Research on image super-resolution reconstruction based on sparse representation

Constructing an appropriate over-complete dictionary is the key problem of super-resolution reconstruction based on sparse representation. First, according to the maximum likelihood estimation principle, an isomorphic over-complete dictionary learning model based on mixture of Gauss is proposed. The model is described by the weight l₂ norm and the weight matrix is designed by the residual. And the isomorphic coupled dictionary learning problem is translated into the single dictionary learning problem. Then, the dictionary is learned by the alternate and iterative strategy using sparse coding and dictionary updating. Finally, the dictionary is utilized in the process of super-resolution reconstruction. The experimental results test the effectiveness of the algorithm.