Polygonal approximation using a competitive Hopfield neural network

Polygonal approximation plays an important role in pattern recognition and computer vision. In this paper, a parallel method using a Competitive Hopfield Neural Network (CHNN) is proposed for polygonal approximation. Based on the CHNN, the polygonal approximation is regarded as a minimization of a c...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition 1994-11, Vol.27 (11), p.1505-1512
Main Authors: Chung, Pau-Choo, Tsai, Ching-Tsorng, Chen, E-Liang, Sun, Yung-Nien
Format: Article
Language:English
Subjects:
Competitive Hopfield neural network
Hopfield network
Parallel image processing
Polygonal approximation
Winner-take-all
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Polygonal approximation plays an important role in pattern recognition and computer vision. In this paper, a parallel method using a Competitive Hopfield Neural Network (CHNN) is proposed for polygonal approximation. Based on the CHNN, the polygonal approximation is regarded as a minimization of a criterion function which is defined as the arc-to-chord deviation between the curve and the polygon. The CHNN differs from the original Hopfield network in that a competitive winner-take-all mechanism is imposed. The winner-take-all mechanism adeptly precludes the necessity of determining the values for the weighting factors in the energy function in maintaining a feasible result. The proposed method is compared to several existing methods by the approximation error norms L 2 and L ∞ with the result that promising approximation polygons are obtained.
ISSN:0031-3203
1873-5142
DOI:10.1016/0031-3203(94)90128-7