Published Paper Details:

Microplastic pollution has become a serious environmental issue affecting oceans, rivers, and drinking water. Detecting microplastics manually under a microscope is time-consuming, costly, and prone to human error. This paper presents a low-cost and automated microplastic detection system using an ESP32-CAM module and a Convolutional Neural Network (CNN) based deep learning model. The system captures images of water samples, processes them using image preprocessing techniques such as adaptive thresholding and morphological operations, and identifies microplastic particles automatically. In addition to detection, the system also counts the number of particles and estimates their size using pixel-to-millimeter calibration. A web-based dashboard is developed to display live streaming, detection results, confidence percentage, statistical graphs, and downloadable PDF reports. Experimental results show that the proposed system provides accurate detection with reduced processing time and lower cost compared to traditional laboratory methods. This solution can be used for real-time environmental monitoring and scalable water quality analysis.