| 王晓光,徐雷,李纲.敦煌壁画数字图像语义描述方法研究[J].中国图书馆学报,2014,40(1):50~59 |
| Semantic Description Framework Research on Dunhuang Fresco Digital Images |
| 敦煌壁画数字图像语义描述方法研究 |
| Received:April 16, 2013 Revised:June 29, 2013 |
| DOI： |
| Key words:Digital images Semantic annotation Semantic description framework Semantic hierarchy model Dunhuang fresco |
| 中文关键词: 数字图像 语义标注 语义描述框架 语义层次模型 敦煌壁画 |
| 基金项目:本文系科技部973项目“文化遗产数字化保护的理论与方法”(编号:904171200)和中组部“青年拔尖人才支持计划”项目“语义出版关键理论与技术”的研究成果之一。 |
|
| Hits: 4510 |
| Download times: 2800 |
| Abstract: |
| Semantic description and annotation of digital images are the key to solve the semantic gap problem in image retrieval.Due to the lack of an effective and domain-oriented description framework for digital images,the annotation results that produced by current methods,such as machine annotation based on low-level visual features of images and human annotation based on expert knowledge are of low quality and no uniform.To solve the problem,this paper proposes a semantic description method based on image metadata and information need theory for Dunhuang fresco digital images content,a specific field of cultural heritages,which combines semantic description framework and domain thesaurus and elaborates each layer's content of the semantic framework and their relationship.What's more,we discuss the effect of the semantic granularity on annotation cost from the perspective of semantic description granularity and the portability of the semantic description framework proposed here.4figs.5tabs.25refs. |
| 中文摘要: |
| 数字图像的语义描述与标注是解决图像检索中语义鸿沟问题的关键。由于缺乏面向领域的有效的数字图像描述方法规范,基于图像底层视觉特征的机器标注和基于专家知识的人为标注的标注结果都存在标注信息质量不高和结果不统一的问题。针对这一现实问题,本文基于图像元数据和信息需求理论,针对敦煌壁画数字图像这一特定文化遗产领域,提出了语义描述框架和领域主题词表相结合的数字图像内容语义描述方法,详细阐述了语义层次及其相互关系。同时,从图像语义描述粒度的角度讨论了语义粒度大小对标注成本的影响,以及该语义描述框架的可移植性问题。图4。表5。参考文献25。 |
|
View Full Text
View/Add Comment Download reader |
