We develop a two-stage, modular neural network classifier and apply it to an automatic target recognition problem. The data are features extracted from infrared and TV images. We discuss the problem of robust classification in terms of a family of decision surfaces, the members of which are functions of a set of global variables. The global variables characterize how the feature space changes from one image to the next. We obtain rapid training times and robust classification with this modular neural network approach.
We describe a one-class classification approach to an automatic target detection problem, which involves distinguishing targets from clutter in diverse environments. We use only target statistics to construct the classifier. The classifier combines conventional and neural network methods. The classifier is a Parzen estimator, which requires storage and recall of all training points. To reduce the size of the training set, we apply two neural network learning algorithms: ( I ) we use a backpropagation network to approximate the Parzen estimator; (2) we apply the infomax learning principle to compress the size of the training set before constructing the Parzen estimator. We find that the results obtained with the infomax scheme approach those obtained with Parzen alone and are better than those obtained with backpropagation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.