A computational framework for analyzing textured image classification

A computational framework for analyzing textured image classification is presented. Parallel and distributed processing is the major element of this framework. The framework is developed by introducing computational constraints namely image representation, algorithms and strategies for texture feature extraction and classification, and fault tolerant behavior of the classifier. An illustration of an application of this framework for analyzing a textured image classification system is presented. Parallel distributed representations in hypercube multicomputer networks are discussed and a method for analyzing its performance is presented. The transputer computational structures in hypercube configurations are used for feature extraction. The networks are analyzed and a performance evaluation is done. The discriminatory power of a neural network is used for classification. It is shown that this framework is useful in analyzing and simplifying computationally intensive and complex image classification procedures. Efficient and optimal classification systems for real-time applications can be designed with this framework.