Abstract

This paper proposes a particle volume reconstruction directly from an in-line hologram using a deep neural network (DNN). 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 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.

© 2019 Optical Society of America

Focus prediction in digital holographic microscopy using deep convolutional neural networks

Tomi Pitkäaho, Aki Manninen, and Thomas J. Naughton
Appl. Opt. 58(5) A202-A208 (2019)

Holographic 3D particle reconstruction using a one-stage network

Yunping Zhang, Yanmin Zhu, and Edmund Y. Lam
Appl. Opt. 61(5) B111-B120 (2022)

Fast particle characterization using digital holography and neural networks

B. Schneider, J. Dambre, and P. Bienstman
Appl. Opt. 55(1) 133-139 (2016)

Accurate detection of small particles in digital holography using fully convolutional networks

Xuecheng Wu, Xinwen Li, Longchao Yao, Yingchun Wu, Xiaodan Lin, Linghong Chen, and Kefa Cen
Appl. Opt. 58(34) G332-G344 (2019)

Digital holography of particle fields: reconstruction by use of complex amplitude

Gang Pan and Hui Meng
Appl. Opt. 42(5) 827-833 (2003)