Morphological Shared-Weight Probabilistic Neural Networks for Pattern Classification of SAR Images

In this paper we describe the application of morphological shared-weight probabilistic neural networks to the problems of pattern classification in synthetic aperture radar (SAR) images. The feature extraction process is learned by interaction with the classification process. Feature extraction is performed using gray-scale hit-miss transforms that are independent of gray-level shifts. The classification process is performed by probabilistic neural networks(PNN). Classification experiments were carried out with SAR images of military objects. And classification results show MSPNN architecture to optimize object recognition versus processing time and veracity.