估计员
图像质量
计算机科学
度量(数据仓库)
人工智能
质量(理念)
图像(数学)
鉴定(生物学)
对象(语法)
计算机视觉
模式识别(心理学)
场景统计
感知
统计
数据挖掘
数学
认识论
哲学
生物
神经科学
植物
作者
David B. Rouse,S.S. Hemami,Romuald Pépion,Patrick Le Callet
标识
DOI:10.1364/josaa.28.000157
摘要
Quality estimators aspire to quantify the perceptual resemblance, but not the usefulness, of a distorted image when compared to a reference natural image. However, humans can successfully accomplish tasks (e.g., object identification) using visibly distorted images that are not necessarily of high quality. A suite of novel subjective experiments reveals that quality does not accurately predict utility (i.e., usefulness). Thus, even accurate quality estimators cannot accurately estimate utility. In the absence of utility estimators, leading quality estimators are assessed as both quality and utility estimators and dismantled to understand those image characteristics that distinguish utility from quality. A newly proposed utility estimator demonstrates that a measure of contour degradation is sufficient to accurately estimate utility and is argued to be compatible with shape-based theories of object perception.
科研通智能强力驱动
Strongly Powered by AbleSci AI