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 average-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, including those based on deep learning, having a Linear Correlation Coefficient (LCC) with human subjective scores of almost 0.91. These results are further confirmed also on four benchmark databases of synthetically distorted images: LIVE, CSIQ, TID2008 and TID2013. Furthermore, in most of the cases, the quality score predictions of DeepBIQ are closer to the average observer than those of a generic human observer.
Click here to download an extended version of the paper with additional material