Feature extraction from multispectral digital images using artificial neural networks and Bayesian classifier

An attempt is made to explore the possibility of automated image classification using an artificial neural network (ANN) and a Bayesian classifier. Computational intricacies of both are discussed. The utility of ANN in case of a large data set and efficiency in reducing the misclassification have been investigated. The result of both the approach on a common data set has been compared.<
>