A NONLINEAR FEATURE FUSION BY VARIADIC NEURAL NETWORK IN SALIENCY-BASED VISUAL ATTENTION

Zahra Kouchaki, Ali Motie Nasrabadi

Abstract

This study presents a novel combinational visual attention system which applies both bottom-up and top-down information. This can be employed in further processing such as object detection and recognition purpose. This biologically-plausible model uses nonlinear fusion of feature maps instead of simple superposition by employing a specific Artificial Neural Network (ANN) as combination operator. After extracting 42 feature maps by Itti’s model, they are weighed purposefully through several training images with their corresponding target masks to highlight the target in the final saliency map. In fact, the weights of 42 feature maps are proportional to their influence on finding target in the final saliency map. The lack of bottom-up information is compensated by applying top-down information with available target masks. Our model could automatically detect the conceptual features of desired object only by considering the target information. We have tried to model the process of combining 42 feature maps to form saliency map by applying the neural network which resembles biological neural network. The Experimental results and comparing our model with the basic saliency model using 32 images of test dataset indicate a noticeable improvement in finding target in the first hit.

References

  1. Bahmani, H., Nasrabadi, A. M., and Hashemi Gholpayegani, M. R. (2008). Nonlinear data fusion in saliency-based visual attention, 4th International IEEE Conference in Intelligent System.
  2. Frintrop, S. (2006). VOCUS: A Visual Attention System for Object Detection and Goal-directed Search, LNAI, 3899, Springer Berlin/Heidelberg. ISBN: 3-540- 32759-2.
  3. Itti, L. and Koch, C. (2001). Computational modeling of visual attention, Nature Reviews Neuroscience, 2(3), 194-203.
  4. Itti, L., Koch, C., and Niebur, E. (1998). A model of saliency-based visual attention for rapid scene analysis, IEEE Trans PAMI, 20(11), 1254-1259.
  5. Itti, L., and Koch, C. (2001). Feature combination strategies for saliency-based visual attention systems, Journal of Electronic Imaging, 10(1), 161-169.
  6. Kouchaki, Z., Nasrabadi, A. M., Maghooli, K. (2011). An improved model of saliency-based visual attention using fuzzy interface system, The 6th International conference on computer science and convergence information technology, 204-207.
  7. McGregor, S. (2007). Neural network processing for multi set data”. In Proc. Artificial neural networks - ICANN2007, 17th international conference, 4668, 460-470.
  8. Navalpakam, V., Rebesco, J. and Itti, L. (2005). Modeling the influence of task on attention, Vision Research, 45(2), 205-231.
  9. Riedmiller M. and Braun, H. (1992). RPROP - A fast adaptive learning algorithm, technical report, Universitat Karlsruhe.
  10. Sun, Y. and Fisher, R. (2003). Object-based visual attention for computer vision, Artificial Intelligence, 146(1), 77-123.
  11. Treisman, A. M. and Gelade, G. A. (1980). A feature integration theory of attention, Cognitive Psychology, 12, 97-136.
  12. Wolfe, J. (1994). A revised model of visual search, Psyconomic Bulletin Review, 1(2), 202-238.
  13. Walter, D. Itti, L., Riesenhuber, M., Poggio T., and koch, C. (2002). Attentional selection for object recognitionA gentle way, LNCS, 25, 472-279
  14. Walther, D. (2006). Interactions of visual attention and object recognition, PhD Thesis, California Institute of Technology.
Download


Paper Citation


in Harvard Style

Kouchaki Z. and Motie Nasrabadi A. (2012). A NONLINEAR FEATURE FUSION BY VARIADIC NEURAL NETWORK IN SALIENCY-BASED VISUAL ATTENTION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 457-461. DOI: 10.5220/0003859204570461


in Bibtex Style

@conference{visapp12,
author={Zahra Kouchaki and Ali Motie Nasrabadi},
title={A NONLINEAR FEATURE FUSION BY VARIADIC NEURAL NETWORK IN SALIENCY-BASED VISUAL ATTENTION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={457-461},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003859204570461},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - A NONLINEAR FEATURE FUSION BY VARIADIC NEURAL NETWORK IN SALIENCY-BASED VISUAL ATTENTION
SN - 978-989-8565-03-7
AU - Kouchaki Z.
AU - Motie Nasrabadi A.
PY - 2012
SP - 457
EP - 461
DO - 10.5220/0003859204570461