No reference quality assessment for screen content images with both local and global feature representation

In this paper, we propose a novel no reference quality assessment method by incorporating statistical luminance and texture features (NRLT) for screen content images (SCIs) with both local and global feature representation. The proposed method is designed inspired by the perceptual property of the h...

Full description

Saved in:
Bibliographic Details
Main Authors: Fang, Yuming, Yan, Jiebin, Li, Leida, Wu, Jinjian, Lin, Weisi
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/142325
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-142325
record_format dspace
spelling sg-ntu-dr.10356-1423252020-06-19T04:05:03Z No reference quality assessment for screen content images with both local and global feature representation Fang, Yuming Yan, Jiebin Li, Leida Wu, Jinjian Lin, Weisi School of Computer Science and Engineering Engineering::Computer science and engineering Screen Content Image Visual Quality Assessment In this paper, we propose a novel no reference quality assessment method by incorporating statistical luminance and texture features (NRLT) for screen content images (SCIs) with both local and global feature representation. The proposed method is designed inspired by the perceptual property of the human visual system (HVS) that the HVS is sensitive to luminance change and texture information for image perception. In the proposed method, we first calculate the luminance map through the local normalization, which is further used to extract the statistical luminance features in global scope. Second, inspired by existing studies from neuroscience that high-order derivatives can capture image texture, we adopt four filters with different directions to compute gradient maps from the luminance map. These gradient maps are then used to extract the second-order derivatives by local binary pattern. We further extract the texture feature by the histogram of high-order derivatives in global scope. Finally, support vector regression is applied to train the mapping function from quality-aware features to subjective ratings. Experimental results on the public large-scale SCI database show that the proposed NRLT can achieve better performance in predicting the visual quality of SCIs than relevant existing methods, even including some full reference visual quality assessment methods. 2020-06-19T04:05:03Z 2020-06-19T04:05:03Z 2017 Journal Article Fang, Y., Yan, J., Li, L., Wu, J., & Lin, W. (2018). No reference quality assessment for screen content images with both local and global feature representation. IEEE Transactions on Image Processing, 27(4), 1600-1610. doi:10.1109/TIP.2017.2781307 1057-7149 https://hdl.handle.net/10356/142325 10.1109/TIP.2017.2781307 29324414 2-s2.0-85038373470 4 27 1600 1610 en IEEE Transactions on Image Processing © 2017 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Screen Content Image
Visual Quality Assessment
spellingShingle Engineering::Computer science and engineering
Screen Content Image
Visual Quality Assessment
Fang, Yuming
Yan, Jiebin
Li, Leida
Wu, Jinjian
Lin, Weisi
No reference quality assessment for screen content images with both local and global feature representation
description In this paper, we propose a novel no reference quality assessment method by incorporating statistical luminance and texture features (NRLT) for screen content images (SCIs) with both local and global feature representation. The proposed method is designed inspired by the perceptual property of the human visual system (HVS) that the HVS is sensitive to luminance change and texture information for image perception. In the proposed method, we first calculate the luminance map through the local normalization, which is further used to extract the statistical luminance features in global scope. Second, inspired by existing studies from neuroscience that high-order derivatives can capture image texture, we adopt four filters with different directions to compute gradient maps from the luminance map. These gradient maps are then used to extract the second-order derivatives by local binary pattern. We further extract the texture feature by the histogram of high-order derivatives in global scope. Finally, support vector regression is applied to train the mapping function from quality-aware features to subjective ratings. Experimental results on the public large-scale SCI database show that the proposed NRLT can achieve better performance in predicting the visual quality of SCIs than relevant existing methods, even including some full reference visual quality assessment methods.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Fang, Yuming
Yan, Jiebin
Li, Leida
Wu, Jinjian
Lin, Weisi
format Article
author Fang, Yuming
Yan, Jiebin
Li, Leida
Wu, Jinjian
Lin, Weisi
author_sort Fang, Yuming
title No reference quality assessment for screen content images with both local and global feature representation
title_short No reference quality assessment for screen content images with both local and global feature representation
title_full No reference quality assessment for screen content images with both local and global feature representation
title_fullStr No reference quality assessment for screen content images with both local and global feature representation
title_full_unstemmed No reference quality assessment for screen content images with both local and global feature representation
title_sort no reference quality assessment for screen content images with both local and global feature representation
publishDate 2020
url https://hdl.handle.net/10356/142325
_version_ 1681057242605944832