Machine Learning Holography for 3D Particle Field Imaging

TL;DR

This paper introduces a learning-based holography method using a U-net architecture to improve 3D particle field imaging, achieving higher accuracy and speed in particle localization across various concentrations.

Contribution

The paper presents a novel deep learning approach with residual U-net, Swish activation, and transfer learning for enhanced 3D particle hologram analysis, outperforming prior methods.

Findings

Significant improvement in particle extraction rate

Higher localization accuracy and speed

Effective in dense particle concentrations

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.