Information Content Weighting for Perceptual Image Quality Assessment

• Published in: IEEE transactions on image processing Vol. 20; no. 5; pp. 1185 - 1198
• Main Authors: Wang, Zhou, Li, Qiang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2011; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Assessments; Biomimetics; Computational modeling; Distortion; Distortion measurement; Gaussian scale mixture (GSM); Humans; Image Enhancement - methods; Image quality; image quality assessment (IQA); information content measure; Information Storage and Retrieval - methods; Mathematical models; peak signal-to-noise-ratio (PSNR); pooling; Reproducibility of Results; Sensitivity and Specificity; Signal to noise ratio; statistical image modeling; structural similarity (SSIM); Studies; Transforms; Visualization; Weight measurement; Weighting
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2010.2092435

Many state-of-the-art perceptual image quality assessment (IQA) algorithms share a common two-stage structure: local quality/distortion measurement followed by pooling. While significant progress has been made in measuring local image quality/distortion, the pooling stage is often done in ad-hoc ways, lacking theoretical principles and reliable computational models. This paper aims to test the hypothesis that when viewing natural images, the optimal perceptual weights for pooling should be proportional to local information content, which can be estimated in units of bit using advanced statistical models of natural images. Our extensive studies based upon six publicly-available subject-rated image databases concluded with three useful findings. First, information content weighting leads to consistent improvement in the performance of IQA algorithms. Second, surprisingly, with information content weighting, even the widely criticized peak signal-to-noise-ratio can be converted to a competitive perceptual quality measure when compared with state-of-the-art algorithms. Third, the best overall performance is achieved by combining information content weighting with multiscale structural similarity measures.