29 August 2016 Super-resolution reconstruction algorithm based on local self-similarity
Author Affiliations +
Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 1003349 (2016) https://doi.org/10.1117/12.2244842
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China
Abstract
Super-resolution has been extensively studied for decades, but its application to a real-world image still remains challenging. In this paper, a novel approach for image super-resolution algorithm based on local self-similarity (SRLS) is proposed. First, a limited window is used to bind several similar patches of the input image into a same group. Then the high-resolution image can be inferred by using the image capturing model. The experiment shows that the proposed algorithm achieves improvement in image quality and provides more details.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Min Shi, Min Shi, Qingming Yi, Qingming Yi, Xinzhong Zhao, Xinzhong Zhao, Yang Bai, Yang Bai, } "Super-resolution reconstruction algorithm based on local self-similarity", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 1003349 (29 August 2016); doi: 10.1117/12.2244842; https://doi.org/10.1117/12.2244842
PROCEEDINGS
5 PAGES


SHARE
RELATED CONTENT

Image coding compression based on DCT
Proceedings of SPIE (June 07 2012)
Free viewpoint image generation from a video captured by a...
Proceedings of SPIE (February 15 2011)
Using the PROJECTRON algorithm for image compression
Proceedings of SPIE (October 19 1993)

Back to Top