Object-based SAR image compression using vector quantization

A simple and elegant algorithm is presented to encode images with rich cont ent, which allows easy access to various objects, An object-plane-based enc oding method for compression of synthetic aperture radar (SAR) imagery is d eveloped, with different object planes for target classes and background, A variable-rate residual vector quantization (VQ) algorithm is developed to encode the background information. This algorithm is very powerful as indic ated by the experimental results. The proposed coding scheme allows compres sion matched to the final application of the images, which in this case is target recognition and classification.