基于结构信息和像素失真的客观图像质量评价

为了度量多种失真类型的图像质量,根据人类视觉系统(HVS)对图像空域结构信息高度敏感和任一类型的失真都会产生像素失真理论,提出一种基于结构信息和像素失真的无参考的质量评价方法.该方法利用色彩信息提取能够表征图像结构信息的视觉内容结构图,并加权像素失真来度量图像质量,同时对部分失真类型进行修正.该方法不涉及任何参数设置也无需训练过程.实验结果表明,该方法能够较好地评价白噪声、JPEG压缩、高斯模糊、JPEG2000压缩和FastFading等失真图像的质量,并与主观评价方法有较好的一致性.

Objective Image Quality Assessment based on Structure Information and Pixel Distortions

To estimate a range of image distortions, a novel no-reference image quality assessment method is proposed based on structural information and pixel distortions, which is under the assumption that human visual system (HVS) is very sensitive to spatial structural information of an image and any kinds of artifacts create pixel distortion. The proposed method uses color information for image structural information extraction to get visual content structure map. And then we evaluate the image quality by using the map to weight pixel distortions. Meanwhile, an effective method for compensating an inappropriate distortion is presented. It does not involve any parameter settings and training procedures. Our experimental results show that the new method accords closely with human subjective judgment. And it can effectively process the artifacts of WN, JPEG, GBLUR, JPEG2000, FastFading and so on.