Dataset Open Access

PCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards

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

MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <controlfield tag="005">20240222115743.0</controlfield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="a">Arbash, Elias</subfield>
    <subfield code="u">Helmholtz Institute Freiberg for Resource Technology</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">circular economy</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">automated data processing</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">optical sensors</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">recycling</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">e-waste</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">printed circuit board</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">hyperspectral</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">RGB</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">conveyor belt</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">sensors</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">machine learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">deep learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">PCBVision</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">open-source data</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">digitalization</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Fuchs, Margret</subfield>
    <subfield code="u">Helmholtz Institute Freiberg for Resource Technology</subfield>
    <subfield code="0">(orcid)0000-0001-7210-1132</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Rasti, Behnood</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Lorenz, Sandra</subfield>
    <subfield code="u">Helmholtz Institute Freiberg for Resource Technology</subfield>
    <subfield code="0">(orcid)0000-0001-8464-2331</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Ghamisi, Pedram</subfield>
    <subfield code="u">Helmholtz Institute Freiberg for Resource Technology</subfield>
    <subfield code="0">(orcid)0000-0003-1203-741X</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Gloaguen, Richard</subfield>
    <subfield code="u">Helmholtz Institute Freiberg for Resource Technology</subfield>
    <subfield code="0">(orcid)0000-0002-4383-473X</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-hzdr</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-rodare</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.14278/rodare.2704</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;&lt;strong&gt;PCB-Vision Dataset&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;Description:&lt;/p&gt;

&lt;p&gt;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.&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Data Format&lt;/strong&gt;&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;RGB Images: .png files&lt;/li&gt;
	&lt;li&gt;PCB Masks: .jpg files&lt;/li&gt;
	&lt;li&gt;HSI Data: Each hyperspectral data cube is accompanied by a data file and a .hdr file.&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;&lt;strong&gt;Folder Organization&lt;/strong&gt;&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;PCBVision
	&lt;ul&gt;
		&lt;li&gt;HSI/
		&lt;ul&gt;
			&lt;li&gt;53 subfolders (one for each PCB)&lt;/li&gt;
			&lt;li&gt;&amp;#39;General_masks&amp;#39; folder for &amp;#39;General&amp;#39; segmentation ground truth&lt;/li&gt;
			&lt;li&gt;&amp;#39;Monoseg_masks&amp;#39; folder for &amp;#39;Monoseg&amp;#39; segmentation ground truth&lt;/li&gt;
			&lt;li&gt;&amp;#39;PCB_Masks&amp;#39; folder for masks of the 53 PCBs in the hyperspectral cube&lt;/li&gt;
		&lt;/ul&gt;
		&lt;/li&gt;
		&lt;li&gt;RGB/
		&lt;ul&gt;
			&lt;li&gt;53 .jpg images&lt;/li&gt;
			&lt;li&gt;&amp;#39;General&amp;#39;&amp;nbsp;folder for RGB images &amp;#39;General&amp;#39; segmentation ground truth&lt;/li&gt;
			&lt;li&gt;&amp;#39;Monoseg_masks&amp;#39; folder for RGB images &amp;#39;Monoseg&amp;#39; segmentation ground truth&lt;/li&gt;
		&lt;/ul&gt;
		&lt;/li&gt;
	&lt;/ul&gt;
	&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;&lt;strong&gt;Data Classes in Masks&lt;/strong&gt;&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;Masks (both &amp;#39;General&amp;#39; and &amp;#39;Monoseg&amp;#39;) contain 1 to 4 segmentation classes:
	&lt;ul&gt;
		&lt;li&gt;0: &amp;quot;Others&amp;quot;&lt;/li&gt;
		&lt;li&gt;1: &amp;quot;IC&amp;quot;&lt;/li&gt;
		&lt;li&gt;2: &amp;quot;Capacitors&amp;quot;&lt;/li&gt;
		&lt;li&gt;3: &amp;quot;Connectors&amp;quot;&lt;/li&gt;
	&lt;/ul&gt;
	&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;&lt;strong&gt;Code Repository&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;To facilitate reading and working with the data, Python codes are available on the GitHub repository:&lt;/p&gt;

&lt;p&gt;https://github.com/hifexplo/PCBVision&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Citation&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;If you use this dataset, please cite the following article:&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Word&lt;/strong&gt;:&lt;/p&gt;

&lt;p&gt;Arbash, Elias, Fuchs, Margret, Rasti, Behnood, Lorenz, Sandra, Ghamisi, Pedram, &amp;amp; Gloaguen, Richard. (2024). PCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards (Version 1) [Data set]. Rodare. &lt;a href="http://doi.org/10.14278/rodare.2704"&gt;http://doi.org/10.14278/rodare.2704&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Latex:&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;@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} }&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Contact&lt;/strong&gt;&lt;/p&gt;

&lt;p&gt;For further information or inquiries, please visit our website:&lt;/p&gt;

&lt;p&gt;https://www.iexplo.space/&lt;/p&gt;

&lt;p&gt;Contact Email: e.arbash@hzdr.de&lt;/p&gt;</subfield>
  </datafield>
  <controlfield tag="001">2704</controlfield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">11392398155</subfield>
    <subfield code="u">https://rodare.hzdr.de/record/2704/files/PCBDataset.zip</subfield>
    <subfield code="z">md5:caeee8bafb7857e9bef3479d5ab3f9b4</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2024-01-29</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="a">10.48550/arXiv.2401.06528</subfield>
    <subfield code="i">isSupplementTo</subfield>
    <subfield code="n">doi</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="a">https://www.hzdr.de/publications/Publ-38684</subfield>
    <subfield code="i">isIdenticalTo</subfield>
    <subfield code="n">url</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="a">10.14278/rodare.2703</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="n">doi</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="o">oai:rodare.hzdr.de:2704</subfield>
    <subfield code="p">openaire_data</subfield>
    <subfield code="p">user-hzdr</subfield>
    <subfield code="p">user-rodare</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">PCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
167
144
views
downloads
All versions This version
Views 167167
Downloads 144144
Data volume 1.6 TB1.6 TB
Unique views 139139
Unique downloads 5454
More info on how stats are collected.
Publication date:
January 29, 2024
DOI:
10.14278/rodare.2704

RODARE DOI Badge

DOI 

10.14278/rodare.2704

Markdown 

[![DOI](https://rodare.hzdr.de/badge/DOI/10.14278/rodare.2704.svg)](https://doi.org/10.14278/rodare.2704)

reStructedText 

.. image:: https://rodare.hzdr.de/badge/DOI/10.14278/rodare.2704.svg
   :target: https://doi.org/10.14278/rodare.2704

HTML 

<a href="https://doi.org/10.14278/rodare.2704"><img src="https://rodare.hzdr.de/badge/DOI/10.14278/rodare.2704.svg" alt="DOI"></a>

Image URL 

https://rodare.hzdr.de/badge/DOI/10.14278/rodare.2704.svg

Target URL 

https://doi.org/10.14278/rodare.2704

Keyword(s):
circular economy automated data processing optical sensors recycling e-waste printed circuit board hyperspectral dataset RGB conveyor belt sensors machine learning deep learning PCBVision open-source data digitalization
Related identifiers:
Identical to:
https://www.hzdr.de/publications/Publ-38684
Supplement to:
10.48550/arXiv.2401.06528
Communities:
License (for files):
Creative Commons Attribution 4.0 International

Versions

Version 1 10.14278/rodare.2704 Jan 29, 2024
Cite all versions? You can cite all versions by using the DOI 10.14278/rodare.2703. This DOI represents all versions, and will always resolve to the latest one. Read more.

Share

Cite as

Export