Journal article Embargoed Access

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

Artusi Alessandro; Banterle Francesco; Carrara Fabio; Moreo Alejandro


Citation Style Language JSON Export

{
  "DOI": "10.1109/TIP.2019.2944079", 
  "container_title": "IEEE Transactions on Image Processing", 
  "language": "eng", 
  "title": "Efficient Evaluation of Image Quality via Deep-Learning Approximation of Perceptual Metrics", 
  "issued": {
    "date-parts": [
      [
        2019, 
        10, 
        7
      ]
    ]
  }, 
  "abstract": "<p>mage metrics based on Human Visual System&nbsp;(HVS) play a remarkable role in the evaluation of complex image&nbsp;processing&nbsp; algorithms. However, mimicking the HVS is known&nbsp;to be complex and computationally expensive (both in terms&nbsp;of time and memory), and its usage is thus limited to a few&nbsp;applications and to small input data. All of this makes such&nbsp;metrics not fully attractive in real-world scenarios. To address&nbsp;these issues, we propose Deep Image Quality Metric (DIQM), a&nbsp;deep-learning approach to learn the global image quality feature&nbsp;(mean-opinion-score). DIQM can emulate existing visual metrics&nbsp;efficiently, reducing the computational costs by more than an</p>", 
  "author": [
    {
      "family": "Artusi Alessandro"
    }, 
    {
      "family": "Banterle Francesco"
    }, 
    {
      "family": "Carrara Fabio"
    }, 
    {
      "family": "Moreo Alejandro"
    }
  ], 
  "page": "1-14", 
  "note": "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 \u2013 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.", 
  "version": "Accepted pre-print", 
  "type": "article-journal", 
  "id": "3522907"
}
30
11
views
downloads
Views 30
Downloads 11
Data volume 238.0 MB
Unique views 28
Unique downloads 10

Share

Cite as