E-waste classification and recycle using deep learning

Abstract

The ability to efficiently recycle the electronic waste found in trash can increase the usefulness of e-waste management systems. Separating e-waste from other wastes in the rubbish is crucial for recycling. Our objective is to construct a model that utilizes image processing techniques to effectively separate electronic waste from regular garbage. Consequently, we have created a model by implementing two image processing algorithms: Support Vector Machine (SVM) and Convolutional Neural Network (CNN). Subsequently, we assessed the precision of each model on our collection of images. The image dataset we possess comprises unprocessed images that we have personally shot from several situations. Our main objective was to identify e-waste, hence the photographs we collected predominantly consist of used electronic equipment, rather than brand-new gadgets that have not been previously used. After examining the algorithmic output, we discovered that, for our model, the CNN algorithm outperforms the SVM method