0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Environmental Sources Human Health Effects Policy & Risk Sign in to save

Automated Plastic Waste Detection Using Advanced Deep Learning Frameworks

2025
Gulam Jakaria, Md. Ferdous, Tahsin Ahmed Chowdhury, Hirak Mondal, Mrinal Kanti Baowaly

Summary

Researchers developed a deep learning system using advanced neural network frameworks for automated detection and classification of plastic waste from images, achieving high accuracy in identifying multiple plastic types to support environmental monitoring and waste sorting.

The increasing accumulation of plastic waste poses one of the most significant threats to both human health and the environment. In recent years, microplastics have been detected ubiquitously—in food, water, and even the air—emphasizing the pressing need for efficient control and monitoring methods. To address this challenge, this study presents a deep learning–based system for automated plastic waste detection from images, with the objective of improving accuracy and efficiency in identifying plastic materials. For experimentation, we used WPRD dataset (combined of WaDaBa and the Plastic Recyclable Detection dataset) and employed the YOLOv11 (You Only Look Once) object detection framework. Five major categories of plastic waste were considered: Polyethylene Terephthalate (PET), High-Density Polyethylene (PEHD), Polypropylene (PP), Polystyrene (PS), and Ultra-High Temperature (UHT) packaging. The system demonstrates strong performance, achieving high precision and recall in classifying plastic objects within diverse environmental contexts. Specifically, the YOLOv11m architecture attained a mean Average Precision (mAP) of 94.8%, underscoring the effectiveness of the proposed approach for automated plastic waste detection.

Share this paper