January 29, 2024 Dataset Open Access

Arbash, Elias; Fuchs, Margret; Rasti, Behnood; Lorenz, Sandra; Ghamisi, Pedram; Gloaguen, Richard

Citation Style Language JSON Export

{
  "DOI": "10.14278/rodare.2704", 
  "abstract": "<p><strong>PCB-Vision Dataset</strong></p>\n\n<p>Description:</p>\n\n<p>The PCB-Vision dataset is a multiscene RGB-Hyperspectral benchmark dataset comprising 53 Printed Circuit Boards (PCBs). The RGB images are collected using a Teledyne Dalsa C4020 camera on a conveyor belt, while hyperspectral images (HSI) are acquired with a Specim FX10 spectrometer. The HSI data contains 224 bands in the VNIR range [400 - 1000]nm.</p>\n\n<p><strong>Data Format</strong></p>\n\n<ul>\n\t<li>RGB Images: .png files</li>\n\t<li>PCB Masks: .jpg files</li>\n\t<li>HSI Data: Each hyperspectral data cube is accompanied by a data file and a .hdr file.</li>\n</ul>\n\n<p><strong>Folder Organization</strong></p>\n\n<ul>\n\t<li>PCBVision\n\t<ul>\n\t\t<li>HSI/\n\t\t<ul>\n\t\t\t<li>53 subfolders (one for each PCB)</li>\n\t\t\t<li>&#39;General_masks&#39; folder for &#39;General&#39; segmentation ground truth</li>\n\t\t\t<li>&#39;Monoseg_masks&#39; folder for &#39;Monoseg&#39; segmentation ground truth</li>\n\t\t\t<li>&#39;PCB_Masks&#39; folder for masks of the 53 PCBs in the hyperspectral cube</li>\n\t\t</ul>\n\t\t</li>\n\t\t<li>RGB/\n\t\t<ul>\n\t\t\t<li>53 .jpg images</li>\n\t\t\t<li>&#39;General&#39;&nbsp;folder for RGB images &#39;General&#39; segmentation ground truth</li>\n\t\t\t<li>&#39;Monoseg_masks&#39; folder for RGB images &#39;Monoseg&#39; segmentation ground truth</li>\n\t\t</ul>\n\t\t</li>\n\t</ul>\n\t</li>\n</ul>\n\n<p><strong>Data Classes in Masks</strong></p>\n\n<ul>\n\t<li>Masks (both &#39;General&#39; and &#39;Monoseg&#39;) contain 1 to 4 segmentation classes:\n\t<ul>\n\t\t<li>0: &quot;Others&quot;</li>\n\t\t<li>1: &quot;IC&quot;</li>\n\t\t<li>2: &quot;Capacitors&quot;</li>\n\t\t<li>3: &quot;Connectors&quot;</li>\n\t</ul>\n\t</li>\n</ul>\n\n<p><strong>Code Repository</strong></p>\n\n<p>To facilitate reading and working with the data, Python codes are available on the GitHub repository:</p>\n\n<p>https://github.com/hifexplo/PCBVision</p>\n\n<p><strong>Citation</strong></p>\n\n<p>If you use this dataset, please cite the following article:</p>\n\n<p><strong>Word</strong>:</p>\n\n<p>Arbash, Elias, Fuchs, Margret, Rasti, Behnood, Lorenz, Sandra, Ghamisi, Pedram, &amp; Gloaguen, Richard. (2024). PCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards (Version 1) [Data set]. Rodare. <a href=\"http://doi.org/10.14278/rodare.2704\">http://doi.org/10.14278/rodare.2704</a></p>\n\n<p><strong>Latex:</strong></p>\n\n<p>@article{arbash2024pcb, title={PCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards}, author={Arbash, Elias and Fuchs, Margret and Rasti, Behnood and Lorenz, Sandra and Ghamisi, Pedram and Gloaguen, Richard}, journal={arXiv preprint arXiv:2401.06528}, year={2024} }</p>\n\n<p><strong>Contact</strong></p>\n\n<p>For further information or inquiries, please visit our website:</p>\n\n<p>https://www.iexplo.space/</p>\n\n<p>Contact Email: e.arbash@hzdr.de</p>", 
  "issued": {
    "date-parts": [
      [
        2024, 
        1, 
        29
      ]
    ]
  }, 
  "type": "dataset", 
  "author": [
    {
      "family": "Arbash, Elias"
    }, 
    {
      "family": "Fuchs, Margret"
    }, 
    {
      "family": "Rasti, Behnood"
    }, 
    {
      "family": "Lorenz, Sandra"
    }, 
    {
      "family": "Ghamisi, Pedram"
    }, 
    {
      "family": "Gloaguen, Richard"
    }
  ], 
  "version": "1", 
  "publisher": "Rodare", 
  "id": "2704", 
  "title": "PCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards"
}