NIR-MFCO dataset: Near-infrared-based false-color images of post-consumer plastics at different material flow compositions and material flow presentations

Nils Kroell; Xiaozheng Chen; Abtin Maghmoumi; Julius Lorenzo; Matthias Schlaak; Christian Nordmann; Bastian Küppers; Eric Thor; Kathrin Greiff

doi:10.1016/j.dib.2023.109054

NIR-MFCO dataset: Near-infrared-based false-color images of post-consumer plastics at different material flow compositions and material flow presentations

Data Brief. 2023 Mar 14:48:109054. doi: 10.1016/j.dib.2023.109054. eCollection 2023 Jun.

Authors

Nils Kroell¹, Xiaozheng Chen¹, Abtin Maghmoumi¹, Julius Lorenzo¹, Matthias Schlaak¹, Christian Nordmann², Bastian Küppers², Eric Thor¹, Kathrin Greiff¹

Affiliations

¹ Department of Anthropogenic Material Cycles, RWTH Aachen University, Wuellnerstr. 2, Aachen D-52062, Germany.
² STADLER Anlagenbau GmbH, Max-Planck-Str. 2, Altshausen D-88361, Germany.

Abstract

Determining mass-based material flow compositions (MFCOs) is crucial for assessing and optimizing the recycling of post-consumer plastics. Currently, MFCOs in plastic recycling are primarily determined through manual sorting analysis, but the use of inline near-infrared (NIR) sensors holds potential to automate the characterization process, paving the way for novel sensor-based material flow characterization (SBMC) applications. This data article aims to expedite SBMC research by providing NIR-based false-color images of plastic material flows with their corresponding MFCOs. The false-color images were created through the pixel-based classification of binary material mixtures using a hyperspectral imaging camera (EVK HELIOS NIR G2-320; 990 nm-1678 nm wavelength range) and the on-chip classification algorithm (CLASS 32). The resulting NIR-MFCO dataset includes n = 880 false-color images from three test series: (T1) high-density polyethylene (HDPE) and polyethylene terephthalate (PET) flakes, (T2a) post-consumer HDPE packaging and PET bottles, and (T2b) post-consumer HDPE packaging and beverage cartons for n = 11 different HDPE shares (0% - 50%) at four different material flow presentations (singled, monolayer, bulk height H1, bulk height H2). The dataset can be used, e.g., to train machine learning algorithms, evaluate the accuracy of inline SBMC applications, and deepen the understanding of segregation effects of anthropogenic material flows, thus further advancing SBMC research and enhancing post-consumer plastic recycling.

Keywords: Circular economy; Computer vision; Lightweight packaging waste; Machine learning; Mechanical plastic recycling; NIR spectroscopy; Polymers; Sensor-based material flow characterization.