New Quality Assessment Method for Dense Light Fields

被引:5
|
作者
Huang, Zhijiao [1 ]
Yu, Mei [1 ]
Xu, Haiyong [1 ]
Song, Yang [1 ]
Jiang, Hao [1 ]
Jiang, Gangyi [1 ]
机构
[1] Ningbo Univ, Fac Informat Sci & Engn, Ningbo, Zhejiang, Peoples R China
来源
OPTOELECTRONIC IMAGING AND MULTIMEDIA TECHNOLOGY V | 2018年 / 10817卷
关键词
light field image; multi-views; quality assessment; quality metrics;
D O I
10.1117/12.2502277
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Light field has richer scene information than traditional images, including not only spatial information but also directional information. Aiming at multiple distortion problem of dense light field, combining with spatial and angular domain information, a light field image quality assessment method based on dense distortion curve analysis and scene information statistics is proposed in this paper. Firstly, the mean difference between all multi-view images in the angular domain of dense light field is extracted, and a corresponding distortion curve is drawn. Three statistical features are obtained by fitting the curve, which are slope, median and peak, respectively represent the distortion deviation, interpolation period and the maximum distortion. Then, the mean information entropy and mean gradient magnitude of the light field are extracted as the global and local features of the spatial domain. Finally, the extracted features are trained and tested by the Support Vector Regression. The experiment is conducted on the public MPI dense light field database. Experimental results show that the PLCC of the proposed method is 0.89, better than the existing methods, especially for different types of distorted contents.
引用
收藏
页数:10
相关论文
共 50 条
  • [1] Towards a quality metric for dense light fields
    Adhikarla, Vamsi Kiran
    Vinkler, Marek
    Sumin, Denis
    Mantiuk, Rafal K.
    Myszkowski, Karol
    Seidel, Hans-Peter
    Didyk, Piotr
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 3720 - 3729
  • [2] A survey on visual quality assessment methods for light fields
    Alamgeer, Sana
    Farias, Mylene C. Q.
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2023, 110
  • [3] New method for polarization measurements of magnetic fields in dense plasmas
    Demura, AV
    Oks, E
    IEEE TRANSACTIONS ON PLASMA SCIENCE, 1998, 26 (04) : 1251 - 1258
  • [4] New method for polarization measurements of magnetic fields in dense plasmas
    RRC `Kurchatov Inst', Moscow, Russia
    IEEE Trans Plasma Sci, 4 (1251-1258):
  • [5] DENSE SCENE RECONSTRUCTION FROM SPHERICAL LIGHT FIELDS
    Gava, Christiano Couto
    Stricker, Didier
    Yokota, Soichiro
    2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 4178 - 4182
  • [6] LINEAR VIEW/IMAGE RESTORATION FOR DENSE LIGHT FIELDS
    Kodama, Kazuya
    Kubota, Akira
    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 5462 - 5466
  • [7] A new assessment method for image fusion quality
    Li, Liu
    Jiang, Wanying
    Li, Jing
    Ming Yuchi
    Ding, Mingyue
    Zhang, Xuming
    MEDICAL IMAGING 2013: IMAGE PERCEPTION, OBSERVER PERFORMANCE, AND TECHNOLOGY ASSESSMENT, 2013, 8673
  • [8] A new method for quality assessment of hyperspectral images
    Garzelli, Andrea
    Nencini, Filippo
    Alparone, Luciano
    Baronti, Stefano
    IGARSS: 2007 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-12: SENSING AND UNDERSTANDING OUR PLANET, 2007, : 5138 - +
  • [9] SPARSE TO DENSE SCENE FLOW ESTIMATION FROM LIGHT FIELDS
    David, Pierre
    Le Pendu, Mikael
    Guillemot, Christine
    2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 3736 - 3740
  • [10] New Ductility Criterions for Quality Assessment of Light Weight Materials
    Schleich, Ralf
    Sindel, Manfred
    Keith, Torsten
    Liewald, Manfred
    MATERIALS TESTING-MATERIALS AND COMPONENTS TECHNOLOGY AND APPLICATION, 2008, 50 (09): : 472 - 476