Abstract
As a result of great economic and social progress, domestic waste production has risen dramatically. Environmental problems will become prevalent without efficient waste management, impeding sustainable growth. Waste classification management is a critical and crucial aspect of resolving this issue. Traditional waste classification technology is inefficient and unreliable. This work presents a waste detection and classification model based on YOLOv5 to enhance the efficiency and accuracy of waste classification. To begin, the researcher obtained the Trashnet Garbage classification dataset, which has 2527 images classified as glass, metal, plastic, paper, cardboard, and trash. This study trained a YOLOv5s model for garbage detection and classification using the dataset. Finally, the performance of the trained model was evaluated. The results indicate that the YOLOv5 garbage classification model achieves an accuracy of 90.2 %, a recall of 91.6 %, and a mean average precision (mAP) of 95.2 %. The model could accurately classify all sorts of waste and achieve a high detection rate.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.