One-Shot learning based classification for segregation of plastic waste

TL;DR

This paper introduces a one-shot learning method using siamese and triplet loss CNNs for classifying plastic waste images, achieving high accuracy in differentiating five types of plastics based on resin codes.

Contribution

It presents a novel application of one-shot learning with deep neural networks for plastic waste classification, improving accuracy and efficiency.

Findings

Achieved 99.74% accuracy on WaDaBa database.

Effectively differentiates five types of plastic waste.

Utilizes discriminative features from CNNs for classification.

Abstract

The problem of segregating recyclable waste is fairly daunting for many countries. This article presents an approach for image based classification of plastic waste using one-shot learning techniques. The proposed approach exploits discriminative features generated via the siamese and triplet loss convolutional neural networks to help differentiate between 5 types of plastic waste based on their resin codes. The approach achieves an accuracy of 99.74% on the WaDaBa Database