19 July 2013 Image super-resolution using DCT interpolation and sparse learning-based method
Author Affiliations +
Proceedings Volume 8878, Fifth International Conference on Digital Image Processing (ICDIP 2013); 88784C (2013) https://doi.org/10.1117/12.2030721
Event: Fifth International Conference on Digital Image Processing, 2013, Beijing, China
Abstract
In this paper we present a method for single image super-resolution that use discrete cosine transform (DCT) interpolation and a sparse learning-based super-resolution method. The input low-resolution (LR) image is interpolated using both DCT interpolation and bicubic interpolation methods. The bicubic Interpolated image undergoes a process sparse coding using OMP algorithm. The obtained sparse coefficients are multiplied with high-resolution dictionary generated in the training phase, resulting in the intermediate high-resolution (HR) image. The final HR image is obtained by adding the DCT interpolated image and intermediate HR image. The experimental results demonstrate the effectiveness of the method proposed in terms of PSNR, SSIM and visual quality.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Saulo R. S. Reis, Saulo R. S. Reis, Graça Bressan, Graça Bressan, } "Image super-resolution using DCT interpolation and sparse learning-based method", Proc. SPIE 8878, Fifth International Conference on Digital Image Processing (ICDIP 2013), 88784C (19 July 2013); doi: 10.1117/12.2030721; https://doi.org/10.1117/12.2030721
PROCEEDINGS
5 PAGES


SHARE
Back to Top