LEARNING TEXTURE-DISCRIMINATION RULES IN A MULTIRESOLUTION SYSTEM

We describe a texture analysis system in which informative discriminat ion rules are learned from a multiresolution representation of the tex tured input. The system incorporates unsupervised and supervised learn ing via statistical machine learning and rule-based neural networks, r espectively. The textured input is represented in the frequency-orient ation space via a log-Gabor pyramidal decomposition. In the unsupervis ed learning stage a statistical clustering scheme is used for the quan tization of the feature-vector attributes. A supervised stage follows in which labeling of the textured map is achieved using a rule-based n etwork. Simulation results for the texture classification task are giv en. An application of the system to real-world problems is demonstrate d.