Benchmarking Deep Learning Models For Automated Waste Classification

Recycling is essential for reducing waste, conserving resources, and promoting a more sustainable and efficient use of materials. However, manual sorting is inefficient, prone to human error, and limits recycling efficiency. This study develops an automated waste sorting system using image recognition and deep learning to enhance recycling efficiency and accessibility.

To achieve this, three deep learning models-google/vit-base-patch16-224, Falconsai/nsfw image detection, and microsoft/resnet-50 -are compared to determine the most suitable one based on accuracy and computational efficiency. The selected model powers an intelligent recycling system that uses image recognition to efficiently categorize waste, reducing costs, enhancing material value, and supporting large-scale waste management. This research highlights the potential of AI-driven sorting to improve recycling, reduce environmental impact, and promote sustainability.