Application of hopfield neural networks in target recognition through mathematical morphology

In this paper an enhancement in target recognition in remote sensing applications using artificial neural network is described. It is proposed how, by using a Hopfield neural network (HNN), more accurate measures of land targets can be obtained compared with those determined using the proportion image processing alone. It is based on applying mathematical morphology to extract the candidate objects followed by implementing the HNN on extracted features to recognize the object using stored templates. Results suggest that HNN is a useful tool for target recognition from remotely sensed imagery.