TY  - CHAP
ID  - eprints2414
EP  - 8
SP  - 1
TI  - Super-resolution using neighbor embedding of back-projection residuals
N2  - In this paper we present a novel algorithm for neighbor embedding based super-resolution (SR), using an external dictionary. In neighbor embedding based SR, the dictionary is trained from couples of high-resolution and low-resolution (LR) training images, and consists of pairs of patches: matching patches (m-patches), which are used to match the input image patches and contain only low-frequency content, and reconstruction patches (r-patches), which are used to generate the output image patches and actually bring the high-frequency details. We propose a novel training scheme, where the m-patches are extracted from enhanced back-projected interpolations of the LR images and the r-patches are extracted from the back-projection residuals. A procedure to further optimize the dictionary is followed, and finally nonnegative neighbor embedding is considered at the SR algorithm stage. We consider singularly the various elements of the algorithm, and prove that each of them brings a gain on the final result. The complete algorithm is then compared to other state-of-the-art methods, and its competitiveness is shown.
AV  - none
N1  - 18th International Conference on Digital Signal Processing (DSP), Santorini, Greece, 1-3 July 2013
T2  - Proceedings of the 18th International Conference on Digital Signal Processing (DSP)
KW  - back-projection; example-based; neighbor embedding; super-resolution
A1  - Bevilacqua, Marco
A1  - Roumy, Aline
A1  - Guillemot, Christine
A1  - Alberi-Morel, Marie Line
UR  - http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6622796&isnumber=6622665
Y1  - 2013/07//
PB  - IEEE
ER  -