Robotics & Machine Learning Daily News2024,Issue(Aug.28) :82-83.

University of Montpellier Researchers Report Research in Machine Learning (BYG-d rop: a tool for enhanced droplet detection in liquid-liquid systems through mach ine learning and synthetic imaging)

Robotics & Machine Learning Daily News2024,Issue(Aug.28) :82-83.

University of Montpellier Researchers Report Research in Machine Learning (BYG-d rop: a tool for enhanced droplet detection in liquid-liquid systems through mach ine learning and synthetic imaging)

扫码查看

Abstract

By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Current study results on artificial in telligence have been published. According to newsreporting from Bagnols sur Cez e, France, by NewsRx journalists, research stated, “A new image processingmachi ne learning algorithm for droplet detection in liquid-liquid systems is here int roduced.”Our news journalists obtained a quote from the research from University of Montp ellier: “The methodcombines three key numerical tools-YOLOv5 for object detecti on, Blender for synthetic image generation,and CycleGAN for image texturing-and was named ‘BYG-Drop for Blender-YOLO-CycleGAn’ droplet detection.BYG-Drop outp erforms traditional image processing techniques in both accuracy and number ofd roplets detected in digital test cases. When applied to experimental images, it remains consistent withestablished techniques such as laser diffraction while o utperforming other image processing techniques indroplet detection accuracy. Th e use of synthetic images for training also provides advantages such astraining on a large labeled dataset, which prevents false detections. CycleGAN’s texturi ng also allows quickadaptation to different fluid systems, increasing the versa tility of image processing in drop size distributionmeasurement.”

Key words

University of Montpellier/Bagnols sur C eze/France/Europe/Cyborgs/Emerging Technologies/Machine Learning

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
段落导航相关论文