Pattern recognition using multilayer neural-genetic algorithm

The genetic algorithm implemented with neural network to determine automatically the suitable network architecture and the set of parameters from a restricted region of space. The multilayer neural-genetic algorithm was applied in image processing for pattern recognition, and to determine the object...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 2003-04, Vol.51, p.237-247
Main Authors: Alsultanny, Yas Abbas, Aqel, Musbah M.
Format: Article
Language:English
Subjects:
Genetic algorithm
Image processing
Neural network
Pattern recognition
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:The genetic algorithm implemented with neural network to determine automatically the suitable network architecture and the set of parameters from a restricted region of space. The multilayer neural-genetic algorithm was applied in image processing for pattern recognition, and to determine the object orientation. The library to cover the views of object was build from real images of (10×10) pixels. Which is the smallest image size can be used in this algorithm to recognize the type of aircraft with its direction The multilayer perecptron neural network integrated with the genetic algorithm, the result showed good optimization, by reducing the number of hidden nodes required to train the neural network (the number of epoch's reduced to less than 50%). One of the important results of the implemented algorithm is the reduction in the time required to train the neural network.
ISSN:0925-2312
1872-8286
DOI:10.1016/S0925-2312(02)00619-7