Share Email Print

Proceedings Paper

Image sharpness assessment based on wavelet energy of edge area
Author(s): Jin Li; Hong Zhang; Lei Zhang; Yifan Yang; Lei He; Mingui Sun
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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.

Paper Details

Date Published: 10 April 2018
PDF: 7 pages
Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106154Y (10 April 2018); doi: 10.1117/12.2302984
Show Author Affiliations
Jin Li, Beihang Univ. (China)
Hong Zhang, Beihang Univ. (China)
Lei Zhang, Beihang Univ. (China)
Yifan Yang, Beihang Univ. (China)
Lei He, Luoyang Electro-optical Equipment Research Institute (China)
Mingui Sun, Univ. of Pittsburgh (United States)

Published in SPIE Proceedings Vol. 10615:
Ninth International Conference on Graphic and Image Processing (ICGIP 2017)
Hui Yu; Junyu Dong, Editor(s)

© SPIE. Terms of Use
Back to Top