Gradient-based Image Quality Assessment

被引:2
作者
Bondzulic, Boban [1 ]
Petrovic, Vladimir [2 ]
Andric, Milenko [1 ]
Pavlovic, Boban [1 ]
机构
[1] Univ Def Belgrade, Mil Acad, Gen Pavla Jurisica Sturma 33, Belgrade 11000, Serbia
[2] Univ Novi Sad, Fac Tech Sci, Trg Dositeja Obradovica 6, Novi Sad 21000, Serbia
关键词
gradient magnitude; gradient orientation; image quality assessment; SIMILARITY; MAGNITUDE; DEVIATION; EFFICIENT; INDEX;
D O I
10.12700/APH.15.4.2018.4.5
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
An objective measure for image quality assessment based on a direct comparison of visual gradient information in the test and reference images is proposed. A perceptual model is defined to provide local estimates of gradient preservation and investigate perceptual importance pooling of such local quality estimates by using the lowest scores. The proposed perceptual pooled measure is validated using extensive subjective test results. Results indicate that the proposed measure is perceptually meaningful in that it corresponds well with the results of subjective evaluation and can outperform actual objective metrics.
引用
收藏
页码:83 / 99
页数:17
相关论文
共 30 条
[1]  
[Anonymous], OBJ PERC ASS VID QUA
[2]  
Bondzulic B. P., 2011, 2011 18th IEEE International Conference on Image Processing (ICIP 2011), P3305, DOI 10.1109/ICIP.2011.6116378
[3]   Additive models and separable pooling, a new look at structural similarity [J].
Bondzulic, Boban P. ;
Petrovic, Vladimir S. .
SIGNAL PROCESSING, 2014, 97 :110-116
[4]   VSNR: A wavelet-based visual signal-to-noise ratio for natural images [J].
Chandler, Damon M. ;
Hemami, Sheila S. .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2007, 16 (09) :2284-2298
[5]   Image quality assessment using natural image statistics in gradient domain [J].
Cheng, Guangquan ;
Huang, Jincai ;
Liu, Zhong ;
Lizhi, Cheng .
AEU-INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATIONS, 2011, 65 (05) :392-397
[6]  
De Simone F., JPEG CORE EXPT EVALU
[7]   No-reference image quality assessment based on natural scene statistics and gradient magnitude similarity [J].
Jia, Huizhen ;
Sun, Quansen ;
Ji, Zexuan ;
Wang, Tonghan ;
Chen, Qiang .
OPTICAL ENGINEERING, 2014, 53 (11)
[8]  
Jin L., 2016, P T INT S EL IM QUAL
[9]  
Larson E.C., CSIQ IMAGE DATABASE
[10]   Most apparent distortion: full-reference image quality assessment and the role of strategy [J].
Larson, Eric C. ;
Chandler, Damon M. .
JOURNAL OF ELECTRONIC IMAGING, 2010, 19 (01)