Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Digital Image Processing
Entropic Estimation of Noise for Medical Volume Restoration
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
A clustering-based fuzzy classifier
Proceedings of the 2005 conference on Artificial Intelligence Research and Development
Image Restoration with Operators Modeled by Artificial Neural Networks
SIBGRAPI '09 Proceedings of the 2009 XXII Brazilian Symposium on Computer Graphics and Image Processing
Genetic-based fuzzy image filter and its application to image processing
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hi-index | 0.00 |
This work aims at improving the performance of a supervised fuzzy classifier on noisy MRI images, by first restoring the image. The image restoration is performed here through the application of the well-known Wiener filter and of a novel ANN multiscale image restoration technique. The paper focuses on the changes in the feature space resulting from the restoration process. The tests were carried out on MRI brain images containing multiple sclerosis lesions: a synthetic image and a real one from a patient diagnosed with the disease. It was observed that the restoration process led to a compact feature space and a better kappa performance classification index, for the real MRI image and for the synthetic one when subjected to high levels of artificially added noise.