CFP last date
20 May 2024
Call for Paper
June Edition
IJCA solicits high quality original research papers for the upcoming June edition of the journal. The last date of research paper submission is 20 May 2024

Submit your paper
Know more
The week's pick
Responsive image
Enhancing Privacy Preservation: Multi-Attribute Protection with P-Sensitive K-Anonymity

Twinkle Patel Kiran Amin
Random Articles
Reseach Article

Simulating and Analyzing IF and LIF Neuron Models for Selective Visual Attention

by Anu Yadav, Sanjeev Kumar Yadav
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 125 - Number 11
Year of Publication: 2015
Authors: Anu Yadav, Sanjeev Kumar Yadav
10.5120/ijca2015906139

Anu Yadav, Sanjeev Kumar Yadav . Simulating and Analyzing IF and LIF Neuron Models for Selective Visual Attention. International Journal of Computer Applications. 125, 11 ( September 2015), 23-27. DOI=10.5120/ijca2015906139

@article{ 10.5120/ijca2015906139,
author = { Anu Yadav, Sanjeev Kumar Yadav },
title = { Simulating and Analyzing IF and LIF Neuron Models for Selective Visual Attention },
journal = { International Journal of Computer Applications },
issue_date = { September 2015 },
volume = { 125 },
number = { 11 },
month = { September },
year = { 2015 },
issn = { 0975-8887 },
pages = { 23-27 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume125/number11/22476-2015906139/ },
doi = { 10.5120/ijca2015906139 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T23:15:46.662265+05:30
%A Anu Yadav
%A Sanjeev Kumar Yadav
%T Simulating and Analyzing IF and LIF Neuron Models for Selective Visual Attention
%J International Journal of Computer Applications
%@ 0975-8887
%V 125
%N 11
%P 23-27
%D 2015
%I Foundation of Computer Science (FCS), NY, USA
Abstract

By nature biological systems have the capacity to selectively guide their attention on some portion of visual scene and process only that selected information for further processing. The similar abilities are also required in artificial vision systems so that they can become more efficient and realistic as biological systems and in future manual supervisory and detection work can be replaced by artificial visual systems. In this paper concepts of visual information processing and selective visual attention are implemented and analyzed. The results from two neuron models viz. IF and LIF models are compared and an analysis is made. In visual selective attention model the attention is guided towards only the most salient object while ignoring the less salient objects this way the time taken to process the image is reduced as large amount of information which is not much relevant is rejected for further processing. The study made in this paper will be proving to very effective as it will enhance the reliability of the system. The visual system can be used in robot vision system, can be deployed in choke points of city and major functions to detect accidents etc. This concept is also useful in marketing to make a few second advertisements more effective.

References
  1. Alwyn Scott, Neuroscience, A Mathematical Primer, Springer- Verlag New York, 2002.
  2. Becker S., Modelling the Mind: From Circuits to Systems, Chapter 2 in New Directions in Statistical Signal Processing: From Systems to brain, Haykin S. et.al. MIT Press, 2005.
  3. Carrasco M, “Visual attention: The past 25 years, vision research 51”, Elsevier Ltd.,2011, pp. 1484-1525.
  4. Chen D and Chu H, “Scale invariant amplitude spectrum modulation for visual saliency detection”, IEEE Transactions on Neural Networks and Learning Systems, Vol 23, No. 8, 2012, pp. 1206-1214.
  5. Itti L and Koch C, “Computational Modeling of Visual Attention”, Macmillan Magazines Ltd., Vol. 2, 2001, pp. 194-203.
  6. Kastner S and Ungerleider L G, “Mechanisms of visual attention in the human cortex”, Annual Review of Neuroscience, Vol 23, 2000, pp. 315-341.
  7. Neokleous K C and Schizas C N, “Computational modeling of visual selective attention”, In Proceedings of the European Future Technologies Conference and Exhibition, 2011, pp. 244-245.
  8. Niebur E. and Koch C., “A Model for the neuronal implementation of selective visual attention based on temporal correlation among neurons”, Journal of Computational Neuroscience 1, pp. 141-158, 1994.
  9. Quiles M. G., Zhao L., Breve F.A. and Romero R. A. F., “A network of integrate and fire neurons for visual selection”, Elsevier journal, Neurocomputing 72, 2009, pp. 2198-2208.
  10. Salinas E and Sejnowski T J, “Integrate and fire neuron driven by correlated stochastic input”, Neural Computation, Vol.14, 2002, pp. 2111-2155.
  11. Tsotsos J K, Culhane S M, Wai W Y K, Lai Y, Davis N and Nuflo F, “Modeling visuall attention via selective tuning”, Artificial Intelligence, Vol 78, 1995, pp. 507-545.
  12. Tyagi A., Yadav A. and Kumar S., “Information processing in brain modeling: challenges and opportunities, IJCA, pp. 27-31, 2014.
  13. Vikram T N, Tscherepanow M and Wrede B, “Impact of real time visual attention on computer vision products and cognitive robotics”, In Proceedings of the European Future Technologies Conference and Exhibition, 2011, pp. 332-333.
  14. Walther D, Rutishauser U, Koch C and Perona P, “selective visual attention enables learning and recognition of multiple objects in cluttered scenes”, computer vision and image understanding, 2005, pp. 41-63
  15. Burkitt A N, “A Review of the integrate and fire neuron model: homogeneous synaptic input”, biological cybernetics, 2006, DOI 10.1007/s00422-006-0068-6.
  16. Giraudo M T and Sacerdote L, “Simulation methods in neuronal modelling”, 1998, pp. 77-83.
  17. Sun Y and Fisher R, “Object-based visual attention for computer vision”, Artificial intelligence, pp. 77-123.
Index Terms

Computer Science
Information Sciences

Keywords

IF-integrate and fire model LIF-leaky integrate and fire model Selective visual attention salient objects robot vision system supervisory and detection work

Powered by PhDFocusTM