Based on the current mainstream algorithms, an effective super-resolution algorithm via sparse representation for MODIS remote sensing images is proposed in the paper. The basic idea behind the proposed algorithm is to obtain the redundant dictionaries deriving from high-resolution Landsat ETM+ images and low-resolution MODIS images, further give the instruction for reconstructing high-resolution MODIS images. Feature extraction is one vital part included in the procedure of dictionary training. The features are extracted from the wavelet-domain images as training samples, and then more effective dictionaries for high-resolution image reconstruction are obtained by applying the k-singular value decomposition (K-SVD) dictionary training algorithm. The experimental results demonstrate the proposed algorithm improved the reconstruction quality both visually and quantitatively. Compared with the traditional algorithm, the PSNR value approximately increases by 1.1 dB and SSIM value increases by 0.07. Moreover, both the quality and computational efficiency of the proposed algorithm can be improved given the appropriate number of atoms.
In Super-Resolution, the combination technique of frequency domain and the improved keren's method has been applied
in the sub-pixel image registration. The method proved to be accurate in movement estimation within given precision,
but the registration accuracy was affected by the relative parameters. Based on the traditional method, an effective
method of image registration for Super-Resolution in the paper was proposed in the paper. The proposed registration
method has good performance by introducing the registration evaluation parameter. The experimental results
demonstrate that the proposed method is effective for different test images, which takes into account the precision of
estimation results and the computation efficiency as well.