Deep learning-based waste classification system for efficient waste management

Abstract

A smart waste management system plays a vital role in building cleanliness, hygienic, and healthier living for the inhabitants of a city. However, the inherent problems of the waste management system are still a matter of great concern even amid this cutting edge of science and technologies. The root cause of this problem points to one fact - which is too much manual labor in the garbage collection, separation, and recycling process. In this research, we have used the Deep Learning-based model ‘Mask R-CNN’ to detect and classify Kitchen Waste, Glass Waste, Metal Waste, Paper Waste, and Plastic Waste from garbage dump waste images for the automation of the waste management system. We have also used the Explainable AI algorithm ‘Grad-CAM’ to introduce explainability to our model which helped to identify the most important features of each object and understand decisions of Mask R-CNN. Mask R-CNN model achieved 92.58% accuracy in classifying the 5 waste categories.