Super-resolution algorithm exploiting multiple dictionaries based on local image structures

We propose an example-based superresolution algorithm that adaptively exploits multiple dictionaries based on local image structures. Noise, irregularities, and blurred textures are noticeable artifacts in the reconstructed image due to a shortage of relevant examples and false exploration in the dictionary. These artifacts are emphasized during successive enhancement. We alleviate the artifacts by constructing multiple dictionaries coupled with different sharpness levels during the learning phase. We exploit these dictionaries adaptively based on local image structures during the synthesis phase. Experimental results show that the proposed algorithm provides more detailed images with significantly reduced artifacts while consuming only 8.6% of storage capacity and 0.25% of CPU running time in comparison with a typical examplebased superresolution algorithm based on neighbor embedding.