Answers are grounded in this paper and cite their sources.
Microplastic pollution has emerged as a critical environmental challenge due to its widespread presence in aquatic ecosystems and its adverse effects on biodiversity and human health.Conventional laboratory analysis of microplastics relies on manual examination of microscope images, which is labour-intensive, time-consuming, and susceptible to human error.This paper proposes a CNN-Based Intelligent System for Microplastic Detection and Analysis in Aquatic Systems, a software-oriented platform that automates the detection, classification, analysis, and reporting of microplastic particles from laboratory-acquired microscope images.The proposed system employs OpenCV-based image preprocessing to enhance image quality, followed by a YOLO-based object detection model for particle localization and a Convolutional Neural Network (CNN) for classifying detected particles into categories such as Fiber, Fragment, Film, Foam, and Pellet.The platform further estimates particle count, size, confidence scores, and contamination severity using a pollution assessment engine.A web-based application developed using React, FastAPI, and PostgreSQL provides secure data management, historical analysis, interactive visualizations, and automated PDF and CSV report generation.The proposed system aims to improve the efficiency, consistency, and traceability of microplastic analysis, offering a practical decision-support tool for environmental laboratories, researchers, and water quality monitoring agencies.
No takes yet. Share an insight, caveat, or question.
N et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: