Reduced-reference quality assessment of screen content images

The screen content images (SCIs) quality influences the user experience and the interactive performance of remote computing systems. With numerous approaches proposed to evaluate the quality of natural images, much less work has been dedicated to reduced-reference image quality assessment (RR-IQA) o...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang, Shiqi, Gu, Ke, Zhang, Xinfeng, Lin, Weisi, Ma, Siwei, Gao, Wen
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/142238
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-142238
record_format dspace
spelling sg-ntu-dr.10356-1422382020-06-17T08:58:20Z Reduced-reference quality assessment of screen content images Wang, Shiqi Gu, Ke Zhang, Xinfeng Lin, Weisi Ma, Siwei Gao, Wen School of Computer Science and Engineering Engineering::Computer science and engineering Image Quality Assessment (IQA) Reduced Reference (RR) The screen content images (SCIs) quality influences the user experience and the interactive performance of remote computing systems. With numerous approaches proposed to evaluate the quality of natural images, much less work has been dedicated to reduced-reference image quality assessment (RR-IQA) of SCIs. Here, we propose an RR-IQA method from the perspective of SCI visual perception. In particular, the quality of the distorted SCI is evaluated by comparing a set of extracted statistical features that consider both primary visual information and unpredictable uncertainty. A unique property that differentiates the proposed method from previous RR-IQA methods for natural images is the consideration of behaviors when human subjects view the screen content, which motivates us to establish the perceptual model according to the distinct properties of SCIs. Validations based on the screen content IQA database show that the proposed algorithm provides accurate predictions across a wide range of SCI distortions with negligible transmission overhead. MOE (Min. of Education, S’pore) 2020-06-17T08:58:20Z 2020-06-17T08:58:20Z 2016 Journal Article Wang, S., Gu, K., Zhang, X., Lin, W., Ma, S., & Gao, W. (2018). Reduced-reference quality assessment of screen content images. IEEE Transactions on Circuits and Systems for Video Technology, 28(1), 1-14. doi:10.1109/TCSVT.2016.2602764 1051-8215 https://hdl.handle.net/10356/142238 10.1109/TCSVT.2016.2602764 2-s2.0-85040582459 1 28 1 14 en IEEE Transactions on Circuits and Systems for Video Technology © 2016 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Image Quality Assessment (IQA)
Reduced Reference (RR)
spellingShingle Engineering::Computer science and engineering
Image Quality Assessment (IQA)
Reduced Reference (RR)
Wang, Shiqi
Gu, Ke
Zhang, Xinfeng
Lin, Weisi
Ma, Siwei
Gao, Wen
Reduced-reference quality assessment of screen content images
description The screen content images (SCIs) quality influences the user experience and the interactive performance of remote computing systems. With numerous approaches proposed to evaluate the quality of natural images, much less work has been dedicated to reduced-reference image quality assessment (RR-IQA) of SCIs. Here, we propose an RR-IQA method from the perspective of SCI visual perception. In particular, the quality of the distorted SCI is evaluated by comparing a set of extracted statistical features that consider both primary visual information and unpredictable uncertainty. A unique property that differentiates the proposed method from previous RR-IQA methods for natural images is the consideration of behaviors when human subjects view the screen content, which motivates us to establish the perceptual model according to the distinct properties of SCIs. Validations based on the screen content IQA database show that the proposed algorithm provides accurate predictions across a wide range of SCI distortions with negligible transmission overhead.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Wang, Shiqi
Gu, Ke
Zhang, Xinfeng
Lin, Weisi
Ma, Siwei
Gao, Wen
format Article
author Wang, Shiqi
Gu, Ke
Zhang, Xinfeng
Lin, Weisi
Ma, Siwei
Gao, Wen
author_sort Wang, Shiqi
title Reduced-reference quality assessment of screen content images
title_short Reduced-reference quality assessment of screen content images
title_full Reduced-reference quality assessment of screen content images
title_fullStr Reduced-reference quality assessment of screen content images
title_full_unstemmed Reduced-reference quality assessment of screen content images
title_sort reduced-reference quality assessment of screen content images
publishDate 2020
url https://hdl.handle.net/10356/142238
_version_ 1681056733282172928