Polymers Hyperspectral Imaging

2026-06-13T03:49:12Z https://rodare.hzdr.de/oai2d

oai:rodare.hzdr.de:3390 2025-02-19T07:28:48Z openaire_data user-hzdr user-rodare

true 3.1 HZDR.RODARE 10.14278/rodare.3390 Arbash, Elias 0009-0000-2187-9171 Helmholtz Institute Freiberg de Lima Ribeiro, Andrea 0000-0003-0096-3627 Helmholtz Institute Freiberg Rizaldy, Aldino 0009-0004-4138-7878 Helmholtz Institute Freiberg Fuchs, Margret 0000-0001-7210-1132 Helmholtz Institute Freiberg Ghamisi, Pedram 0000-0003-1203-741X Helmholtz Institute Freiberg Scheunders, Paul 0000-0003-2447-4772 University of Antwerp Gloaguen, Richard 0000-0002-4383-473X Helmholtz Institute Freiberg Polymers Hyperspectral Imaging Rodare 2024 Hyperspectral Image Classification Plastic Polymers E-waste Deep Learning Machine Learning 2024-12-08 https://rodare.hzdr.de/record/3390 https://www.hzdr.de/publications/Publ-40592 https://www.hzdr.de/publications/Publ-40590 10.14278/rodare.3389 https://rodare.hzdr.de/communities/hzdr https://rodare.hzdr.de/communities/rodare 1.0 Creative Commons Attribution 4.0 International Open Access Investigating State of the Art Hyperspectral Imaging Classification Models for Plastic Types Identification Polymers Dataset Description: The polymers dataset is a multiscene Hyperspectral benchmark dataset comprising of reference polymer samples and shredded polymer samples in the visible to short-wave infrared, capturing 450 bands within the [400–2500] nm range using an AisaFENIX (Spectral Imaging Ltd, Oulu, Finland) spectrometer. Two sample batches were investigated: <ul> <li>reference polymers of known composition and dimensions (15 X 10) cm, commonly found in e-waste.</li> <li>shredded pieces of polymers with sizes ranging from (0.3–4) cm.</li> </ul> Data Format <ul> <li>HSI data: each hyperspectral data cube is accompanied by a data file and a .hdr file.</li> <li>Ground truth mask: .png file (only for multi samples scenes)</li> </ul> Folder Organization <ul> <li>Polymers <ul> <li>Test <ul> <li>HSI: .dat & .hdr</li> <li>Ground truth mask: test.png</li> <li>False colour representation of the scene: .png</li> </ul> </li> <li>Train <ul> <li>HSI_ : 3 different scans of reference samples scanned</li> <li>PC, PE, PET, PP: Hyperspectral cubes (11x11x450) .hdr & .dat</li> </ul> </li> </ul> </li> </ul> Data Classes in Masks <ul> <li>Masks contain 1 to 6 segmentation classes: <ul> <li>1: "PP"</li> <li>2: "Black Plastic"</li> <li>3: "PVC"</li> <li>4: "PET"</li> <li>5: "ABS"</li> <li>6: "PE"</li> </ul> </li> </ul> Code Repository To facilitate reading and working with the data, Python codes are available on the GitHub repository: https://github.com/hifexplo https://github.com/Elias-Arbash Citation If you use this dataset, please cite the following article: (To be filled once published) Contact For further information or inquiries, please visit our website: https://www.iexplo.space/ Contact Email: e.arbash@hzdr.de The HSI dataset of the work: INVESTIGATING STATE OF THE ART HYPERSPECTRAL IMAGING CLASSIFICATION MODELS FOR PLASTIC TYPES IDENTIFICATION