December 8, 2024 Dataset Open Access

Arbash, Elias; de Lima Ribeiro, Andrea; Rizaldy, Aldino; Fuchs, Margret; Ghamisi, Pedram; Scheunders, Paul; Gloaguen, Richard

Citation Style Language JSON Export

{
  "type": "dataset", 
  "id": "3390", 
  "issued": {
    "date-parts": [
      [
        2024, 
        12, 
        8
      ]
    ]
  }, 
  "title": "Polymers Hyperspectral Imaging", 
  "author": [
    {
      "family": "Arbash, Elias"
    }, 
    {
      "family": "de Lima Ribeiro, Andrea"
    }, 
    {
      "family": "Rizaldy, Aldino"
    }, 
    {
      "family": "Fuchs, Margret"
    }, 
    {
      "family": "Ghamisi, Pedram"
    }, 
    {
      "family": "Scheunders, Paul"
    }, 
    {
      "family": "Gloaguen, Richard"
    }
  ], 
  "version": "1.0", 
  "note": "The HSI dataset of the work: INVESTIGATING STATE OF THE ART HYPERSPECTRAL IMAGING CLASSIFICATION MODELS FOR PLASTIC TYPES IDENTIFICATION", 
  "DOI": "10.14278/rodare.3390", 
  "publisher": "Rodare", 
  "abstract": "<p><strong>Investigating State of the Art Hyperspectral Imaging Classification Models for Plastic Types Identification</strong></p>\r\n\r\n<p><strong>Polymers Dataset</strong></p>\r\n\r\n<p>Description:</p>\r\n\r\n<p>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\u20132500] nm range using an AisaFENIX (Spectral Imaging Ltd, Oulu, Finland) spectrometer.\u00a0</p>\r\n\r\n<p>Two sample batches were investigated:</p>\r\n\r\n<ul>\r\n <li>reference polymers of known composition and dimensions (15 X 10) cm, commonly found in e-waste.</li>\r\n <li>shredded pieces of polymers with sizes ranging from (0.3\u20134) cm.</li>\r\n</ul>\r\n\r\n<p><strong>Data Format</strong></p>\r\n\r\n<ul>\r\n <li>HSI data: each hyperspectral data cube is accompanied by a data file and a .hdr file.</li>\r\n <li>Ground truth mask: .png file (only for multi samples scenes)</li>\r\n</ul>\r\n\r\n<p><strong>Folder Organization</strong></p>\r\n\r\n<ul>\r\n <li>Polymers\r\n <ul>\r\n  <li>Test\r\n  <ul>\r\n   <li>HSI:\u00a0.dat & .hdr</li>\r\n   <li>Ground truth mask: test.png</li>\r\n   <li>False colour representation of the scene: .png</li>\r\n  </ul>\r\n  </li>\r\n  <li>Train\r\n  <ul>\r\n   <li>HSI_ : 3 different scans of reference samples scanned</li>\r\n   <li>PC, PE, PET, PP: Hyperspectral cubes (11x11x450) .hdr & .dat</li>\r\n  </ul>\r\n  </li>\r\n </ul>\r\n </li>\r\n</ul>\r\n\r\n<p><strong>Data Classes in Masks</strong></p>\r\n\r\n<ul>\r\n <li>Masks contain 1 to 6 segmentation classes:\r\n <ul>\r\n  <li>1: \"PP\"</li>\r\n  <li>2: \"Black Plastic\"</li>\r\n  <li>3: \"PVC\"</li>\r\n  <li>4: \"PET\"</li>\r\n  <li>5: \"ABS\"</li>\r\n  <li>6: \"PE\"</li>\r\n </ul>\r\n </li>\r\n</ul>\r\n\r\n<p><strong>Code Repository</strong></p>\r\n\r\n<p>To facilitate reading and working with the data, Python codes are available on the GitHub repository:</p>\r\n\r\n<p>https://github.com/hifexplo</p>\r\n\r\n<p>https://github.com/Elias-Arbash</p>\r\n\r\n\r\n\r\n<p><strong>Citation</strong></p>\r\n\r\n<p>If you use this dataset, please cite the following article: (To be filled once published)</p>\r\n\r\n\r\n\r\n<p><strong>Contact</strong></p>\r\n\r\n<p>For further information or inquiries, please visit our website:</p>\r\n\r\n<p>https://www.iexplo.space/</p>\r\n\r\n<p>Contact Email: e.arbash@hzdr.de</p>"
}