Image Quality under Chromatic Impairments

IF 1.9 4区 计算机科学 Q3 COMPUTER SCIENCE, SOFTWARE ENGINEERING ACM Transactions on Applied Perception Pub Date : 2016-08-25 DOI:10.1145/2964908
Marco V. Bernardo, A. Pinheiro, P. Fiadeiro, Manuela Pereira
{"title":"Image Quality under Chromatic Impairments","authors":"Marco V. Bernardo, A. Pinheiro, P. Fiadeiro, Manuela Pereira","doi":"10.1145/2964908","DOIUrl":null,"url":null,"abstract":"The influence of chromatic impairments on the perceived image quality is studied in this article. Under the D65 standard illuminant, a set of hyperspectral images were represented into the CIELAB color space, and the corresponding chromatic coordinates were subdivided into clusters with the k-means algorithm. Each color cluster was shifted by a predefined chromatic impairment ΔE*ab with random direction in a*b* chromatic coordinates only. Applying impairments of 3, 6, 9, 12, and 15 in a*b* coordinates to five hyperspectral images a set of modified images was generated. Those images were shown to subjects that were asked to rank their quality based on their naturalness. The Mean Opinion Score of the subjective evaluations was computed to quantify the sensitivity to the chromatic variations. This article is also complemented with an objective evaluation of the quality using several state-of-the-art metrics and using the CIEDE2000 color difference among others. Analyzing the correlations between subjective and objective quality evaluation helps us to conclude that the proposed quality estimators based on the CIEDE2000 provide the best representation. Moreover, it was concluded that the established quality metrics only become reliable by averaging their results on each color component.","PeriodicalId":50921,"journal":{"name":"ACM Transactions on Applied Perception","volume":"120 1","pages":"6:1-6:20"},"PeriodicalIF":1.9000,"publicationDate":"2016-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Applied Perception","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1145/2964908","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 5

Abstract

The influence of chromatic impairments on the perceived image quality is studied in this article. Under the D65 standard illuminant, a set of hyperspectral images were represented into the CIELAB color space, and the corresponding chromatic coordinates were subdivided into clusters with the k-means algorithm. Each color cluster was shifted by a predefined chromatic impairment ΔE*ab with random direction in a*b* chromatic coordinates only. Applying impairments of 3, 6, 9, 12, and 15 in a*b* coordinates to five hyperspectral images a set of modified images was generated. Those images were shown to subjects that were asked to rank their quality based on their naturalness. The Mean Opinion Score of the subjective evaluations was computed to quantify the sensitivity to the chromatic variations. This article is also complemented with an objective evaluation of the quality using several state-of-the-art metrics and using the CIEDE2000 color difference among others. Analyzing the correlations between subjective and objective quality evaluation helps us to conclude that the proposed quality estimators based on the CIEDE2000 provide the best representation. Moreover, it was concluded that the established quality metrics only become reliable by averaging their results on each color component.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
色差下的图像质量
本文研究了色差对感知图像质量的影响。在D65标准光源下,将一组高光谱图像表示到CIELAB色彩空间中,并利用k-means算法将相应的色彩坐标细分为簇。每个色簇通过预定义的色差ΔE*ab移动,仅在a*b*色坐标中具有随机方向。将a*b*坐标下的3、6、9、12、15的损伤值分别应用于5张高光谱图像,生成一组修改后的图像。这些图片被展示给受试者,受试者被要求根据它们的自然程度对它们的质量进行排名。计算主观评价的平均意见得分来量化对颜色变化的敏感性。本文还使用几种最先进的度量标准和CIEDE2000色差等对质量进行了客观评估。分析主观和客观质量评价之间的相关性有助于我们得出结论,基于CIEDE2000提出的质量估计器提供了最好的代表性。此外,得出的结论是,建立的质量指标只有通过对每个颜色成分的结果进行平均才能变得可靠。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
ACM Transactions on Applied Perception
ACM Transactions on Applied Perception 工程技术-计算机:软件工程
CiteScore
3.70
自引率
0.00%
发文量
22
审稿时长
12 months
期刊介绍: ACM Transactions on Applied Perception (TAP) aims to strengthen the synergy between computer science and psychology/perception by publishing top quality papers that help to unify research in these fields. The journal publishes inter-disciplinary research of significant and lasting value in any topic area that spans both Computer Science and Perceptual Psychology. All papers must incorporate both perceptual and computer science components.
期刊最新文献
Understanding the Impact of Visual and Kinematic Information on the Perception of Physicality Errors Decoding Functional Brain Data for Emotion Recognition: A Machine Learning Approach Assessing Human Reactions in a Virtual Crowd Based on Crowd Disposition, Perceived Agency, and User Traits Color Hint-guided Ink Wash Painting Colorization with Ink Style Prediction Mechanism Adaptation to Simulated Hypergravity in a Virtual Reality Throwing Task
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1