基于兴趣区域的无参考图像质量评价方法-计算机工程与应用.PDFVIP

Computer Engineering and Applications 计算机工程与应用 2018 ，54（16） 169 基于兴趣区域的无参考图像质量评价方法 用 1 1 1 2 文继李 ，丁立新 ，万润泽 ，邹桢苹 应 1 1 1 2 WEN Jili , DING Lixin , WAN Runze , ZOU Zhenping 与 1. 武汉大学 计算机学院，武汉 430072程 2. 武汉大学 经济与管理学院，武汉 430072 g 1.School of Computer Science, Wuhan University, Wuhan 430072, China r 工 o 2.School of Economics and Management, Wuhan University, Wuhan 430072, China . 机 j a WEN Jili, DING Lixin, WAN Runze, et al. Non-reference image quality assessment method based on region of 算 e interest. Computer Engineering and Applications, 2018, 54 （16）：169-175. c 计 w. Abstract ：In order to evaluate the quality of images with different distortion types, this paper proposes a non-reference image quality assessment method based on Regions of Interests （ROI ）and Natural Scene Statistics （NSS ）. Firstly, the w existing Itti model is improved, and this improved Itti model is used to extract regions of both interests and non-interests w from the distorted image. Secondly, the NSS of the image is extracted from the nonsubsampled contourlet domain. At last, the discrepancy between the NSS of the distorted image and that of the natural image is calculated as the quality score of the image. Comparing the proposed methods with existing methods on the LIVE dataset, experimental results show that the proposed method correlates well with human subjective perception. Key words ：Region of Interest （ROI ）; nonsubsampled Contourlet transfo