Journal article Embargoed Access

Efficient Evaluation of Image Quality via Deep-Learning Approximation of Perceptual Metrics

Artusi Alessandro; Banterle Francesco; Carrara Fabio; Moreo Alejandro


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="URL">https://zenodo.org/record/3522907</identifier>
  <creators>
    <creator>
      <creatorName>Artusi Alessandro</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-4502-663X</nameIdentifier>
      <affiliation>MRG DeepCamera Group, RISE Ltd</affiliation>
    </creator>
    <creator>
      <creatorName>Banterle Francesco</creatorName>
      <affiliation>ISTI CNR, Italy</affiliation>
    </creator>
    <creator>
      <creatorName>Carrara Fabio</creatorName>
      <affiliation>ISTI CNR, Italy</affiliation>
    </creator>
    <creator>
      <creatorName>Moreo Alejandro</creatorName>
      <affiliation>ISTI CNR, Italy</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Efficient Evaluation of Image Quality via Deep-Learning Approximation of Perceptual Metrics</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <subjects>
    <subject>Convolutional Neural Networks (CNNs)</subject>
    <subject>Objective Metrics</subject>
    <subject>Image Evaluation</subject>
    <subject>Human Visual System</subject>
    <subject>JPEG-XT</subject>
    <subject>HDR Imaging</subject>
  </subjects>
  <dates>
    <date dateType="Available">2021-10-07</date>
    <date dateType="Accepted">2019-10-07</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Text">Journal article</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3522907</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1109/TIP.2019.2944079</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/rise-teaming-cyprus</relatedIdentifier>
  </relatedIdentifiers>
  <version>Accepted pre-print</version>
  <rightsList>
    <rights rightsURI="http://creativecommons.org/licenses/by-nc-nd/4.0/legalcode">Creative Commons Attribution Non Commercial No Derivatives 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/embargoedAccess">Embargoed Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;mage metrics based on Human Visual System&amp;nbsp;(HVS) play a remarkable role in the evaluation of complex image&amp;nbsp;processing&amp;nbsp; algorithms. However, mimicking the HVS is known&amp;nbsp;to be complex and computationally expensive (both in terms&amp;nbsp;of time and memory), and its usage is thus limited to a few&amp;nbsp;applications and to small input data. All of this makes such&amp;nbsp;metrics not fully attractive in real-world scenarios. To address&amp;nbsp;these issues, we propose Deep Image Quality Metric (DIQM), a&amp;nbsp;deep-learning approach to learn the global image quality feature&amp;nbsp;(mean-opinion-score). DIQM can emulate existing visual metrics&amp;nbsp;efficiently, reducing the computational costs by more than an&lt;/p&gt;</description>
    <description descriptionType="Other">This work has been partly supported by the project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 739578 (RISE – Call: H2020-WIDESPREAD-01-2016-2017-TeamingPhase2) and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/739578/">739578</awardNumber>
      <awardTitle>Research Center on Interactive Media, Smart System and Emerging Technologies</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
30
11
views
downloads
Views 30
Downloads 11
Data volume 238.0 MB
Unique views 28
Unique downloads 10

Share

Cite as