A Review on Image Based Classification of Waste Material

Abstract

Recent administration of law by the Indian government for the well-being of hygiene workers has raised the need for an automatic system in waste management. The existing garbage removal system in India consists of unsystematic waste collected from homes which are then separated at manually. This separation of waste done by manual labor can bring about many health hazards and problems for the waste sorters in addition to being less efficient, time consuming and not totally feasible due to their large amount of waste. In our project, we have proposed an Image-based classification of waste material using Convolutional Neural Network (CNN) algorithm in Deep learning to classify objects as biodegradable and non-biodegradable, where the system once trained with an initial data set, can identify objects real-time and classify them almost accurately. Biodegradable waste is used to produce power, improve soil and act as food to animals. This process does not harm the earth making it valuable, ecologically safe and helps us to protect our environment, rich ecology and human inhabitants in future. Categories like glass, paper, cardboard, plastic, metal, and other trash.