Technical feasibility study of an instrument for optical sorting of textiles

The project aimed to propose a preliminary architecture of an optical sorting system for the development and integration into a value chain of an automated clothing sorting system. The value chain related to clothing sorting and recycling involves technological, economic, and social challenges. This project focused on developing the technological aspect in order to facilitate the establishment of the ecosystem required to implement this value chain, from collection to textile recovery.

Project conclusions:

Near-infrared spectroscopy is very popular, as demonstrated by the numerous publications on the subject. It is robust, easy to implement, and provides highly accurate classification results when combined with machine learning algorithms. Applied in this project, the spectroscopic measurement tools and algorithmic methods developed and used proved to be very effective for textile optical sorting. Classification rates of 100% were achieved on pure samples of wool, silk, cotton, and polyester, as well as on blended fibers in this preliminary study. Thanks to the performance of the spectral and algorithmic analysis, doubts were even raised regarding the composition of several samples.