Image Quality Assessment by Comparing CNN Features Between Images

TitleImage Quality Assessment by Comparing CNN Features Between Images
Publication TypeJournal Article
Year of Publication2016
AuthorsAmirshahi, S. Ali, Pedersen M., & Yu S. X.
Published inJournal of Imaging Science and Technology
Keywordsimage quality assessment, symmetry
Abstract

Finding an objective image quality metric that matches the subjective quality has always been a challenging task. We propose a new full reference image quality metric based on features extracted from Convolutional Neural Networks (CNNs). Using a pre-trained AlexNet model, we extract feature maps of the test and reference images at multiple layers, and compare their feature similarity at each layer. Such similarity scores are then pooled across layers to obtain an overall quality value. Experimental results on four state-of-the-art databases show that our metric is either on par or outperforms 10 other state-of-the-art metrics, demonstrating that CNN features at multiple levels are superior to handcrafted features used in most image quality metrics in capturing aspects that matter for discriminative perception.

URLhttp://www1.icsi.berkeley.edu/~stellayu/publication/doc/2016qualityJIST.pdf
ICSI Research Group

Vision