The present work is an attempt to measure the efficiency
of a region method in segmenting an image. To
accomplish our study, we conceive a new hybrid
clustering method which combines a neural network and a
genetic training, in order to realize a fuzzy learning, and
adapt a new tool for clustering called ACE (Alternating
Cluster Estimation). The ACE is a new clustering model
constituted of two update equations which, in contrast to
classical models, are user specified and are not necessary
relating to an objective function. The used neural network
is composed of five layers each one, except the first,
corresponds to a step of the fuzzy learning. The values
optimised by the genetic training algorithm are the weights
which represent the centres of membership functions
characterizing linguistic terms. System input and output
will be respectively, colorimetric components and cluster
centres. The HSV color space is used in order to, partly,
get rid of the RGB space correlation. The experimental
results obtained using the proposed method are
encouraging.
1st Mosharaka International Conference on Communications, Signals and Coding (MIC-CSC 2007)
Congress
2007 Global Congress on Communications, Signals and Coding (GC-CSC 2007), 7-9 June 2007, Amman, Jordan
Pages
18-23
Topics
Neural Networks Digital Image Processing
ISSN
2227-331X
DOI
BibTeX
@inproceedings{684CSC2007,
title={New Fuzzy Clustering Method Based on Neural Networks and Genetic Training, Application for Color Image Segmentation},
author={Fella Hachouf},
booktitle={2007 Global Congress on Communications, Signals and Coding (GC-CSC 2007)},
year={2007},
pages={18-23},
doi={}},
organization={Mosharaka for Research and Studies}
}