Published in Scientific Papers. Series E. Land Reclamation, Earth Observation & Surveying, Environmental Engineering, Vol. XIII
Written by Dan Constantin PUCHIANU
The integration of advanced deep-learning techniques and object detection architectures represents an advanced methodology for waste detection. Considering the importance of recycling and environmental protection in sustainable waste management, automation of such processes becomes an essential task to improve efficiency and accuracy in various industrial and environmental applications. In this study, a system based on convolutional neural networks is proposed for the identification and classification of different types of waste, such as paper, metal, plastic, or glass. An extensive dataset was used to train and evaluate the proposed models using digital RGB images. Following the experimental results, the implementations of this study demonstrated a detection accuracy of over 90%, highlighting the effectiveness of these models and providing modern solutions for correct waste management and manual sorting errors. Efficient recycling is important for ensuring good environmental sustainability practices and automating the process using deep-learning systems is an important step in this direction.
[Read full article] [Citation]
