Deep Learning Approaches for Microplastic Identification in Microscopic Water Samples

DOI

10.2991/978-94-6239-616-6_63How to use a DOI?

Keywords

Microplastic Detection; Deep Learning; Faster R-CNN; ROI Filtering; HRAMD Framework

Abstract

Water sources are increasingly threatened by pollution from rapid urbanization, industrial discharge, and agricultural runoff, which introduce harmful contaminants into aquatic ecosystems. Due to their durability, irregular morphology, and possible hazards to the environment and human health, microplastics have become a significant issue among pollutants. A deep learning approach is used to improve the precision and dependability of microplastic identification in microscopic water samples. To address the challenge of detecting microplastics in complex microscopic water images, a Hybrid ROI-Aware Microplastic Detection (HRAMD) framework is proposed. A ResNet-50 FPN backbone is used for feature extraction and bounding box creation in Faster R-CNN for high-resolution droplet photos. The HRAMD method applies Region Of Interest (ROI) refinement to filter out irrelevant background noise, ensuring that only microplastics within the droplet area are considered for analysis. The contamination level is then quantified by calculating the percentage of microplastic area relative to the droplet region, with experimental evaluation yielding an overall average contamination level of 13.13%. This combination of visual bounding box detection and quantitative assessment establishes a transparent and interpretable framework for microplastic monitoring, offering a scalable solution for water quality assessment and sustainable resource management.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - J. Rajeswari
AU  - B. Ashok Kumar
AU  - S. Senthilrani
AU  - S. Amrudha
AU  - M. Annie Pushpa
AU  - S. Thamarai Natchiyar
PY  - 2026
DA  - 2026/03/31
TI  - Deep Learning Approaches for Microplastic Identification in Microscopic Water Samples
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 837
EP  - 847
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_63
DO  - 10.2991/978-94-6239-616-6_63
ID  - Rajeswari2026
ER  -