Abstract | ||
---|---|---|
It is often desirable to evaluate images quality with a perceptually relevant measure that does not require a reference image. Recent approaches to this problem use human provided quality scores with machine learning to learn a measure. The biggest hurdles to these efforts are: 1) the difficulty of generalizing across diverse types of distortions and 2) collecting the enormity of human scored training data that is needed to learn the measure. We present a new blind image quality measure that addresses these difficulties by learning a robust, nonlinear kernel regression function using a rectifier neural network. The method is pre-trained with unlabeled data and fine-tuned with labeled data. It generalizes across a large set of images and distortion types without the need for a large amount of labeled data. We evaluate our approach on two benchmark datasets and show that it not only outperforms the current state of the art in blind image quality estimation, but also outperforms the state of the art in non-blind measures. Furthermore, we show that our semi-supervised approach is robust to using varying amounts of labeled data. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/CVPR.2014.368 | CVPR |
Keywords | Field | DocType |
nonlinear kernel regression function,learning (artificial intelligence),regression analysis,distortion,nonblind measure,quality score,image distortion,blind image quality assessment,nonlinear functions,labeled data,computer vision,machine learning,semi-supervised rectifier neural network | Semi-supervised learning,Computer science,Image quality,Artificial intelligence,Labeled data,Artificial neural network,Distortion,Kernel regression,Computer vision,Rectifier,Pattern recognition,Generalization,Machine learning | Conference |
ISSN | Citations | PageRank |
1063-6919 | 27 | 0.83 |
References | Authors | |
10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huixuan Tang | 1 | 113 | 4.81 |
Neel Joshi | 2 | 1155 | 63.95 |
Ashish Kapoor | 3 | 1833 | 119.72 |