arrow
返回

Sparse representation-based image quality assessment

delete2014-11-01
delete35
delete
OA
AI
T
Tanaya Guha *
E
Ehsan Nezhadarya
R
Rabab Ward
DOI:10.1016/j.image.2014.09.010delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
A highly promising approach to assess the quality of an image involves comparing the perceptually important structural information in this image with that in its reference image. The extraction of the perceptually important structural information is however a challenging task. This paper employs a sparse representation-based approach to extract such structural information. It proposes a new metric called the sparse representation-based quality (SPARQ) index that measures the visual quality of an image. The proposed approach learns the inherent structures of the reference image as a set of basis vectors. These vectors are obtained such that any structure in the image can be efficiently represented by a linear combination of only a few of these basis vectors. Such a sparse strategy is known to generate basis vectors that are qualitatively similar to the receptive field of the simple cells present in the mammalian primary visual cortex. To estimate the visual quality of the distorted image, structures in the visually important areas in this image are compared with those in the reference image, in terms of the learnt basis vectors. Our approach is evaluated on six publicly available subject-rated image quality assessment datasets. The proposed SPARQ index consistently exhibits high correlation with the subjective ratings of all datasets and overall, performs better than a number of popular image quality metrics. (C) 2014 Elsevier B.V. All rights reserved.
Keyword:
Dictionary learning
Image quality assessment
Sparse representation
Structural similarity
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

S
Signal Processing and Image Communication
IF:
2.7
论文数:
2.8K
被引数:
4.2K

机构

U
University of British Columbia
学者数:
7.0W
论文数: 6.1W
被引数: 8.6W
引用论文

引用论文

err分享
err收藏
err分享
err收藏
学者 查看更多内容