基于Contourlet统计特性的无参考图像质量评价 = No-reference quality assessment based on the statistics in Cntourlet domain

• Main Authors: 焦淑红 Jiao Shu-hong, 齐欢 Qi Huan, 林维斯 Lin Wei-si, 唐琳 Tang Lin, 申维和 Shen Wei-he
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: Chinese
• Published: 2018
• Subjects: DRNTU::Engineering::Computer science and engineering; 图像质量评价; 信息处理技术
• Online Access: https://hdl.handle.net/10356/102624; http://hdl.handle.net/10220/47268; http://xuebao.jlu.edu.cn/gxb
• Institution: Nanyang Technological University

利用Contourlet统计特征建立自然统计模型与待评价图像模型,提出了Contourlet域无参考图像质量评价方法(SCIQA)。通过在主观数据库上的实验表明,无论同种干扰类型的图像还是多种干扰图像集合,SCIQA均明显优于经典全参考算法和通用型无参考算法,并且具有较强的通用性。 The statistic features in Cntourlet domain are employed to build the natural statistic model and the tested image model first. Then a no-reference assessment algorithm in Coutourlet domain (SCIQR) is proposed. Experiment results on subjective databases show that SCIQR outperforms the classical full-reference image quality assessment algorithm and the universal no-reference algorithm nomatter on single distortion type images and on the set of different types of distortion images. The demonstrates that SCIQR has good universality.