Image quality assessment based on multi-feature extraction and synthesis with support vector regression

Serving as quality monitor and evaluator, image quality assessment (IQA) plays an important role in various image processing systems. With humans on the receiving end of these systems, it is evident that desirable IQA methods should correlate well with subjective sensations. Yet traditional methods are usually either inaccurate for lack of consideration on human visual system (HVS) or too complex due to excessive effort on HVS simulation. To the pursuit of both accuracy and efficiency, we propose a method based on the exploitation of features closely related to image inherent quality. Specifically, in the novel method, Sobel operator, log Gabor filter and local pattern analysis are employed for complementary representation of image quality to make use of the properties of the primary and secondary visual cortex in HVS. Finally, support vector regression is implemented for the synthesis of the multiple distortion indices and mapping the quantification into an objective quality score. Experiments conducted on four large-scale databases, i.e. LIVE, T1D2008, TID2013, and CSIQ prove that the objective evaluation of image quality by our method is highly consistent with subjective perception, and it is robust across different databases and distortion types.