Potts MFT neural networks for recognition of partially occluded shapes

In this paper, learning schemes are presented to optimally map the homomorphic graph matching problem onto the Potts mean field theory (MFT) neural networks. The computation of the weighting factors used in the compatibility measure equation is formulated as an optimization problem and solved using...

Full description

Saved in:
Bibliographic Details
Published inProceedings of IECON '95 - 21st Annual Conference on IEEE Industrial Electronics Vol. 2; pp. 1417 - 1421 vol.2
Main Authors Suganthan, P.N., Teoh, E.K., Mital, D.P.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1995
Subjects
Clustering algorithms
Constraint optimization
Equations
Layout
Neural networks
Object recognition
Power engineering computing
Quadratic programming
Robustness
Shape
Online AccessGet full text

Cover

More Information
Summary:In this paper, learning schemes are presented to optimally map the homomorphic graph matching problem onto the Potts mean field theory (MFT) neural networks. The computation of the weighting factors used in the compatibility measure equation is formulated as an optimization problem and solved using the quadratic programming procedure based learning algorithm. The formulation implicitly evaluates ambiguity, robustness and discriminatory power of the relational attributes chosen for graph matching and assigns weighting factors appropriately to these relational attributes. Further, the tolerance and steepness parameters are also learnt. These learning schemes also enable the construction of augmented weighted model attributed relational graphs (WARG). The proposed parameter learning schemes are employed to solve the silhouette objects recognition problem and the necessity for such learning schemes is also demonstrated.
ISBN:0780330269
9780780330269
DOI:10.1109/IECON.1995.484158