自然性
计算机科学
高动态范围
人工智能
色调映射
图像质量
可视化
计算机视觉
质量(理念)
特征(语言学)
航程(航空)
模式识别(心理学)
动态范围
图像(数学)
工程类
认识论
物理
哲学
航空航天工程
量子力学
语言学
作者
Guanghui Yue,Chunping Hou,Tianwei Zhou
出处
期刊:IEEE Transactions on Industrial Electronics
[Institute of Electrical and Electronics Engineers]
日期:2019-05-01
卷期号:66 (5): 3784-3793
被引量:50
标识
DOI:10.1109/tie.2018.2851984
摘要
Nowadays, high-dynamic-range (HDR) imaging represents a prevailing trend and attracts much attention from both academic and industrial scholars. Since HDR images cannot be properly produced on the mainstream low-dynamic-range (LDR) displays, various tone-mapping operators or postprocessing technologies have been designed to transform HDR images into LDR images for visualization on LDR displays. However, it inevitably induces artifacts and distortions due to dynamic range compression. Besides, existing tone-mapped (TM) technologies cannot effectively handle all kinds of images with diverse contents and structures, leaving to a very challenging and urgent image quality assessment (IQA) problem. To cope with this challenge, in this paper, an effective blind quality assessment approach for TM images is proposed through a comprehensive consideration of their characteristics. More specifically, to dig out sufficient information from TM images, multiple quality-sensitive features are captured to fully represent different attributes, including colorfulness, naturalness, and structure. The connection between feature space and associated subjective ratings is established via a regression model. Extensive experiments on a recently released TM image database prove that the proposed approach is superior to the state-of-the-art no-reference IQA approaches.
科研通智能强力驱动
Strongly Powered by AbleSci AI