Machine learning holography for measuring 3D particle distribution

Siyao Shao, Kevin Mallery, Jiarong Hong

Research output: Contribution to journalArticlepeer-review


We propose a learning-based image processing method for particle size measurement based on digital holography in this paper. The proposed approach uses a modified U-net architecture with recorded holograms, hologram reconstructed to each longitudinal location, and minimum intensity projection in longitudinal direction as inputs to produce outputs consisting of in-focus particles at each longitudinal location and their 2D centroids. A soft generalized dice loss is used for the particle size channel and a total variation regularized mean squared error loss is employed for the 2D centroids channel. The proposed method has been assessed using synthetic, manually-labeled experimental, and real experimental holograms. The results demonstrate that our approach have better performance in comparison to the state-of-the-art non-machine-learning methods in terms of particle extraction rate and positioning accuracy. Our learning-based approach can be readily extended to other types of image-based particle size measurement tasks such as shadowgraph imaging and defocusing imaging.

Original languageEnglish (US)
Article number115830
JournalChemical Engineering Science
StatePublished - Nov 2 2020


  • Deep neural network
  • Digital inline holography
  • Image analysis
  • Machine learning
  • Particle size distribution

Fingerprint Dive into the research topics of 'Machine learning holography for measuring 3D particle distribution'. Together they form a unique fingerprint.

Cite this