FOCUS OF ATTENTION AND REGION SEGREGATION BY LOW-LEVEL GEOMETRY

J. A. Martins, J. A. Rodrigues, J. M. H. du Buf

Abstract

Research has shown that regions with conspicuous colours are very effective in attracting attention, and that regions with different textures also play an important role. We present a biologically plausible model to obtain a saliency map for Focus-of-Attention (FoA), based on colour and texture boundaries. By applying grouping cells which are devoted to low-level geometry, boundary information can be completed such that segregated regions are obtained. Furthermore, we show that low-level geometry, in addition to rendering filled regions, provides important local cues like corners, bars and blobs for region categorisation. The integration of FoA, region segregation and categorisation is important for developing fast gist vision, i.e., which types of objects are about where in a scene.

References

  1. Bar M., et al. (2006). Top-down facilitation of visual recognition. PNAS, 103(2):449-454.
  2. du Buf, J. (2007). Improved grating and bar cell models in cortical area V1 and texture coding. Image and Vision Computing, 25(6):873-882.
  3. Elazary, L. and Itti, L. (2008). Interesting objects are visually salient. Journal of Vision, 8(3):1-15.
  4. Finlayson, G., Schiele, B., and Crowley, J. (1998). Comprehensive colour image normalization. Proc. 5th Europ. Conf. Comp. Vision, I:475-490.
  5. Hubel, D. (1995). Eye, brain and vision. Scientific American Library.
  6. Itti, L. and Koch, C. (2001). Computational modeling of visual attention. Nature Reviews: Neuroscience, 2(3):194-203.
  7. Niebur, E. and Koch, C. (1996). Control of selective visual attention: Modeling the 'where' pathway. Neural Information Processing Systems, 8:802-808.
  8. Rensink, R. (2000). The dynamic representation of scenes. Visual Cogn., 7(1-3):17-42.
  9. Rodrigues, J. and du Buf, J. (2004). Visual cortex frontend: integrating lines, edges, keypoints and disparity. Proc. Int. Conf. Image Anal. Recogn., Springer LNCS 3211(1):664-671.
  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. (2007). Invariant multiscale object categorisation and recognition. Proc. 3rd Iberian Conf. on Patt. Recogn. and Image Anal., Springer LNCS 4477:459-466.
  12. van de Weijer, J., Gevers, T., and Bagdanov, A. D. (2006). Boosting color saliency in image feature detection. IEEE Tr. PAMI, 28(1):150-156.
Download


Paper Citation


in Harvard Style

A. Martins J., A. Rodrigues J. and M. H. du Buf J. (2009). FOCUS OF ATTENTION AND REGION SEGREGATION BY LOW-LEVEL GEOMETRY . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 267-272. DOI: 10.5220/0001768502670272


in Bibtex Style

@conference{visapp09,
author={J. A. Martins and J. A. Rodrigues and J. M. H. du Buf},
title={FOCUS OF ATTENTION AND REGION SEGREGATION BY LOW-LEVEL GEOMETRY},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={267-272},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001768502670272},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)
TI - FOCUS OF ATTENTION AND REGION SEGREGATION BY LOW-LEVEL GEOMETRY
SN - 978-989-8111-69-2
AU - A. Martins J.
AU - A. Rodrigues J.
AU - M. H. du Buf J.
PY - 2009
SP - 267
EP - 272
DO - 10.5220/0001768502670272