@InProceedings{8553127,
  author = {A. Chetouani},
  booktitle = {2018 26th European Signal Processing Conference (EUSIPCO)},
  title = {A Blind Image Quality Metric using a Selection of Relevant Patches based on Convolutional Neural Network},
  year = {2018},
  pages = {1452-1456},
  abstract = {Image quality assessment is an important field in different computer vision applications. A plethora of metrics has been proposed in the literature to answer this request. In this paper, we propose an image quality framework without reference based on selection of saliency patches and Convolutional Neural Network. The idea is here to not consider all patches of the distorted image but rather some of them, which are considered as the more perceptually relevant and thus impact more the Mean Opinion Score of the image. To do that, we first compute the saliency map of the distorted image. A scanpath prediction method, that aims to reproduce the visual behavior, is then applied to select the more relevant patches. A Convolutional Neural Network model is finally used to predict the quality score. Its input is the selected patches, while its output is the predicted Mean Opinion Score. The proposed was evaluated using four well-known datasets (LIVE-P2, TID 2008, TID 2013 and CSIQ). The results obtained show its efficiency.},
  keywords = {computer vision;convolution;feedforward neural nets;visual perception;image quality framework;saliency patches;distorted image;saliency map;scanpath prediction method;Convolutional Neural Network model;quality score;predicted Mean Opinion Score;blind image quality metric;image quality assessment;computer vision applications;Protocols;Measurement;Correlation;Image quality;Degradation;Visualization;Europe;Image quality;model;Saliency;Scanpath prediction},
  doi = {10.23919/EUSIPCO.2018.8553127},
  issn = {2076-1465},
  month = {Sep.},
  url = {https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570438790.pdf},
}

{"_id":"aPge39dPqW8yYXgGT","bibbaseid":"chetouani-ablindimagequalitymetricusingaselectionofrelevantpatchesbasedonconvolutionalneuralnetwork-2018","authorIDs":[],"author_short":["Chetouani, A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["A."],"propositions":[],"lastnames":["Chetouani"],"suffixes":[]}],"booktitle":"2018 26th European Signal Processing Conference (EUSIPCO)","title":"A Blind Image Quality Metric using a Selection of Relevant Patches based on Convolutional Neural Network","year":"2018","pages":"1452-1456","abstract":"Image quality assessment is an important field in different computer vision applications. A plethora of metrics has been proposed in the literature to answer this request. In this paper, we propose an image quality framework without reference based on selection of saliency patches and Convolutional Neural Network. The idea is here to not consider all patches of the distorted image but rather some of them, which are considered as the more perceptually relevant and thus impact more the Mean Opinion Score of the image. To do that, we first compute the saliency map of the distorted image. A scanpath prediction method, that aims to reproduce the visual behavior, is then applied to select the more relevant patches. A Convolutional Neural Network model is finally used to predict the quality score. Its input is the selected patches, while its output is the predicted Mean Opinion Score. The proposed was evaluated using four well-known datasets (LIVE-P2, TID 2008, TID 2013 and CSIQ). The results obtained show its efficiency.","keywords":"computer vision;convolution;feedforward neural nets;visual perception;image quality framework;saliency patches;distorted image;saliency map;scanpath prediction method;Convolutional Neural Network model;quality score;predicted Mean Opinion Score;blind image quality metric;image quality assessment;computer vision applications;Protocols;Measurement;Correlation;Image quality;Degradation;Visualization;Europe;Image quality;model;Saliency;Scanpath prediction","doi":"10.23919/EUSIPCO.2018.8553127","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570438790.pdf","bibtex":"@InProceedings{8553127,\n author = {A. Chetouani},\n booktitle = {2018 26th European Signal Processing Conference (EUSIPCO)},\n title = {A Blind Image Quality Metric using a Selection of Relevant Patches based on Convolutional Neural Network},\n year = {2018},\n pages = {1452-1456},\n abstract = {Image quality assessment is an important field in different computer vision applications. A plethora of metrics has been proposed in the literature to answer this request. In this paper, we propose an image quality framework without reference based on selection of saliency patches and Convolutional Neural Network. The idea is here to not consider all patches of the distorted image but rather some of them, which are considered as the more perceptually relevant and thus impact more the Mean Opinion Score of the image. To do that, we first compute the saliency map of the distorted image. A scanpath prediction method, that aims to reproduce the visual behavior, is then applied to select the more relevant patches. A Convolutional Neural Network model is finally used to predict the quality score. Its input is the selected patches, while its output is the predicted Mean Opinion Score. The proposed was evaluated using four well-known datasets (LIVE-P2, TID 2008, TID 2013 and CSIQ). The results obtained show its efficiency.},\n keywords = {computer vision;convolution;feedforward neural nets;visual perception;image quality framework;saliency patches;distorted image;saliency map;scanpath prediction method;Convolutional Neural Network model;quality score;predicted Mean Opinion Score;blind image quality metric;image quality assessment;computer vision applications;Protocols;Measurement;Correlation;Image quality;Degradation;Visualization;Europe;Image quality;model;Saliency;Scanpath prediction},\n doi = {10.23919/EUSIPCO.2018.8553127},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570438790.pdf},\n}\n\n","author_short":["Chetouani, A."],"key":"8553127","id":"8553127","bibbaseid":"chetouani-ablindimagequalitymetricusingaselectionofrelevantpatchesbasedonconvolutionalneuralnetwork-2018","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570438790.pdf"},"keyword":["computer vision;convolution;feedforward neural nets;visual perception;image quality framework;saliency patches;distorted image;saliency map;scanpath prediction method;Convolutional Neural Network model;quality score;predicted Mean Opinion Score;blind image quality metric;image quality assessment;computer vision applications;Protocols;Measurement;Correlation;Image quality;Degradation;Visualization;Europe;Image quality;model;Saliency;Scanpath prediction"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2018url.bib","creationDate":"2021-02-13T15:38:40.141Z","downloads":0,"keywords":["computer vision;convolution;feedforward neural nets;visual perception;image quality framework;saliency patches;distorted image;saliency map;scanpath prediction method;convolutional neural network model;quality score;predicted mean opinion score;blind image quality metric;image quality assessment;computer vision applications;protocols;measurement;correlation;image quality;degradation;visualization;europe;image quality;model;saliency;scanpath prediction"],"search_terms":["blind","image","quality","metric","using","selection","relevant","patches","based","convolutional","neural","network","chetouani"],"title":"A Blind Image Quality Metric using a Selection of Relevant Patches based on Convolutional Neural Network","year":2018,"dataSources":["yiZioZximP7hphDpY","iuBeKSmaES2fHcEE9"]}