Rapid Bacteria Detection
- Problem Statement: The study addresses the challenge of accurately detecting and classifying microscopic particles, specifically particulate matter and E. coli, using a novel digital inline holography setup and machine learning.
- Objectives:The primary goal of this study is to enhance particle detection and classification accuracy using modified digital inline holography.
- Project date: 15 January, 2024
- Project URL: Private GitHub Repository
Abstract
This project presents a novel approach to enhancing the detection and classification of microscopic particles, such as particulate matter and E. coli, through an advanced digital inline holography (DIH) setup and the integration of machine learning. By modifying a standard light microscope with a pulsed laser and employing a global shutter camera, we captured high-resolution images, which were then meticulously processed and labeled for machine learning analysis. Utilizing the Ultralytics YOLOv8n model, we achieved improved accuracy in real-time particle detection. The study also introduces a user-friendly graphical interface, facilitating system control and data analysis. Our methodology demonstrates significant advancements in particle imaging and classification, offering valuable insights for environmental monitoring and biomedical applications.