Neural techniques for image segmentation

In this work we present new neural techniques including unsupervised technology and Fuzzy Logic foundations. We realized a hybrid neural network and we applied three different unsupervised learning algorithms that we made specially for it: Fuzzy MLSOM, Fuzzy Hierarchical "Neural Gas" and Fuzzy Hierarchical "Maximum Entropy"The experiments here presented are on image segmentation. The results are very interesting: they show that neural networks are a valid instrument for image processing and shape recognition.