Segregation of Plastic and Non-plastic Waste using Convolutional Neural Network

Abstract

Abstract Due to industrialization and urbanization the rapid rise in the volumeand amount of hazardous waste and the disposal of it is becoming a burgeoning problem that the world is facing today. One of the best ways out for this problem is to collect, sort and reuse or recycle these waste. So this paper proposes an architecture which sorts waste materials into plastic and non-plastic using Convolutional Neural Networks (CNN). CNN is one among the efficient machine learning techniques, which is able to provide maximum learning efficiency. This technique requires less parameter for training compared to the standard neural network. A dataset of waste materials required for our setup is collected. They are trained and tested using CNN. The proposed architecture with CNN gives an accuracy of 0.978. The proposed design also consists of a prototype, which acts as a real-time classifier. This system reduces the human efforts in separating plastics from non-plastics.