Supervised and Unsupervised Textile Classification via Near-Infrared Hyperspectral Imaging and Deep Learning

TL;DR

This paper explores the use of hyperspectral near-infrared imaging combined with deep learning models, including supervised CNNs and unsupervised autoencoders, to improve textile fiber classification and recycling efficiency.

Contribution

It demonstrates the effectiveness of optimized deep learning models in generalizing across different textile structures for sustainable recycling.

Findings

CNNs and autoencoders achieve robust generalization

Hyperspectral imaging enhances classification accuracy

Deep learning models outperform traditional methods

Abstract

Recycling textile fibers is critical to reducing the environmental impact of the textile industry. Hyperspectral near-infrared (NIR) imaging combined with advanced deep learning algorithms offers a promising solution for efficient fiber classification and sorting. In this study, we investigate supervised and unsupervised deep learning models and test their generalization capabilities on different textile structures. We show that optimized convolutional neural networks (CNNs) and autoencoder networks achieve robust generalization under varying conditions. These results highlight the potential of hyperspectral imaging and deep learning to advance sustainable textile recycling through accurate and robust classification.