Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain

• Published in: IEEE transactions on image processing 2012-08, Vol.21 (8), p.3339-3352
• Main Authors: Saad, M. A., Bovik, A. C., Charrier, C.
• Format: Article
• Language: English
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Computational modeling; Computer Science; Data Interpretation, Statistical; Detection, estimation, filtering, equalization, prediction; Discrete cosine transform (DCT); Discrete cosine transforms; Exact sciences and technology; Feature extraction; generalized Gaussian density; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image Processing; Image quality; Imaging, Three-Dimensional - methods; Information, signal and communications theory; natural scene statistics; no-reference image quality assessment; Pattern Recognition, Automated - methods; Predictive models; Reproducibility of Results; Sensitivity and Specificity; Signal and communications theory; Signal processing; Signal, noise; Single-Blind Method; Telecommunications and information theory; Visualization
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2012.2191563

We develop an efficient general-purpose blind/no-reference image quality assessment (IQA) algorithm using a natural scene statistics (NSS) model of discrete cosine transform (DCT) coefficients. The algorithm is computationally appealing, given the availability of platforms optimized for DCT computation. The approach relies on a simple Bayesian inference model to predict image quality scores given certain extracted features. The features are based on an NSS model of the image DCT coefficients. The estimated parameters of the model are utilized to form features that are indicative of perceptual quality. These features are used in a simple Bayesian inference approach to predict quality scores. The resulting algorithm, which we name BLIINDS-II, requires minimal training and adopts a simple probabilistic model for score prediction. Given the extracted features from a test image, the quality score that maximizes the probability of the empirically determined inference model is chosen as the predicted quality score of that image. When tested on the LIVE IQA database, BLIINDS-II is shown to correlate highly with human judgments of quality, at a level that is competitive with the popular SSIM index.