception in Graphics and Visualization, 153:33-40.
  16. Vogel, J., Schwaninger, A., Wallraven, C., and Bülthoff, H. (2007). Categorization of natural scenes: Local versus global information and the role of color. ACM Trans. Appl. Perception, 4(3):1-21.
  17. Xiao, J., Hayes, J., Ehinger, K., Oliva, A., and Torralba, A. (2010). Sun database: Large-scale scene recognition from abbey to zoo. Proc. 23rd IEEE Conf. on Computer Vision and Pattern Recognition, San Francisco, USA, pages 3485 - 3492.
Download


Paper Citation


in Harvard Style

M. F. Rodrigues J. and M. H. du Buf J. (2011). A CORTICAL FRAMEWORK FOR SCENE CATEGORISATION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011) ISBN 978-989-8425-47-8, pages 364-371. DOI: 10.5220/0003368603640371


in Bibtex Style

@conference{visapp11,
author={J. M. F. Rodrigues and J. M. H. du Buf},
title={A CORTICAL FRAMEWORK FOR SCENE CATEGORISATION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)},
year={2011},
pages={364-371},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003368603640371},
isbn={978-989-8425-47-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)
TI - A CORTICAL FRAMEWORK FOR SCENE CATEGORISATION
SN - 978-989-8425-47-8
AU - M. F. Rodrigues J.
AU - M. H. du Buf J.
PY - 2011
SP - 364
EP - 371
DO - 10.5220/0003368603640371