10 April 2018 Image sharpness assessment based on wavelet energy of edge area
Author Affiliations +
Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 106154Y (2018) https://doi.org/10.1117/12.2302984
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China
Abstract
Image quality assessment is needed in multiple image processing areas and blur is one of the key reasons of image deterioration. Although great full-reference image quality assessment metrics have been proposed in the past few years, no-reference method is still an area of current research. Facing this problem, this paper proposes a no-reference sharpness assessment method based on wavelet transformation which focuses on the edge area of image. Based on two simple characteristics of human vision system, weights are introduced to calculate weighted log-energy of each wavelet sub band. The final score is given by the ratio of high-frequency energy to the total energy. The algorithm is tested on multiple databases. Comparing with several state-of-the-art metrics, proposed algorithm has better performance and less runtime consumption.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jin Li, Jin Li, Hong Zhang, Hong Zhang, Lei Zhang, Lei Zhang, Yifan Yang, Yifan Yang, Lei He, Lei He, Mingui Sun, Mingui Sun, } "Image sharpness assessment based on wavelet energy of edge area", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106154Y (10 April 2018); doi: 10.1117/12.2302984; https://doi.org/10.1117/12.2302984
PROCEEDINGS
7 PAGES


SHARE
Back to Top