Classification of Organic and Solid Waste Using Deep Convolutional Neural Networks

The total amount of waste is increasing all around the world day-by-day especially in urban areas. The increasing amount of unprocessed waste is very dangerous to mankind as it creates severe pollution in the environment. Most of this wastage is recyclable. For recycling, the waste needs to be separated at first, as different types of waste require different recycling techniques. But unfortunately, categorizing waste manually is very costly and time-consuming. So, in this work, a method is proposed to automatically classify waste into four categories. For this, a dataset named OrgalidWaste is prepared by collecting images from four other waste datasets. The prepared dataset contains around 5600 images with four classes including one organic waste class and three solid waste classes (glass, metal, and plastic). On this dataset, several CNN architectures including 3-layer CNN, VGG16, VGG19, Inception-V3, and ResNet50 have been implemented for training. Among them, VGG16 outperforms other models with 88.42% accuracy. It is believed that this work will be greatly beneficial in the waste management sector.