Through analyzing the influence of certain digital image factors (brightness, texture details, dimentional position, etc.) on human visual characteristic, a mathematic model which combines human visual characteristic and structural similarity of images was built, a new image-quality assessment method in accordance with human visual characteristic was put forward. By unoverlapped partitioning of images using equal-sized sliding windows, this method can calculate the following factors with influence on the partitions: influencing brightness, influencing texture details, and influencing dimentional position. The weighted value of each partition is generated after normalization, and the weighted structural similarity is used as the assessing index of image quality. Experiment shows that this method is in accordance with human visual characteristic, and consistent with the result of subjective assessment.
Wifried Osberger. Perceptual vision models for picture quality assessment and compression applications . Queensland: Department of Computer Science & Computer Engineering, Queensland University of Technology, 1999
Marmolin H. Subjective MSE measures[J].IEEE Trans On Systems, Man, and Cybernetics.1986, 16 (3):486-489
Eskiciogln A M. Image quality measures and their performance [J].IEEE Trans Comm.1995,43(12):2959-2965
Karunaseka S A. A distortion measure for blocking artifacts in image based on human visual sensitivity [J]. IEEE Trans IP, 1995,4(6):713-724
½���,������,���ĸ�,��.�����Ӿ�����Ȥ����ͼ���������۷���[J].�������Ϣ,2005,21(10-3):95-96 Lu Xuguang, Wang Yuefeng, Hu Wengang, et al. A method of image quality assessment based on visual regions of interest[J]. Microcomputer Information, 2005,21(10-3):95-96 (in Chinese)
֣ʥ��,Ҷ����,����ƽ.���ھֲ��������Ե�ͼ����������[J].�����Ӧ��, 2006,26(3):605-606 Zheng Shengchao, Ye Zhenglin, Chen Zouping. Image quality evaluation method based on local self-similarity [J]. Computer Applications, 2006,26(3):605-606 (in Chinese)