Authors:
Meriem Timouyas
1
;
Souad Eddarouich
2
and
Ahmed Hammouch
1
Affiliations:
1
Mohammed 5 University, Morocco
;
2
Regional Educational Center, Morocco
Keyword(s):
Probability Density Function, Competitive Neural Networks, Mahalanobis Distance, Competitive Hebbian Learning, Topology Preserving Feature, K-means, Segmentation, Competitive Concept, Thresholding.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Enterprise Information Systems
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Methodologies and Methods
;
Neural Network Software and Applications
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Theory and Methods
Abstract:
This paper proposes a new unsupervised color image segmentation procedure based on the competitive concept, divided into three processing stages. It begins by the estimation of the probability density function, followed by a training competitive neural network with Mahalanobis distance as an activation function. This stage allows detecting the local maxima of the pdf. After that, we use the Competitive Hebbian Learning to analyze the connectivity between the detected maxima of the pdf upon Mahalanobis distance. The so detected groups of Maxima are then used for the segmentation. Compared to the K-means clustering or to the clustering approaches based on the different competitive learning schemes, the proposed approach has proven, under a real and synthetic test images, that does not pass by any thresholding and does not require any prior information on the number of classes nor on the structure of their distributions in the dataset.