Robustness and reliability evaluations of image annotation

NCU Institutional Repository > 管理學院 > 資訊管理學系 > 期刊論文 > Item 987654321/106995

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://ir.lib.ncu.edu.tw/handle/987654321/106995

题名:	Robustness and reliability evaluations of image annotation
作者:	柯士文;Lin, W.-C.;Ke, S.-W.;Tsai, C.-F.
贡献者:	管理學院資訊管理學系
关键词:	Annotation accuracy;Coefficient of variation;Image annotation;Performance evaluation
日期:	2016-01-01
上传时间:	2026-04-23 13:52:24 (UTC+8)
出版者:	Maney Publishing;Taylor & Francis
摘要:	摘要： The semantic gap problem in image retrieval has motivated much work focusing on automatic image annotation, aimed at facilitating computers to automatically assign keywords to images. The basic measure for evaluating the annotation performance is usually to examine the annotation accuracy. To do this, the fraction of the relevant images, which have been correctly classified by a specific classifier or image annotation system, is measured. Consequently, the evaluation result can be thought of as a surrogate for the judgment of real users. However, the ability of this kind of quantitative evaluation measure to fully evaluate the performance and value of image annotation systems is limited. This paper introduces two complementary metrics related to the rates of annotation accuracy, which can help to further assess the robustness and stability of image annotation systems. They are: (i) the number of annotated keywords with zero-rate accuracy and (ii) the coefficient of variation of annotation accuracy. The evaluation results based on three datasets show that these two metrics are very useful to make a more reliable conclusion for image annotation systems. 出版者： Taylor & Francis 出版日期： 2016-02-17 出處： The imaging science journal, 2016-02, Vol.64 (2), p.94-99 資源來源： Academic Search Premier (EBSCO) 版權： 2016 The Royal Photographic Society 2016 識別號： ISSN: 1368-2199 識別號： EISSN: 1743-131X 識別號： DOI: 10.1080/13682199.2016.1139290
显示于类别:	[資訊管理學系] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	13	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....