Journal of Spectral Imaging,   Volume 8   Article ID a17   (2019)

Peer reviewed Paper

Hyperspectral imaging for textile sorting in the visible–near infrared range

  • Carolina Blanch-Perez-del-Notario
  • Wouter Saeys
  • Andy Lambrechts
Division of Mechatronics, Biostatistics and Sensors, KU Leuven, 3001, Leuven, Belgium

 https://orcid.org/0000-0002-5849-4301
 Search for papers by this author
Imec, Kapeldreef 75, 3001, Leuven, Belgium

 Search for papers by this author
 Corresponding Author
Imec, Kapeldreef 75, 3001, Leuven, Belgium and Division of Mechatronics, Biostatistics and Sensors, KU Leuven, 3001, Leuven, Belgium
[email protected]
 Search for papers by this author

Recycling of textile materials is becoming important due to the increasing amount of textile waste and its large environmental impact. The Resyntex project aims at dealing with this textile waste by enabling its chemical recycling. To do so, pure textile materials and blends need to be sorted first. In this paper we evaluate the suitability of hyperspectral imaging for pure and blend textile sorting. We also test the discrimination capacity between denim and non-denim textile, since this is required prior to the de-colouration processes. For this purpose, we use a line-scan sensor in the 450–950 nm range, since its cost, compactness and speed characteristics make it suitable for industrial deployment. To deal with the strong colour interference of the textile a hierarchical classification approach is proposed. The results on the available sample set show promising discrimination potential for material discrimination as well as for denim versus non-denim detection.

Keywords: vis-NIR spectral response, textile material, colour classification

Metrics

Downloads:

247

Full-Text HTML Views:

39

Abstract Views:

2,051