中文摘要：

分析了非下采样Contourlet变换（NSCT）方向子带亲戚系数间和父子系数间的强相关性及其包含的结构信息,并基于图像发生失真会影响这些系数间的强相关性和结构信息的假设,提出了一种新的无参考图像质量评价（NR-IQA）方法。首先,分别计算NSCT方向子带亲戚系数间和父子系数间的互信息（MI）,以此作为描述这些系数间相关性的统计特征;其次,分别计算NSCT方向子带亲戚系数间和父子系数间的结构相似度（SSIM）,以此作为描述图像结构信息的统计特征;进而,结合这些系数间的MI和SSIM等统计特征,构造了相应的NR-IQA模型和图像失真类型识别模型;最后,在LIVE及LIVE Multiply Distorted图像质量评价数据库上进行了大量的实验仿真。结果表明,本文评价模型的评价结果与人类主观评价具有非常高的相关性,LIVE图像质量评价数据库上的斯皮尔曼等级相关系数和皮尔逊线性相关系数均在0.931以上。无论总体评价效果还是各失真类型评价效果,与当今主流评价算法相比非常具有竞争性;而且,失真类型识别模型的识别精度可以达到92.31%,明显高于这些主流算法。

英文摘要：

The nonsubsampled contourlet transform （NSCT）, which is fully shifvinvariant, is a multiscale,local,multi-direction and overcomplete image representation. In this paper, we analyze the strong correlation and structure information of cousinsr coefficients and father-son coefficients respectively,and put forward a no-reference image quality assessment （NR-IQA） method based on the hypothesis that the distorted image can affect the strong correlation and the structural information between these coefficients. Firstly, the mutual information of cousinsr coefficients and father-son coefficients is calculated respectively and used to describe the statistical characteristics of the coefficients correlation. Secondly, structure similarity （SSIM） of those subband coefficients is calculated and used to describe the statistics characteristic of image structure information. Then, a no-reference image quality assessment model and an image distortion type recognition model are constructed by combining with the mutual information statistical characteristics and structural similarity statistical characteristics. Finally, a large number of simulation experiments are carried out in the LIVE and LIVE Multiply Distorted image quality evaluation databases. The simulation results show that this method is suitable for many common image distortion types and correlates well with the human judgments of image quality,and the Spearman＇s rank ordered correlation coefficient （SROCC） and the pearson＇s linear correlation coefficient （PLCC） in LIVE image quality evaluation database are more than 0. 931. The overall and every distortion type evaluation of this assessment model have highly competitive performance than other state-of-the-art NR-IQA algorithms, and the recognition accuracy of the model is up to 92.31%, significantly higher than that of other methods.