No-Reference Quality Assessment for Contrast-Distorted Images
Contrast distortion is a common distortion type in the image applications. However, there are still very limited approaches proposed for quantifying the quality of the contrast-distorted images reliably. In this paper, we devise a novel no-reference/blind quality assessment method for those contrast...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9084139/ |
id |
doaj-4c4d9fd2369e497aac2fa52e32e92af5 |
---|---|
record_format |
Article |
spelling |
doaj-4c4d9fd2369e497aac2fa52e32e92af52021-03-30T01:43:32ZengIEEEIEEE Access2169-35362020-01-018841058411510.1109/ACCESS.2020.29918429084139No-Reference Quality Assessment for Contrast-Distorted ImagesYutao Liu0https://orcid.org/0000-0002-3066-1884Xiu Li1Department of Information Science and Technology, Tsinghua Shenzhen International Graduate School, Shenzhen, ChinaDepartment of Information Science and Technology, Tsinghua Shenzhen International Graduate School, Shenzhen, ChinaContrast distortion is a common distortion type in the image applications. However, there are still very limited approaches proposed for quantifying the quality of the contrast-distorted images reliably. In this paper, we devise a novel no-reference/blind quality assessment method for those contrast-distorted images. In the proposed method, we characterize the image quality by deeply investigating multiple contrast distortion-relevant properties of the image, i.e., spatial characteristics, image histogram, visual perception characteristics and chrominance, which can describe the image quality more comprehensively and precisely. Accordingly, a series of quality-aware features are developed to characterize the contrast-distorted image quality properly. Support vector regression (SVR) is then employed to integrate all the extracted features and infer the image quality score. Extensive experiments conducted on the standard contrast-distorted image databases/datasets demonstrate that the proposed method achieves superior prediction performance to the state-of-the-art NR quality assessment models on evaluating the contrast-distorted image quality.https://ieeexplore.ieee.org/document/9084139/Image quality assessmentno-reference/blindcontrast distortionfree-energy theorynatural scene statistics (NSS) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yutao Liu Xiu Li |
spellingShingle |
Yutao Liu Xiu Li No-Reference Quality Assessment for Contrast-Distorted Images IEEE Access Image quality assessment no-reference/blind contrast distortion free-energy theory natural scene statistics (NSS) |
author_facet |
Yutao Liu Xiu Li |
author_sort |
Yutao Liu |
title |
No-Reference Quality Assessment for Contrast-Distorted Images |
title_short |
No-Reference Quality Assessment for Contrast-Distorted Images |
title_full |
No-Reference Quality Assessment for Contrast-Distorted Images |
title_fullStr |
No-Reference Quality Assessment for Contrast-Distorted Images |
title_full_unstemmed |
No-Reference Quality Assessment for Contrast-Distorted Images |
title_sort |
no-reference quality assessment for contrast-distorted images |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Contrast distortion is a common distortion type in the image applications. However, there are still very limited approaches proposed for quantifying the quality of the contrast-distorted images reliably. In this paper, we devise a novel no-reference/blind quality assessment method for those contrast-distorted images. In the proposed method, we characterize the image quality by deeply investigating multiple contrast distortion-relevant properties of the image, i.e., spatial characteristics, image histogram, visual perception characteristics and chrominance, which can describe the image quality more comprehensively and precisely. Accordingly, a series of quality-aware features are developed to characterize the contrast-distorted image quality properly. Support vector regression (SVR) is then employed to integrate all the extracted features and infer the image quality score. Extensive experiments conducted on the standard contrast-distorted image databases/datasets demonstrate that the proposed method achieves superior prediction performance to the state-of-the-art NR quality assessment models on evaluating the contrast-distorted image quality. |
topic |
Image quality assessment no-reference/blind contrast distortion free-energy theory natural scene statistics (NSS) |
url |
https://ieeexplore.ieee.org/document/9084139/ |
work_keys_str_mv |
AT yutaoliu noreferencequalityassessmentforcontrastdistortedimages AT xiuli noreferencequalityassessmentforcontrastdistortedimages |
_version_ |
1724186535686832128 |