Screen Content Image Quality Assessment Using Multi-Scale Difference of Gaussian

Ying Fu; Huanqiang Zeng; Lin Ma; Zhangkai Ni; Jianqing Zhu; Kai-Kuang Ma

doi:10.1109/TCSVT.2018.2854176

Screen Content Image Quality Assessment Using Multi-Scale Difference of Gaussian

Ying Fu
, Huanqiang Zeng^*
, Lin Ma
, Zhangkai Ni
, Jianqing Zhu
, Kai-Kuang Ma

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

80 Citations (Scopus)

Abstract

In this paper, a novel image quality assessment (IQA) model for the screen content images (SCIs) is proposed by using multi-scale difference of Gaussian (MDOG). Motivated by the observation that the human visual system (HVS) is sensitive to the edges while the image details can be better explored in different scales, the proposed model exploits MDOG to effectively characterize the edge information of the reference and distorted SCIs at two different scales, respectively. Then, the degree of edge similarity is measured in terms of the smaller-scale edge map. Finally, the edge strength computed based on the larger-scale edge map is used as the weighting factor to generate the final SCI quality score. Experimental results have shown that the proposed IQA model for the SCIs produces high consistency with human perception of the SCI quality and outperforms the state-of-the-art quality models.

Original language	English
Pages (from-to)	2428-2432
Number of pages	5
Journal	IEEE Transactions on Circuits and Systems for Video Technology
Volume	28
Issue number	9
Online published	9 Jul 2018
DOIs	https://doi.org/10.1109/TCSVT.2018.2854176
Publication status	Published - Sept 2018
Externally published	Yes

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant 61401167, Grant 61372107, and Grant 61602191, in part by the Natural Science Foundation of Fujian Province under Grant 2016J01308 and Grant 2017J05103, in part by the Fujian-100 Talented People Program, in part by the High-level Talent Innovation Program of Quanzhou City under Grant 2017G027, in part by the Promotion Program for Young and Middle-aged Teacher in Science and Technology Research of Huaqiao University under Grant ZQN-YX403 and Grant ZQN-PY418, and in part by the High-Level Talent Project Foundation of Huaqiao University under Grant 14BS201, Grant 14BS204, and Grant 16BS108. This paper was recommended by Associate Editor A. Pizurica.

Research Keywords

Human visual system (HVS)
image quality assessment (IQA)
screen content image (SCI)
multi-scale difference of Gaussian

Access Output

10.1109/TCSVT.2018.2854176

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{53326e30c4a741e39f502a1fc7cf0c1b,

title = "Screen Content Image Quality Assessment Using Multi-Scale Difference of Gaussian",

abstract = "In this paper, a novel image quality assessment (IQA) model for the screen content images (SCIs) is proposed by using multi-scale difference of Gaussian (MDOG). Motivated by the observation that the human visual system (HVS) is sensitive to the edges while the image details can be better explored in different scales, the proposed model exploits MDOG to effectively characterize the edge information of the reference and distorted SCIs at two different scales, respectively. Then, the degree of edge similarity is measured in terms of the smaller-scale edge map. Finally, the edge strength computed based on the larger-scale edge map is used as the weighting factor to generate the final SCI quality score. Experimental results have shown that the proposed IQA model for the SCIs produces high consistency with human perception of the SCI quality and outperforms the state-of-the-art quality models.",

keywords = "Human visual system (HVS), image quality assessment (IQA), screen content image (SCI), multi-scale difference of Gaussian",

author = "Ying Fu and Huanqiang Zeng and Lin Ma and Zhangkai Ni and Jianqing Zhu and Kai-Kuang Ma",

year = "2018",

month = sep,

doi = "10.1109/TCSVT.2018.2854176",

language = "English",

volume = "28",

pages = "2428--2432",

journal = "IEEE Transactions on Circuits and Systems for Video Technology",

issn = "1051-8215",

publisher = "IEEE",

number = "9",

}

TY - JOUR

T1 - Screen Content Image Quality Assessment Using Multi-Scale Difference of Gaussian

AU - Fu, Ying

AU - Zeng, Huanqiang

AU - Ma, Lin

AU - Ni, Zhangkai

AU - Zhu, Jianqing

AU - Ma, Kai-Kuang

PY - 2018/9

Y1 - 2018/9

N2 - In this paper, a novel image quality assessment (IQA) model for the screen content images (SCIs) is proposed by using multi-scale difference of Gaussian (MDOG). Motivated by the observation that the human visual system (HVS) is sensitive to the edges while the image details can be better explored in different scales, the proposed model exploits MDOG to effectively characterize the edge information of the reference and distorted SCIs at two different scales, respectively. Then, the degree of edge similarity is measured in terms of the smaller-scale edge map. Finally, the edge strength computed based on the larger-scale edge map is used as the weighting factor to generate the final SCI quality score. Experimental results have shown that the proposed IQA model for the SCIs produces high consistency with human perception of the SCI quality and outperforms the state-of-the-art quality models.

AB - In this paper, a novel image quality assessment (IQA) model for the screen content images (SCIs) is proposed by using multi-scale difference of Gaussian (MDOG). Motivated by the observation that the human visual system (HVS) is sensitive to the edges while the image details can be better explored in different scales, the proposed model exploits MDOG to effectively characterize the edge information of the reference and distorted SCIs at two different scales, respectively. Then, the degree of edge similarity is measured in terms of the smaller-scale edge map. Finally, the edge strength computed based on the larger-scale edge map is used as the weighting factor to generate the final SCI quality score. Experimental results have shown that the proposed IQA model for the SCIs produces high consistency with human perception of the SCI quality and outperforms the state-of-the-art quality models.

KW - Human visual system (HVS)

KW - image quality assessment (IQA)

KW - screen content image (SCI)

KW - multi-scale difference of Gaussian

UR - https://www.scopus.com/pages/publications/85049663753

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85049663753&origin=recordpage

U2 - 10.1109/TCSVT.2018.2854176

DO - 10.1109/TCSVT.2018.2854176

M3 - RGC 21 - Publication in refereed journal

SN - 1051-8215

VL - 28

SP - 2428

EP - 2432

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

IS - 9

ER -

Screen Content Image Quality Assessment Using Multi-Scale Difference of Gaussian

Abstract

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this