A Novel Spatial Pooling Strategy for Image Quality Assessment

• Published in: Journal of computer science and technology Vol. 31; no. 2; pp. 225 - 234
• Main Authors: Li, Qiaohong, Fang, Yu-Ming, Xu, Jing-Tao
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.03.2016; Springer Nature B.V; School of Computer Engineering, Nanyang Technological University, Singapore 639798, Singapore%School of Information Technology, Jiangxi University of Finance and Economics, Nanchang 330013, China%School of Information and Communication Engineering, Beijing University of Posts and Telecommunications Beijing 100086, China
• Subjects: Algorithms; Artificial Intelligence; Assessments; Computer engineering; Computer Science; Correlation; Data Structures and Information Theory; Distortion; Human performance; Human subjects; Image processing systems; Image quality; Information Systems Applications (incl.Internet); Quality assessment; Regression analysis; Regular Paper; Science; Software Engineering; Standard deviation; Statistical analysis; Strategy; Studies; Support vector machines; Theory of Computation; 图像质量评价; 支持向量回归; 整体质量; 统筹方法; 统计分析; 评价空间; 质量分布; 质量评估; support vector regression; structural similarity; image quality assessment; statistical pooling; spatial pooling
• ISSN: 1000-9000; 1860-4749
• DOI: 10.1007/s11390-016-1623-9

A variety of existing image quality assessment （IQA） metrics share a similar two-stage framework： at the first stage, a quality map is constructed by comparison between local regions of reference and distorted images; at the second stage, the spatial pooling is adopted to obtain overall quality scor...