SAR image compression based on sparse representation

The sparse representation based on over-complete dictionary is a new image representation theory. The redundancy of over-complete dictionary can make it effectively to capture the structural characteristics of the image. In this article, we realize SAR image compression based on sparse representation. We only need to store the coefficients of sparse decomposition and the corresponding indices in order to seize the image´s information. We adopt a learning method — K-SVD to construct the dictionary. Because the training examples are all from the image itself, the dictionary could be more approximative to the image´s structure. The simulation indicates the proposed method is useful for SAR image compression and it outperforms the DCT based JPEG method and the wavelet based EZW and SPIHT method.