Answers are grounded in this paper and cite their sources.
Microplastic contamination in drinking water has become an increasing environmental and health concern due to the widespread use and degradation of plastic materials. Conventional techniques such as Fourier Transform Infrared Spectroscopy (FTIR), Raman Spectroscopy, and Scanning Electron Microscopy (SEM) provide accurate identification, but they require expensive laboratory equipment, trained personnel, and considerable time, making them unsuitable for routine monitoring. This paper presents an automated optical detection and monitoring architecture for potential microplastic particles in water using microscopic imaging and computer vision. A water sample is pumped through a micro-filtration setup (20–50 µm membrane) using a peristaltic pump monitored by a flow sensor for precise volume measurement. The retained particles are imaged under a digital microscope with LED back-illumination, and the captured images are processed using a fine-tuned YOLOv8n object detection model. Real-time diagnostics, particle counts per liter, and confidence scores are presented on a local display and synchronized to a web platform dashboard (built with React.js and Node.js). A literature review shows that existing systems lack low-cost edge deployment with high-throughput filtration and web analytics, motivating the proposed design. The paper presents the problem definition, objectives, system architecture, methodology, expected benefits, and experimental results
No takes yet. Share an insight, caveat, or question.
SP et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: