Advertisement

Emergence of Attention Focus in a Biologically-Based Bidirectionally-Connected Hierarchical Network

  • Mohammad Saifullah
  • Rita Kovordányi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6593)

Abstract

We present a computational model for visual processing where attentional focus emerges fundamental mechanisms inherent to human vision. Through detailed analysis of activation development in the network we demonstrate how normal interaction between top-down and bottom-up processing and intrinsic mutual competition within processing units can give rise to attentional focus. The model includes both spatial and object-based attention, which are computed simultaneously, and can mutually reinforce each other. We show how a non-salient location and a corresponding non-salient feature set that are at first weakly activated by visual input can be reinforced by top-down feedback signals (centrally controlled attention), and instigate a change in attentional focus to the weak object. One application of this model is highlight a task-relevant object in a cluttered visual environment, even when this object is non-salient (non-conspicuous).

Keywords

Spatial attention Object-based attention Biased competition Recurrent bidirectionally connected networks 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lee, S., Kim, K., Kim, J., Kim, M., Yoo, H.: Familiarity based unified visual attention model for fast and robust object recognition. Pattern Recognition 43, 1116–1128 (2010)CrossRefzbMATHGoogle Scholar
  2. 2.
    Poggio, T., Serre, T., Tan, C., Chikkerur, S.: An integrated model of visual attention using shape-based features. MIT-CSAIL-TR-2009-029 (2009)Google Scholar
  3. 3.
    Navalpakkam, V., Itti, L.: Modeling the influence of task on attention. Vision Research 45, 205–231 (2005)CrossRefGoogle Scholar
  4. 4.
    Duncan, J.: Converging levels of analysis in the cognitive neuroscience of visual attention. Philosophical Transactions of the Royal Society B: Biological Sciences 353, 1307–1317 (1998)CrossRefGoogle Scholar
  5. 5.
    O’Reilly, R.C., Munakata, Y.: Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain. MIT Press, Cambridge (2000)Google Scholar
  6. 6.
    O’Reilly, R.C.: Six principles for biologically based computational models of cortical cognition. Trends in Cognitive Sciences 2, 455–462 (1998)CrossRefGoogle Scholar
  7. 7.
    Behrmann, M., Zemel, R., Mozer, M.: Object-Based Attention and Occlusion: Evidence from Normal Participants and a Computational Model. Journal of Experimental Psychology: Human Perception and Performance 24, 1011–1036 (1998)Google Scholar
  8. 8.
    Phaf, R., Van der Heijden, A., Hudson, P.: SLAM: A connectionist model for attention in visual selection tasks. Cognitive Psychology 22, 273–341 (1990)CrossRefGoogle Scholar
  9. 9.
    Hamker, F.H.: The emergence of attention by population-based inference and its role in distributed processing and cognitive control of vision. Computer Vision and Image Understanding 100, 64–106 (2005)CrossRefGoogle Scholar
  10. 10.
    Rothenstein, A.L., Rodríguez-Sánchez, A.J., Simine, E., Tsotsos, J.K.: Visual feature binding within the selective tuning attention framework. International Journal of Pattern Recognition and Artificial Intelligence 22, 861 (2008)CrossRefGoogle Scholar
  11. 11.
    Sun, Y., Fisher, R., Wang, F., Gomes, H.: A computer vision model for visual-object-based attention and eye movements. Computer Vision and Image Understanding 112, 126–142 (2008)CrossRefGoogle Scholar
  12. 12.
    Aisa, B., Mingus, B., O’Reilly, R.: The emergent neural modeling system. Neural Networks: The Official Journal of the International Neural Network Society 21, 1146–1152 (2008)CrossRefGoogle Scholar
  13. 13.
    Kovordányi, R., Roy, C.: Cyclone track forecasting based on satellite images using artificial neural networks. ISPRS Journal of Photogrammetry and Remote Sensing 64, 513–521 (2009)CrossRefGoogle Scholar
  14. 14.
    Kovordanyi, R., Saifullah, M., Roy, C.: Local feature extraction — What receptive field size should be used? In: Presented at the International Conference on Image Processing, Computer Vision and Pattern Recognition, Las Vegas, USA (2009) Google Scholar
  15. 15.
    Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: IEEE. CVPR 2004. Workshop on Generative-Model Based Vision (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mohammad Saifullah
    • 1
  • Rita Kovordányi
    • 1
  1. 1.Department of Information and Computer ScienceLinköping UniversityLinköpingSweden

Personalised recommendations