Full-Reference Image Quality Assessment Using Neural Networks

This paper presents a full-reference (FR) image quality assessment (IQA) method based on a deep convolutional neural network (CNN). The CNN extracts features from distorted and reference image patches and estimates the quality of the distorted ones by combining and regressing the feature vectors using two fully connected layers. Experiments are performed on the LIVE and TID2013 databases and correlations comparable or superior to state-of-the-art IQA methods are achieved.

[1]  Andrew B. Watson,et al.  Image quality and entropy masking , 1997, Electronic Imaging.

[2]  Alan C. Bovik,et al.  A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms , 2006, IEEE Transactions on Image Processing.

[3]  Peng Zhang,et al.  SOM: Semantic obviousness metric for image quality assessment , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Nikolay N. Ponomarenko,et al.  Combining full-reference image visual quality metrics by neural network , 2015, Electronic Imaging.

[5]  David Zhang,et al.  FSIM: A Feature Similarity Index for Image Quality Assessment , 2011, IEEE Transactions on Image Processing.

[6]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[7]  Yi Li,et al.  Convolutional Neural Networks for No-Reference Image Quality Assessment , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Sebastian Bosse,et al.  A deep neural network for image quality assessment , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[9]  Nikolay N. Ponomarenko,et al.  Color image database TID2013: Peculiarities and preliminary results , 2013, European Workshop on Visual Information Processing (EUVIP).

[10]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[11]  J. Lubin.  A human vision system model for objective picture quality measurements , 1997 .

[12]  David S. Doermann,et al.  Real-Time No-Reference Image Quality Assessment Based on Filter Learning , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  David S. Doermann,et al.  Unsupervised feature learning framework for no-reference image quality assessment , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.