Machine Learning Holography for 3D Particle Field Imaging

Abstract

We propose a new learning-based approach for 3D particle field imaging using holography. Our approach uses a U-net architecture incorporating residual connections, Swish activation, hologram preprocessing, and transfer learning to cope with challenges arising in particle holograms where accurate measurement of individual particles is crucial. Assessments on both synthetic and experimental holograms demonstrate a significant improvement in particle extraction rate, localization accuracy and speed compared to prior methods over a wide range of particle concentrations, including highly-dense concentrations where other methods are unsuitable. Our approach can be potentially extended to other types of computational imaging tasks with similar features.

12 pages, 7 figures

References in corpus (5)

• Phase recovery and holographic image reconstruction using deep learning in neural networks
• Searching for Activation Functions
• Deep learning-based color holographic microscopy
• Regularized Inverse Holographic Volume Reconstruction for 3D Particle Tracking
• Total 3D imaging of phase objects using defocusing microscopy: application to red blood cells

Cited by in corpus (1)

• Machine learning holography for measuring 3D particle size distribution