The invention provides a dictionary-type image super-resolution system and method based on iteration projection reconstruction. The system comprises a dictionary training and pre-calculation matrix prediction module, an iteration projection super-resolution reconstruction module based on a projection matrix and a post-processing module based on global restriction. The method comprises steps: firstly, dictionary learning and projection matrix calculation are carried out; secondly, iteration projection super-resolution reconstruction based on a projection matrix is carried out, namely, y is inputted into a low-resolution image block, an atom most similar to y is searched in a dictionary, y is subjected to super-resolution reconstruction by utilization f the projection matrix of the atom, the generated residual vector is subjected to projection reconstruction, high-resolution reconstruction of the residual vector is obtained, iteration reconstruction is carried out in the above way, finally all the reconstruction components are subjected to weighing addition and the sum is employed as the reconstruction result; thirdly, the reconstruction image is subjected to global restriction to eliminate the unnatural effect. The calculation speed of the dictionary-type method can be raised effectively and image high-frequency detail information can be recovered.