Image Segmentation and Edge Detection Using a Neural Networks RBF Approach

The system consist of a multilayer perceptron (MLP)-like network that performs image segmentation by RBF technique of the input image using labels automatically pre-selected by a fuzzy clustering technique. The proposed architecture is feedforward, the learning is unsupervised. The proposed system is capable to perform automatic multilevel segmentation of images, based solely on information contained by the image itself. No a priori assumptions whatsoever are made about the image (type, features, contents, stochastic model, etc.). The proposed system can be readily employed, “as is,” or as a basic building block by a more sophisticated and/or application-specific image segmentation algorithm. Keyword — Image segmentation, Multilayer perceptron, unsupervised, Fuzzy clustering.