Human-Like Selective Attention Model with Reinforcement and Inhibition Mechanism

  • Sang-Bok Choi
  • Sang-Woo Ban
  • Minho Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3316)

Abstract

In this paper, we propose a trainable selective attention model that can not only inhibit an unwanted salient area but also reinforce an interesting area. The proposed model was implemented by the bottom-up saliency map model in conjunction with the top-down attention mechanism. The bottom-up saliency map model generates a salient area, and human supervisor decides whether the selected salient area is inhibited or reinforced. The fuzzy adaptive resonance theory (Fuzzy-ART) network can generate an inhibit signal or a reinforcement signal so that the sequence of attention areas is modified to be a desired scan path. Computer simulation results show that the proposed model successfully generates the plausible scan path of salient region.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Patt. Anal. Mach. Intell. 20(11), 1254–1259 (1998)CrossRefGoogle Scholar
  2. 2.
    Koike, T., Saiki, J.: Stochastic guided search model for search asymmetries in visual search tasks. In: Bülthoff, H.H., Lee, S.-W., Poggio, T.A., Wallraven, C. (eds.) BMCV 2002. LNCS, vol. 2525, pp. 408–417. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  3. 3.
    Sun, Y., Fisher, R.B.: Hierarchical selectivity for object-based visual attention. In: Bülthoff, H.H., Lee, S.-W., Poggio, T.A., Wallraven, C. (eds.) BMCV 2002. LNCS, vol. 2525, pp. 427–438. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  4. 4.
    Bruce Goldstein, E.: Sensation and Perception, 4th edn. An international Thomson publishing company, USA (1995)Google Scholar
  5. 5.
    Park, S.J., An, K.H., Lee, M.: Saliency map model with adaptive masking based on independent component analysis. Neurocomputing 49, 417–422 (2002)CrossRefGoogle Scholar
  6. 6.
    Seo, K.S., Park, C.J., Cho, S.H., Choi, H.M.: Context-Free Marker-Controlled Watershed Transform for Efficient Multi-Object Detection and Segmentation. IEICE Trans. E84- A(6), 1066–1074 (2001)Google Scholar
  7. 7.
    Bell, A.J., Sejnowski, T.J.: The independent components of natural scenes are edge filters. Vision Research 37, 3327–3338 (1997)CrossRefGoogle Scholar
  8. 8.
    Barlow, H.B., Tolhust, D.J.: Why do you have edge detectors? Optical society of America Technical Digest 23, 172 (1992)Google Scholar
  9. 9.
    Frank, T., Kraiss, K.F., Kuklen, T.: Comparative analysis of Fuzzy ART and ART-2A network clustering performance. IEEE Trans. Neural Networks 9(3), 544–559 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Sang-Bok Choi
    • 1
  • Sang-Woo Ban
    • 2
  • Minho Lee
    • 2
  1. 1.Dept. of Sensor EngineeringKyungpook National UniversityTaeguKorea
  2. 2.School of Electronic and Electrical EngineeringKyungpook National UniversityTaeguKorea

Personalised recommendations