No-reference image quality assessment of authentically distorted images with global and local statistics

The development of digital image processing techniques requires reliable image quality assessment (IQA) methods. Since images acquired by a camera often contain various distortions and their non-distorted versions are not available, a no-reference IQA (NR-IQA) technique should be used. Many popular methods are developed to assess artificially distorted images, available in benchmark databases. In this paper, a new large benchmark database, containing naturally distorted images captured with a digital camera, is introduced along with a new NR-IQA metric. The method uses a wide spectrum of local and global image features and their statistics to address a diversity of distortions. Among 80 employed features, 56 are introduced to the IQA for the first time, while the remaining statistics are used to further improve the quality prediction performance of the method. The obtained perceptual feature vector is used to provide a quality model with support vector regression technique. The experimental comparison of the method with the state-of-the-art IQA measures on the database reveals its superiority in terms of correlation with human scores.