loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
1995 International Conference on Image Processing (ICIP'95) - Volume 2
Figure-ground separation by a neural dynamical system
Washington D.C.
October 23-October 26
ISBN: 0-8186-7310-9
ASCII Text
x 
 
Jun Zhang, Jianhua Lin, "Figure-ground separation by a neural dynamical system," Image Processing, International Conference on, vol. 2, pp. 2615, 1995 International Conference on Image Processing (ICIP'95) - Volume 2, 1995.
 
 
BibTex
x
 
@article{ 10.1109/ICIP.1995.537554,
author = {Jun Zhang and Jianhua Lin},
title = {Figure-ground separation by a neural dynamical system},
journal ={Image Processing, International Conference on},
volume = {2},
year = {1995},
isbn = {0-8186-7310-9},
pages = {2615},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICIP.1995.537554},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Image Processing, International Conference on
TI - Figure-ground separation by a neural dynamical system
SN - 0-8186-7310-9
SP
EP
A1 - Jun Zhang,
A1 - Jianhua Lin,
PY - 1995
KW - object recognition; image recognition; nonlinear differential equations; visual perception; neural nets; figure-ground separation; neural dynamical system; neural network inspired dynamical system; perceptual grouping problem; nonlinear differential equation; steady state solution; neighbourhood couplings; spatial interactions; perceptual grouping; excitation; inhibition; dot grouping; synthetic images; real-world images
VL - 2
JA - Image Processing, International Conference on
ER -
 
Jun Zhang, Dept. of Electr. Eng. & Comput. Sci., Wisconsin Univ., Milwaukee, WI, USA
Jianhua Lin, Dept. of Electr. Eng. & Comput. Sci., Wisconsin Univ., Milwaukee, WI, USA
This paper describes a neural network inspired dynamical system approach to a perceptual grouping problem-figure-ground separation. In this approach, a non-linear differential equation is defined at each pixel site and coupled with those at its neighbours. The steady state solution would determine whether a pixel is part of a salient structure or background/noise. The neighbourhood couplings are used to achieve spatial interactions that are essential to perceptual grouping, such as excitation and inhibition. Experimental results on the grouping of dots in synthetic and real-world images demonstrate the efficacy of the proposed approach.
Index Terms:
object recognition; image recognition; nonlinear differential equations; visual perception; neural nets; figure-ground separation; neural dynamical system; neural network inspired dynamical system; perceptual grouping problem; nonlinear differential equation; steady state solution; neighbourhood couplings; spatial interactions; perceptual grouping; excitation; inhibition; dot grouping; synthetic images; real-world images
Citation:
Jun Zhang, Jianhua Lin, "Figure-ground separation by a neural dynamical system," icip, vol. 2, pp.2615, 1995 International Conference on Image Processing (ICIP'95) - Volume 2, 1995
Usage of this product signifies your acceptance of the Terms of Use.