Journals IEEE Transactions on Neural Networks
Name
IEEE Transactions on Neural Networks
Subjects
Fuzzy neural networks
Neural networks
Subspace constraints
Gray-scale
Fractals
Resonance
Nearest neighbor searches
Testing
Phase noise
Image segmentation
Neural networks
Subspace constraints
Gray-scale
Fractals
Resonance
Nearest neighbor searches
Testing
Phase noise
Image segmentation
ISSN
1941-0093
Description
This paper describes an approach to classification of noisy signals using a technique based on the fuzzy ARTMAP neural network (FAMNN). The proposed method is a modification of the testing phase of the fuzzy ARTMAP that exhibits superior generalization performance compared to the generalization performance of the standard fuzzy ARTMAP in the presence of noise. An application to textured grayscale image segmentation is presented. The superiority of the proposed modification over the standard fuzzy ARTMAP is established by a number of experiments using various texture sets, feature vectors and noise types. The texture sets include various aerial photos and also samples obtained from the Brodatz album. Furthermore, the classification performance of the standard and the modified fuzzy ARTMAP is compared for different network sizes. Classification results that illustrate the performance of the modified algorithm and the FAMNN are presented.
Impact Factor (2 years)
2.633
Publisher
IEEE
Journal Webpage
Journal type
Subscription Journal