Blind PSNR Estimation of Compressed Video Sequences Supported by Machine Learning

Takahiro Kumekawa, Masahiro Wakabayashi, Jiro Katto, Naofumi Wada

    Research output: Contribution to journalArticle

    1 Citation (Scopus)

    Abstract

    The peak signal-to-noise ratio (PSNR) used as an index of image quality usually requires original images, but this is difficult for consumer generated content such as videos on YouTube. Therefore, we developed two blind PSNR estimation methods without bit-stream analysis in which multiple support vector machines are prepared to learn differently encoded images in PSNR; using an entire frame and dividing the frame into two areas. We confirmed that higher estimation accuracy is possible for the latter method against that using the entire frame.

    Original languageEnglish
    Pages (from-to)353-361
    Number of pages9
    JournalITE Transactions on Media Technology and Applications
    Volume2
    Issue number4
    Publication statusPublished - 2014

    Fingerprint

    Learning systems
    Signal to noise ratio
    Image quality
    Support vector machines

    Keywords

    • AC Power
    • Blind PSNR Estimation
    • Saliency Map
    • SVM
    • Video Quality Assessment

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Signal Processing
    • Media Technology

    Cite this

    Blind PSNR Estimation of Compressed Video Sequences Supported by Machine Learning. / Kumekawa, Takahiro; Wakabayashi, Masahiro; Katto, Jiro; Wada, Naofumi.

    In: ITE Transactions on Media Technology and Applications, Vol. 2, No. 4, 2014, p. 353-361.

    Research output: Contribution to journalArticle

    Kumekawa, Takahiro ; Wakabayashi, Masahiro ; Katto, Jiro ; Wada, Naofumi. / Blind PSNR Estimation of Compressed Video Sequences Supported by Machine Learning. In: ITE Transactions on Media Technology and Applications. 2014 ; Vol. 2, No. 4. pp. 353-361.
    @article{9275679e8cd1483c886a0a4ee37ee10b,
    title = "Blind PSNR Estimation of Compressed Video Sequences Supported by Machine Learning",
    abstract = "The peak signal-to-noise ratio (PSNR) used as an index of image quality usually requires original images, but this is difficult for consumer generated content such as videos on YouTube. Therefore, we developed two blind PSNR estimation methods without bit-stream analysis in which multiple support vector machines are prepared to learn differently encoded images in PSNR; using an entire frame and dividing the frame into two areas. We confirmed that higher estimation accuracy is possible for the latter method against that using the entire frame.",
    keywords = "AC Power, Blind PSNR Estimation, Saliency Map, SVM, Video Quality Assessment",
    author = "Takahiro Kumekawa and Masahiro Wakabayashi and Jiro Katto and Naofumi Wada",
    year = "2014",
    language = "English",
    volume = "2",
    pages = "353--361",
    journal = "ITE Transactions on Media Technology and Applications",
    issn = "2186-7364",
    publisher = "Institute of Image Information and Television Engineers",
    number = "4",

    }

    TY - JOUR

    T1 - Blind PSNR Estimation of Compressed Video Sequences Supported by Machine Learning

    AU - Kumekawa, Takahiro

    AU - Wakabayashi, Masahiro

    AU - Katto, Jiro

    AU - Wada, Naofumi

    PY - 2014

    Y1 - 2014

    N2 - The peak signal-to-noise ratio (PSNR) used as an index of image quality usually requires original images, but this is difficult for consumer generated content such as videos on YouTube. Therefore, we developed two blind PSNR estimation methods without bit-stream analysis in which multiple support vector machines are prepared to learn differently encoded images in PSNR; using an entire frame and dividing the frame into two areas. We confirmed that higher estimation accuracy is possible for the latter method against that using the entire frame.

    AB - The peak signal-to-noise ratio (PSNR) used as an index of image quality usually requires original images, but this is difficult for consumer generated content such as videos on YouTube. Therefore, we developed two blind PSNR estimation methods without bit-stream analysis in which multiple support vector machines are prepared to learn differently encoded images in PSNR; using an entire frame and dividing the frame into two areas. We confirmed that higher estimation accuracy is possible for the latter method against that using the entire frame.

    KW - AC Power

    KW - Blind PSNR Estimation

    KW - Saliency Map

    KW - SVM

    KW - Video Quality Assessment

    UR - http://www.scopus.com/inward/record.url?scp=84952316250&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84952316250&partnerID=8YFLogxK

    M3 - Article

    VL - 2

    SP - 353

    EP - 361

    JO - ITE Transactions on Media Technology and Applications

    JF - ITE Transactions on Media Technology and Applications

    SN - 2186-7364

    IS - 4

    ER -