Machine learning shadowgraph for particle size and shape characterization

Jiaqi Li, Siyao Shao, Jiarong Hong

Research output: Contribution to journalArticlepeer-review

17 Scopus citations


Conventional image processing for a particle shadow image is usually time-consuming and suffers degraded image segmentation when dealing with images consisting of complex-shaped and clustered particles with varying backgrounds. In this paper, we introduce a robust learning-based method using a single convolution neural network for analyzing particle shadow images. Our approach employs a two-channel-output U-net model to generate a binary particle image and a particle centroid image. The binary particle image is subsequently segmented through a marker-controlled watershed approach with the particle centroid image as the marker image. The assessment of this method on both synthetic and experimental bubble images has exhibited a better performance compared to the state-of-art non-machine-learning method. The proposed machine learning shadow image processing approach provides a promising tool for real-time particle image analysis in industrial applications.

Original languageEnglish (US)
Article number015406
JournalMeasurement Science and Technology
Issue number1
StatePublished - Jan 2021

Bibliographical note

Publisher Copyright:
© 2020 IOP Publishing Ltd Printed in the UK


  • Convolution neural network
  • Image segmentation
  • Particle shadow image
  • Particle size distribution


Dive into the research topics of 'Machine learning shadowgraph for particle size and shape characterization'. Together they form a unique fingerprint.

Cite this