Multi-polarimetric SAR image compression based on sparse representation and super-resolution

The use of sparse representations in signal and image processing is gradually increasing in the past several years. Considering the relativity among the multi-polarimetric SAR images, a new compression scheme for multi-polarimetric SAR image based sparse representation and super-resolution is proposed. Multilevel dictionary is learned iteratively in the 9/7 wavelet domain using one channel SAR image, and the other channels are compressed by down-sampling followed with sparse representation scheme. The super-resolution algorithm is used to restore the high frequency information removed during the down-sampling process. Experimental results are compared with state-of-the-art compression methods JPEG2000, and our method performs well in terms of both subjective quality and edge preservation.