Rclaws: Recyclable Waste Classification System Using Convolutional Neural Network

Abstract

Waste Management is one of the common ways to manage waste generation and waste disposal. The Philippines is one of the highest ranks in terms of trash collection rates in South East Asia and the third (3rd) water resources serve as the biggest dumping areas of plastic [24].

 The use of Convolutional Neural Networks to open a new way to address this issue is to manage and lessen garbage generation every day. The application of image processing is capable to identify and monitor the garbage that can be recyclable. The system will collect useful data and categorize with the use of CNN classification. The CNN model is trained each recyclable waste materials by putting a label for test and training. The system was tested on recyclable waste materials dataset which achieved an accuracy of 96.67% on the dataset. This kind of segregation process of waste becomes faster and perceptive which can reduce human involvement in classifying recyclable materials and eventually can have an efficient and correct way of sorting recyclable materials.

Keywords: Waste, Classification, Recyclable Waste Segregation, Convolutional Neural Network, Machine Learning