3D image quality index using SDP-based binocular perception model

Hyunsuk Ko, Chang-Su Kim, Seo Young Choi, C. C Jay Kuo

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    10 Citations (Scopus)

    Abstract

    A novel quality index for stereoscopic image pairs is proposed in this work. First, we introduce a parameter called the structural distortion parameter (SDP), which varies according to different distortion types. Then, we use the SDP as a control parameter in a binocular perception model, and apply it into three components of SSIM to obtain an overall quality index. In the proposed framework, the binocular model accommodates distortion types and distortion degrees and, therefore, offers robust quality assessment results for both symmetric and asymmetric distortions. It is shown by experimental results that the proposed index outperforms several existing 3D image quality index methods.

    Original languageEnglish
    Title of host publication2013 IEEE 11th IVMSP Workshop
    Subtitle of host publication3D Image/Video Technologies and Applications, IVMSP 2013 - Proceedings
    DOIs
    Publication statusPublished - 2013
    Event2013 IEEE 11th Workshop on 3D Image/Video Technologies and Applications, IVMSP 2013 - Seoul, Korea, Republic of
    Duration: 2013 Jun 102013 Jun 12

    Publication series

    Name2013 IEEE 11th IVMSP Workshop: 3D Image/Video Technologies and Applications, IVMSP 2013 - Proceedings

    Other

    Other2013 IEEE 11th Workshop on 3D Image/Video Technologies and Applications, IVMSP 2013
    Country/TerritoryKorea, Republic of
    CitySeoul
    Period13/6/1013/6/12

    Keywords

    • 3D
    • asymmetric distortion
    • binocular perception model
    • quality index
    • structural distortion

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Computer Vision and Pattern Recognition
    • Computer Science Applications

    Fingerprint

    Dive into the research topics of '3D image quality index using SDP-based binocular perception model'. Together they form a unique fingerprint.

    Cite this