Objective image quality assessment based on image color appearance and gradient features

Abstract

With the rapid development of color image contents and imaging devices in various kinds of multimedia communication systems, conventional grayscale counterparts are replaced by chromatic ones. Under such a transition, the image quality assessment (IQA) model needs to be built by subjective visual measurement, designed in accordance with the results, and applied to the related practical problems. Based on the visual perception characteristics, chromaticity and the structure feature information are quantified, and an objective IQA model combining the color appearance and the gradient image features is proposed in this paper, namely color appearance and gradient similarity(CAGS) model. Two new color appearance indices, vividness and depth, are selected to build the chromatic similarity map. The structure information is characterized by gradient similarity map. Vividness map plays two roles in the proposed model. One is utilized as feature extractor to compute the local quality of distorted image, and the other is as a weight part to reflect the importance of local domain. To quantify the specific parameters of CAGS, Taguchi method is used and four main parameters, i.e., <i>K</i>_<i>V</i>, <i>K</i>_<i>D</i>, <i>K</i>_<i>G</i> and <i>α</i>, of this model are determined based on the statistical correlation indices. The optimal parameters of CAGS are <i>K</i>_<i>V</i> = <i>K</i>_<i>D</i> = 0.02, <i>K</i>_<i>G</i> = 50, and <i>α</i> = 0.1. Furthermore, the CAGS is tested by utilizing 94 reference images and 4830 distorted images from the four open image databases (LIVE, CSIQ, TID2013 and IVC). Additionally, the influences of the 35 distortion types on IQA are analyzed. Massive experiments are performed on four publicly available benchmark databases between CAGS and other 10 state-of-the-art and recently published IQA models, for the accuracy, complexity and generalization performance of IQA. The experimental results show that the accuracy PLCC of the CAGS model can achieve 0.8455 at lowest and 0.9640 at most in the four databases, and the results about commonly evaluation criteria prove that the CAGS performs higher consistency with the subjective evaluations. Among the 35 distortion types, the two distortion types, namely contrast change and change of color saturation, CAGS and mostly IQA models have the worst influence on IQA, and the CAGS yields the highest top three rank number. Moreover, the SROCC values of CAGS for other distortion types are all larger than 0.6 and the number of SROCC value larger than 0.95 is 14 times. Besides, the CAGS maintains a moderate computational complexity. These results of test and comparison above show that the CAGS model is effective and feasible, and the corresponding model has an excellent performance.