Compression based class-specific target recognition using SAR images

摘要: Recognizing complex targets with unknown pose and scale remains an unsolved problem even after half a century of research in the field synthetic aperture radar (SAR) based automatic target recognition (ATR). Feature extraction high-dimension feature vectors are two major issues ATR. Class-specific classification algorithms address dimensionality issue to some extent, but is such classifiers. Compression can be used extract features image for classification, has not been exploited much by ATR community. Using compression only avoids problems associated high-dimensional space also minimizes storage computational overheads. However, disadvantage using that performance suffers. The proposed technique, class-specific algorithm, modular classifier which uses circumvent at same time achieve optimal results.