A Novel Method for Super-Resolution

For existing super-resolution reconstruction algorithms, the image upper sampling process and de-blurring process are separated. The developed de-blurring methods can perform well. Thus, most researchers spent more effort on the up-sampling process. In the super-resolution reconstruction of images,...

Full description

Saved in:
Bibliographic Details
Published in2019 16th International Computer Conference on Wavelet Active Media Technology and Information Processing pp. 336 - 339
Main Authors ZHOU, FANG-RONG, MOU, FAN, CHENG, HUIXUAN, PENG, JING, MA, YI, ZHENG, ZE-ZHONG, YU, SHI-JIE, LI, JIANG
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2019
Subjects
Color
De-blurring
Image reconstruction
Kernel
Mathematical model
Reconstruction
Reconstruction algorithms
Spatial resolution
Super-resolution
Up-sampling
Online AccessGet full text

Cover

More Information
Summary:For existing super-resolution reconstruction algorithms, the image upper sampling process and de-blurring process are separated. The developed de-blurring methods can perform well. Thus, most researchers spent more effort on the up-sampling process. In the super-resolution reconstruction of images, although the common algorithms can estimate the transformation and rotation of different sequence frames accurately, they cannot deal with blurred images well. If we separate the upper sampling and de-blurring process in the super-resolution reconstruction, we can't make full use of the sequence images in the de-blurring process. In this paper, we developed a novel method by combining up-sampling process with the estimation of fuzzy kernel. The experimental results showed that our proposed method outperformed the commonly used algorithms subjectively and objectively. Therefore, our proposed approach is a robust method for the super- resolution reconstruction.
ISBN:9781728142418
1728142415
ISSN:2576-8964
DOI:10.1109/ICCWAMTIP47768.2019.9067650