Abstract
Three-dimensional particle positioning from inline holograms is performed using convolutional neural networks. The faster R-CNN architecture is implemented for multi-particle identification and lateral positioning, and a second network estimates the depth position. Supervised learning is used to train the network using simulated holograms.
© 2020 The Author(s)
PDF ArticleMore Like This
M. Hossein Eybposh, Nicholas W. Caira, Praneeth Chakravarthula, Mathew Atisa, and Nicolas C. Pégard
BTu2C.2 Optics and the Brain (BRAIN) 2020
Jun Rong Ong, Chin Chun Ooi, Thomas Y. L. Ang, Flynn Loh, Yu Xiang Peh, Soon Thor Lim, and Ching Eng Png
PsTh1F.2 Photonics in Switching and Computing (PS) 2020
Siddharth Varughese, Daniel A. Garon, Alirio Melgar, Varghese A. Thomas, Pavel Zivny, Shane Hazzard, and Stephen E. Ralph
W4F.4 Optical Fiber Communication Conference (OFC) 2020