Abstract:

Proposed in this paper is a constrained stepwise magnification strategy for the super-resolution image reconstructionbased on the neighbor embedding,which is used to increase the neighborhood-preserving rate and improvethe reconstruction effect.Then,the iterative back-projection constraint is used to modify the magnified imagein each step,which decreases the errors that may occur during the learning procedure and makes the solution of eachstep evolve in a correct direction.Moreover,in order to take full advantage of the information of the test image,ajoint training set is constructed by concatenating the on-line training set learned from the test image and the offlinetraining set learned from the training image database,and is used to further improve the algorithm performance.Experimentalresults show that,as compared with some existing algorithms,the proposed algorithm helps to obtainbetter visual effect and more objective evaluation results.

Key words: image processing, super-resolution reconstruction, neighbor embedding, stepwise magnification, itera-tiveback projection, joint training set