Multi-frame image super resolution based on sparse coding

Toshiyuki Kato, Hideitsu Hino, Noboru Murata

    Research output: Contribution to journalArticle

    13 Citations (Scopus)

    Abstract

    An image super-resolution method from multiple observation of low-resolution images is proposed. The method is based on sub-pixel accuracy block matching for estimating relative displacements of observed images, and sparse signal representation for estimating the corresponding high-resolution image, where correspondence between high- and low-resolution images are modeled by a certain degradation process. Relative displacements of small patches of observed low-resolution images are accurately estimated by a computationally efficient block matching method. The matching scores of the block matching are used to select a subset of low-resolution patches for reconstructing a high-resolution patch, that is, an adaptive selection of informative low-resolution images is realized. The proposed method is shown to perform comparable or superior to conventional super-resolution methods through experiments using various images.

    Original languageEnglish
    Pages (from-to)64-78
    Number of pages15
    JournalNeural Networks
    Volume66
    DOIs
    Publication statusPublished - 2015 Jun 1

    Fingerprint

    Image resolution
    Optical resolving power
    Pixels
    Observation
    Degradation
    Experiments

    Keywords

    • Image super resolution
    • Multi-frame super-resolution
    • Sparse coding

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Cognitive Neuroscience

    Cite this

    Multi-frame image super resolution based on sparse coding. / Kato, Toshiyuki; Hino, Hideitsu; Murata, Noboru.

    In: Neural Networks, Vol. 66, 01.06.2015, p. 64-78.

    Research output: Contribution to journalArticle

    Kato, Toshiyuki ; Hino, Hideitsu ; Murata, Noboru. / Multi-frame image super resolution based on sparse coding. In: Neural Networks. 2015 ; Vol. 66. pp. 64-78.
    @article{de00c78c8dad4e888a637c26db2fb247,
    title = "Multi-frame image super resolution based on sparse coding",
    abstract = "An image super-resolution method from multiple observation of low-resolution images is proposed. The method is based on sub-pixel accuracy block matching for estimating relative displacements of observed images, and sparse signal representation for estimating the corresponding high-resolution image, where correspondence between high- and low-resolution images are modeled by a certain degradation process. Relative displacements of small patches of observed low-resolution images are accurately estimated by a computationally efficient block matching method. The matching scores of the block matching are used to select a subset of low-resolution patches for reconstructing a high-resolution patch, that is, an adaptive selection of informative low-resolution images is realized. The proposed method is shown to perform comparable or superior to conventional super-resolution methods through experiments using various images.",
    keywords = "Image super resolution, Multi-frame super-resolution, Sparse coding",
    author = "Toshiyuki Kato and Hideitsu Hino and Noboru Murata",
    year = "2015",
    month = "6",
    day = "1",
    doi = "10.1016/j.neunet.2015.02.009",
    language = "English",
    volume = "66",
    pages = "64--78",
    journal = "Neural Networks",
    issn = "0893-6080",
    publisher = "Elsevier Limited",

    }

    TY - JOUR

    T1 - Multi-frame image super resolution based on sparse coding

    AU - Kato, Toshiyuki

    AU - Hino, Hideitsu

    AU - Murata, Noboru

    PY - 2015/6/1

    Y1 - 2015/6/1

    N2 - An image super-resolution method from multiple observation of low-resolution images is proposed. The method is based on sub-pixel accuracy block matching for estimating relative displacements of observed images, and sparse signal representation for estimating the corresponding high-resolution image, where correspondence between high- and low-resolution images are modeled by a certain degradation process. Relative displacements of small patches of observed low-resolution images are accurately estimated by a computationally efficient block matching method. The matching scores of the block matching are used to select a subset of low-resolution patches for reconstructing a high-resolution patch, that is, an adaptive selection of informative low-resolution images is realized. The proposed method is shown to perform comparable or superior to conventional super-resolution methods through experiments using various images.

    AB - An image super-resolution method from multiple observation of low-resolution images is proposed. The method is based on sub-pixel accuracy block matching for estimating relative displacements of observed images, and sparse signal representation for estimating the corresponding high-resolution image, where correspondence between high- and low-resolution images are modeled by a certain degradation process. Relative displacements of small patches of observed low-resolution images are accurately estimated by a computationally efficient block matching method. The matching scores of the block matching are used to select a subset of low-resolution patches for reconstructing a high-resolution patch, that is, an adaptive selection of informative low-resolution images is realized. The proposed method is shown to perform comparable or superior to conventional super-resolution methods through experiments using various images.

    KW - Image super resolution

    KW - Multi-frame super-resolution

    KW - Sparse coding

    UR - http://www.scopus.com/inward/record.url?scp=84925280789&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84925280789&partnerID=8YFLogxK

    U2 - 10.1016/j.neunet.2015.02.009

    DO - 10.1016/j.neunet.2015.02.009

    M3 - Article

    C2 - 25805366

    AN - SCOPUS:84925280789

    VL - 66

    SP - 64

    EP - 78

    JO - Neural Networks

    JF - Neural Networks

    SN - 0893-6080

    ER -