24 December 2013 Quality enhancement of low-resolution image by using natural images
Author Affiliations +
Proceedings Volume 9067, Sixth International Conference on Machine Vision (ICMV 2013); 90671L (2013) https://doi.org/10.1117/12.2051684
Event: Sixth International Conference on Machine Vision (ICMV 13), 2013, London, United Kingdom
Abstract
In this paper, we propose a new algorithm to estimate a super-resolution image from a given low-resolution image, by adding high-frequency information that is extracted from natural high-resolution images in the training dataset. The selection of the high-frequency information from the training dataset is accomplished in two steps: a nearest-neighbor search algorithm is used to select the closest images from the training dataset, which can be implemented in the GPU, and a sparse-representation algorithm is used to estimate a weight parameter to combine the high-frequency information of selected images. This simple but very powerful super-resolution algorithm can produce state-of-the-art results. Qualitatively and quantitatively, we demonstrate that the proposed algorithm outperforms existing common practices.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
E. Bilgazyev, E. Yeniaras, I. Uyanik, M. Unan, E. L. Leiss, "Quality enhancement of low-resolution image by using natural images", Proc. SPIE 9067, Sixth International Conference on Machine Vision (ICMV 2013), 90671L (24 December 2013); doi: 10.1117/12.2051684; https://doi.org/10.1117/12.2051684
PROCEEDINGS
7 PAGES


SHARE
Back to Top