Application of Computer Vision Techniques for Segregation of PlasticWaste based on Resin Identification Code

TL;DR

This paper explores machine learning methods, including one-shot learning and dimensionality reduction, to identify known and unknown plastic waste types based on resin codes, enhancing recycling efficiency.

Contribution

It introduces novel ML approaches for plastic waste identification, achieving high accuracy without data augmentation for known types and effective detection of new types.

Findings

Achieved 99.74% accuracy in identifying known plastic waste categories.

Achieved 95% accuracy in recognizing new plastic waste types.

Demonstrated effectiveness of Siamese and Triplet networks for waste classification.

Abstract

This paper presents methods to identify the plastic waste based on its resin identification code to provide an efficient recycling of post-consumer plastic waste. We propose the design, training and testing of different machine learning techniques to (i) identify a plastic waste that belongs to the known categories of plastic waste when the system is trained and (ii) identify a new plastic waste that do not belong the any known categories of plastic waste while the system is trained. For the first case,we propose the use of one-shot learning techniques using Siamese and Triplet loss networks. Our proposed approach does not require any augmentation to increase the size of the database and achieved a high accuracy of 99.74%. For the second case, we propose the use of supervised and unsupervised dimensionality reduction techniques and achieved an accuracy of 95% to correctly identify a new plastic waste.