{
  "id": "1602.05531",
  "version": "v1",
  "published": "2016-02-17T19:12:50.000Z",
  "updated": "2016-02-17T19:12:50.000Z",
  "title": "On the Use of Deep Learning for Blind Image Quality Assessment",
  "authors": [
    "Simone Bianco",
    "Luigi Celona",
    "Paolo Napoletano",
    "Raimondo Schettini"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "In this work we investigate the use of deep learning for distortion-generic blind image quality assessment. We report on different design choices, ranging from the use of features extracted from pre-trained Convolutional Neural Networks (CNNs) as a generic image description, to the use of features extracted from a CNN fine-tuned for the image quality task. Our best proposal, named DeepBIQ, estimates the image quality by aver- age pooling the scores predicted on multiple sub-regions of the original image. The score of each sub-region is computed using a Support Vector Regression (SVR) machine taking as input features extracted using a CNN fine-tuned for category-based image quality assessment. Experimental results on the LIVE In the Wild Image Quality Challenge Database show that DeepBIQ outperforms the state-of-the-art methods compared, having a Linear Correlation Coefficient (LCC) with human subjective scores of almost 0.91. Furthermore, in many cases, the quality score predictions of DeepBIQ are closer to the average observer than those of a generic human observer.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-02-17T19:12:50.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep learning",
      "distortion-generic blind image quality assessment",
      "wild image quality challenge database",
      "image quality task",
      "linear correlation coefficient"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}