Recent progress in supervised image classification research, has demonstrated the potential usefulness of incorporating fuzziness in the training, allocation and testing stages of several classification techniques. In this paper a multiresolu tion neural network approach to supervised classification is presented, exploiting the inherent fuzziness of such tech niques in order to perform classification at different resolution levels and gain in computational complexity. In par ticular, multiresolution image analysis is carried out and hierarchical neural networks are used as an efficient archi tecture for classification of the derived multiresolution image representations. A new scheme is th
13th International Conference on Digital Signal Processing, Santorini, Greece, July 1997.
[ Bibtex ] [ PDF ]