Machine-learning approach to holographic particle characterization

Aaron Yevick, Mark Hannel, David G. Grier

    Research output: Contribution to journalArticle

    Abstract

    Holograms of colloidal dispersions encode comprehensive information about individual particles' three-dimensional positions, sizes and optical properties. Extracting that information typically is computationally intensive, and thus slow. Here, we demonstrate that machine-learning techniques based on support vector machines (SVMs) can analyze holographic video microscopy data in real time on low-power computers. The resulting stream of precise particle-resolved tracking and characterization data provides unparalleled insights into the composition and dynamics of colloidal dispersions and enables applications ranging from basic research to process control and quality assurance.

    Original languageEnglish (US)
    Pages (from-to)26884-26890
    Number of pages7
    JournalOptics Express
    Volume22
    Issue number22
    DOIs
    StatePublished - 2014

    Fingerprint

    machine learning
    assurance
    microscopy
    optical properties

    ASJC Scopus subject areas

    • Atomic and Molecular Physics, and Optics

    Cite this

    Machine-learning approach to holographic particle characterization. / Yevick, Aaron; Hannel, Mark; Grier, David G.

    In: Optics Express, Vol. 22, No. 22, 2014, p. 26884-26890.

    Research output: Contribution to journalArticle

    Yevick, A, Hannel, M & Grier, DG 2014, 'Machine-learning approach to holographic particle characterization', Optics Express, vol. 22, no. 22, pp. 26884-26890. https://doi.org/10.1364/OE.22.026884
    Yevick, Aaron ; Hannel, Mark ; Grier, David G. / Machine-learning approach to holographic particle characterization. In: Optics Express. 2014 ; Vol. 22, No. 22. pp. 26884-26890.
    @article{d410f5ea490a4283928299e857c8c81e,
    title = "Machine-learning approach to holographic particle characterization",
    abstract = "Holograms of colloidal dispersions encode comprehensive information about individual particles' three-dimensional positions, sizes and optical properties. Extracting that information typically is computationally intensive, and thus slow. Here, we demonstrate that machine-learning techniques based on support vector machines (SVMs) can analyze holographic video microscopy data in real time on low-power computers. The resulting stream of precise particle-resolved tracking and characterization data provides unparalleled insights into the composition and dynamics of colloidal dispersions and enables applications ranging from basic research to process control and quality assurance.",
    author = "Aaron Yevick and Mark Hannel and Grier, {David G.}",
    year = "2014",
    doi = "10.1364/OE.22.026884",
    language = "English (US)",
    volume = "22",
    pages = "26884--26890",
    journal = "Optics Express",
    issn = "1094-4087",
    publisher = "The Optical Society",
    number = "22",

    }

    TY - JOUR

    T1 - Machine-learning approach to holographic particle characterization

    AU - Yevick, Aaron

    AU - Hannel, Mark

    AU - Grier, David G.

    PY - 2014

    Y1 - 2014

    N2 - Holograms of colloidal dispersions encode comprehensive information about individual particles' three-dimensional positions, sizes and optical properties. Extracting that information typically is computationally intensive, and thus slow. Here, we demonstrate that machine-learning techniques based on support vector machines (SVMs) can analyze holographic video microscopy data in real time on low-power computers. The resulting stream of precise particle-resolved tracking and characterization data provides unparalleled insights into the composition and dynamics of colloidal dispersions and enables applications ranging from basic research to process control and quality assurance.

    AB - Holograms of colloidal dispersions encode comprehensive information about individual particles' three-dimensional positions, sizes and optical properties. Extracting that information typically is computationally intensive, and thus slow. Here, we demonstrate that machine-learning techniques based on support vector machines (SVMs) can analyze holographic video microscopy data in real time on low-power computers. The resulting stream of precise particle-resolved tracking and characterization data provides unparalleled insights into the composition and dynamics of colloidal dispersions and enables applications ranging from basic research to process control and quality assurance.

    UR - http://www.scopus.com/inward/record.url?scp=84922125479&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84922125479&partnerID=8YFLogxK

    U2 - 10.1364/OE.22.026884

    DO - 10.1364/OE.22.026884

    M3 - Article

    VL - 22

    SP - 26884

    EP - 26890

    JO - Optics Express

    JF - Optics Express

    SN - 1094-4087

    IS - 22

    ER -