Waste Management Using Convolutional Neural Network and Object Detection

Effective waste management is a global challenge, and accurate waste classification is essential for improving recycling and disposal processes. Traditional models like YOLO and VGG often struggle with complex waste types and overlapping items. In this paper, we propose a Convolutional Neural Network (CNN)-based approach to address these limitations. The CNN model captures spatial features and structural relationships, enabling accurate classification of irregular and overlapping waste items. By utilizing transfer learning and data augmentation, our model achieved an accuracy of 96.6% after 20 epochs and 98.2% after 30 epochs. This method significantly enhances classification accuracy, data efficiency, and adaptability, making it a scalable and reliable solution for automated waste management, contributing to more sustainable practices.