MURAL - Maynooth University Research Archive Library



    Deep convolutional neural networks and digital holographic microscopy for in-focus depth estimation of microscopic objects


    Pitkäaho, Tomi and Manninen, Aki and Naughton, Thomas J. (2017) Deep convolutional neural networks and digital holographic microscopy for in-focus depth estimation of microscopic objects. In: Irish Machine Vision and Image Processing Conference Proceedings 2017. Irish Pattern Recognition & Classification Society, pp. 52-59. ISBN 978-0-9934207-2-6

    [img]
    Preview
    Download (317kB) | Preview


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    Deep artificial neural network learning is an emerging tool in image analysis. We demonstrate its poten- tial in the field of digital holographic microscopy by addressing the challenging problem of determining the in-focus reconstruction depth of an arbitrary epithelial cell cluster encoded in a digital hologram. A deep convolutional neural network learns the in-focus depths from half a million hologram amplitude images. The trained network correctly determines the in-focus depth of new holograms with high probability, with- out performing numerical propagation. To our knowledge, this is the first application of deep learning in the field of digital holographic microscopy.

    Item Type: Book Section
    Additional Information: This paper was presented at the 19th Irish Machine Vision and Image Processing conference (IMVIP 2017) Aug 30th-Sept 1st, 2017, Maynooth, Ireland.
    Keywords: Imaging; Digital Holographic Microscopy; Autofocusing; Deep Learning; Machine Learning;
    Academic Unit: Faculty of Science and Engineering > Computer Science
    Faculty of Science and Engineering > Research Institutes > Hamilton Institute
    Item ID: 12049
    Depositing User: Thomas Naughton
    Date Deposited: 18 Dec 2019 16:16
    Publisher: Irish Pattern Recognition & Classification Society
    Refereed: Yes
    URI:

    Repository Staff Only(login required)

    View Item Item control page

    Downloads

    Downloads per month over past year