Skip to main content

ORIGINAL RESEARCH article

Front. Chem. Eng.
Sec. Separation Processes
Volume 6 - 2024 | doi: 10.3389/fceng.2024.1415453
This article is part of the Research Topic Solvent Extraction Pathways to Sustainable Industrial Processes: New Solvents, Modelling, and Design Methods View all 4 articles

BYG-Drop, a tool for enhanced droplet detection in liquid-liquid systems through machine learning and synthetic imaging

Provisionally accepted
Grégory Bana Grégory Bana 1,2,3Fabrice Lamadie Fabrice Lamadie 1*Sophie Charton Sophie Charton 1Tojonirina Randriamanantena Tojonirina Randriamanantena 1Didier Lucor Didier Lucor 3Nida Sheibat-Othman Nida Sheibat-Othman 2
  • 1 CEA Marcoule, Bagnols-sur-Cèze, France
  • 2 Université Claude Bernard Lyon 1, Lyon, Rhône-Alpes, France
  • 3 Other, Paris - Saclay, France

The final, formatted version of the article will be published soon.

    A new image processing machine learning algorithm for droplet detection in liquid-liquid systems is introduced. The method combines three key numerical tools: YOLOv5 for object detection, Blender for synthetic image generation, and CycleGAN for image texturing. Consequently, it was named BYG-Drop for Blender-YOLO-cycleGAn droplet detection. BYG-Drop outperforms traditional image processing techniques in both accuracy and number of droplets detected in digital test cases. When applied to experimental images, it remains consistent with established techniques such as laser diffraction, while outperforming other image processing techniques in droplet detection accuracy. In addition, the use of synthetic images for training provides advantages such as training on a large labeled dataset, which prevents false detections.CycleGAN's texturing also allows quick adaptation to different fluid systems, increasing the versatility of image processing in drop size distribution measurement. Finally, the processing time per image is significantly faster with this approach.

    Keywords: Droplet detection, machine learning, Convolutional neural networks (CNNs), generative adversarial networks (GANs), Liquid-liquid emulsion, Droplet size distribution

    Received: 10 Apr 2024; Accepted: 19 Jun 2024.

    Copyright: © 2024 Bana, Lamadie, Charton, Randriamanantena, Lucor and Sheibat-Othman. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Fabrice Lamadie, CEA Marcoule, Bagnols-sur-Cèze, France

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.