Automatic Detection of 'ROIs' for Plastic Bottle Classification

Abstract

Recycling is widely assumed to be environmentally beneficial, although the collection, sorting and processing of materials gives rise to some environmental impacts and energy use. Previously, plastic recycling are based on the material used. In this work, we propose a new approach to classify plastic bottle by implementing the viability of imaging technology for automated sorting. According to the original image of plastic bottle, there are obvious features that can discriminate between 2 classes of plastic bottles which are PET and Non-PET. The methodology involves an automatic detection of 'ROIs' from region segmented technique and proposed the histogram of pixel intensity algorithm in order to differentiate between 2 class of bottle; i.e PET and non-PET according to the property of transparency and opacity. The proposed technique shows ability to perform plastic bottle classification with more than 80% accuracy was obtained from this research.