This paper proposes a particle volume reconstruction directly from an in-line hologram using a deep neural network. Digital holographic volume reconstruction conventionally uses multiple diffraction calculations to obtain sectional reconstructed images from an in-line hologram, followed by detection of the lateral and axial positions, and the sizes of particles by using focus metrics. However, the axial resolution is limited by the numerical aperture of the optical system, and the processes are time-consuming. The method proposed here can simultaneously detect the lateral and axial positions, and the particle sizes via a deep neural network (DNN). We numerically investigated the performance of the DNN in terms of the errors in the detected positions and sizes. The calculation time is faster than conventional diffracted-based approaches.
@article{arxiv.1810.09444,
title = {Digital holographic particle volume reconstruction using a deep neural network},
author = {Tomoyoshi Shimobaba and Takayuki Takahashi and Yota Yamamoto and Yutaka Endo and Atsushi Shiraki and Takashi Nishitsuji and Naoto Hoshikawa and Takashi Kakue and Tomoyosh Ito},
journal= {arXiv preprint arXiv:1810.09444},
year = {2019}
}