No-reference quality assessment for contrast-distorted image
Jun Wu, Zhaoqiang Xia, Yifeng Ren, Huifang Li · 2016
Contrast change is a special type of image distortion which is vitally important for visual perception of image quality, while little investigates has been dedicated to the contrast-distorted images. A proper contrast change not only reduces human visual perception, instead of improving it. This characteristic determines that full-reference way cannot assess contrast-distorted images properly. In this paper, we propose a no-reference way for contrast-distorted image assessment. Five statistical features are extracted from the distortion image, and two features are extracted from the phase congruence (PC) map of distortion image. These features and human mean opinion scores (MOS) of training images are jointly utilized to train a model of support vector regression (SVR). The quality of testing image is evaluated by this learned model. Experiments on CCID2014 database demonstrate the promising performance of the proposed metric.