Microplastics detection using deep learning ensemble with vision language models
Hossain, S. M.Asif Mohona, Israt Jahan Ayrin, Fateha Jannat Rahman, Md Mizanur Chakraborty, Madhusodan Khondaker, Md Maruf Hasan Akuthota, Vishwanath Bin Saad, Sahal
Hossain, S. M.Asif
Mohona, Israt Jahan
Ayrin, Fateha Jannat
Rahman, Md Mizanur
Chakraborty, Madhusodan
Khondaker, Md Maruf Hasan
Akuthota, Vishwanath
Bin Saad, Sahal
Citations
Altmetric:
Other Names
Location
Time Period
Advisors
Original Date
Digitization Date
Issue Date
2025-05-27
Type
Conference paper
Genre
Keywords
Computer Vision,Deep Learning,Ensemble Methods,Machine Learning,Microplastics Detection,Vision Transformers
Subjects (LCSH)
Citation
S. M. A. Hossain et al., "Microplastics Detection Using Deep Learning Ensemble with Vision Language Models," 2025 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE), Dhaka, Bangladesh, 2025, pp. 43-48, doi: 10.1109/WIECON-ECE69386.2025.11525939.
Abstract
Microplastics pollution poses a significant environmental threat requiring accurate and efficient detection methods. This paper presents a novel ensemble approach combining deep learning models with Vision Language Models (VLMs) and traditional machine learning algorithms for microplastics classification, achieving unprecedented accuracy rates across multiple datasets. Our methodology integrates state-of-the-art Vision Transformers (EVA02-Large, ViT-Large, Swin-Large, BEiTLarge), advanced CNNs (EfficientNet-B7, ConvNeXt-XLarge), and traditional ML baselines (SVM, Random Forest, XGBoost) with comprehensive data augmentation, test-time augmentation (TTA), and stratified cross-validation strategies. We evaluated our hybrid approach on three comprehensive datasets: holographic imaging dataset, microplastic imaging dataset, and PS-PMMA comprehensive dataset. The Vision Language Model ensemble consistently outperformed traditional approaches, the complete hybrid ensemble with TTA achieved a an accuracy of 99.21% across all datasets. Our results demonstrate the superiority of Vision Transformers over conventional CNNs for microplastics detection, establishing new benchmarks for automated environmental monitoring systems.
Table of Contents
Description
Click on the DOI link to access this article at the publishers website (may not be free).
Publisher
IEEE