Super-resolution algorithms are used to improve the qualityand resolution of low-resolution images. These algorithms can be dividedinto two classes of hallucination- and reconstruction-based ones. Theimprovement factors of these algorithms are limited, however, previousresearch ,  has shown that combining super-resolution algorithmsfrom these two different groups can push the improvement factor further.We have shown in this paper that combining super-resolution algorithmsof the same class can also push the improvement factor up. For thispurpose, we have combined two hallucination based algorithms, namelythe one found in Single Image Super-Resolution from Transformed Self-Exemplars  and the Super-Resolution Convolutional Neural Networkfrom . The combination of these two, through an alpha-blending, hasresulted in a system that outperforms state-of-the-art super-resolutionalgorithms on public benchmark datasets.
|Conference||23rd international conference on pattern recognition (ICPR 2016)|
|Period||04/12/2016 → 08/12/2016|
|Series||Lecture Notes in Computer Science|