Year: 2016
Author: Chen Huang, Ming Jiang, Tingting Jiang
Journal of Computational Mathematics, Vol. 34 (2016), Iss. 6 : pp. 705–722
Abstract
Image Quality Assessment (IQA) is a fundamental problem in image processing. It is a common principle that human vision is hierarchical: we first perceive global structural information such as contours then focus on local regional details if necessary. Following this principle, we propose a novel framework for IQA by quantifying the degenerations of structural information and region content separately, and mapping both to obtain the objective score. The structural information can be obtained as contours by contour detection techniques. Experiments are conducted to demonstrate its performance in comparison with multiple state-of-the-art methods on two large scale datasets.
You do not have full access to this article.
Already a Subscriber? Sign in as an individual or via your institution
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.4208/jcm.1611-m2016-0534
Journal of Computational Mathematics, Vol. 34 (2016), Iss. 6 : pp. 705–722
Published online: 2016-01
AMS Subject Headings:
Copyright: COPYRIGHT: © Global Science Press
Pages: 18
Keywords: Image quality assessment Contour detection Image segmentation.