ITR: Advancing Digital Imagery Technologies for Asian Art and Cultural Heritages

ITR：推进亚洲艺术和文化遗产的数字图像技术

• 批准号: 0219272
• 负责人: James Wang
• 金额: $ 20万
• 依托单位: Pennsylvania State Univ University Park
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2002
• 资助国家: 美国
• 起止时间: 2002-08-15 至 2006-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0219272&HistoricalAwards=false
• 关键词: ITR; Advancing; Digital; Imagery; Technologies

This collaborative research project aims at advancing informationtechnologies related to the preservation, retrieval, and disseminationof digital imagery for Asian art and cultural heritages. Researchersin the US, China, and South Korea will collectively investigate anddevelop technologies for acquiring, browsing, managing, and searchinglarge collections of high quality art images. This project willcontribute to the fundamental knowledge and technologies required tocreate and maintain information systems that can operate in multiplelanguages, formats, media, and social and organizational contexts.The US research team will focus on (1) multimodal media management,(2) distributed data mining, and (3) image storage and display. The teamwill develop theoretical foundations to associate linguistic termswith image features. The testbed databases of art images for thisresearch project consist of high quality scans, with metadatainformation and detailed keyword information, as well as comprehensivetextual descriptions. The research work will show that (1) modernmachine learning and statistical data mining tools are capable oflearning from non-structured or semi-structured input data such ashuman annotations, (2) statistical image modeling techniques can beused in automatic linguistic indexing and concept dictionary building.------

本合作研究计划旨在推动亚洲艺术及文化遗产数码影像的保存、检索及传播等相关资讯科技。美国、中国和韩国的研究人员将共同研究和开发获取、浏览、管理和搜索大量高质量艺术图像的技术。该项目将有助于创建和维护可在多语言、格式、媒体以及社会和组织环境中运行的信息系统所需的基础知识和技术。美国研究团队将专注于(1)多模式媒体管理，(2)分布式数据挖掘，以及(3)图像存储和显示。该团队将建立理论基础，将语言术语与图像特征联系起来。本研究项目的艺术图像测试平台数据库包括高质量的扫描图，具有元数据信息和详细的关键字信息，以及全面的文本描述。研究工作将表明：(1)现代机器学习和统计数据挖掘工具能够从非结构化或半结构化的输入数据（如人类注释）中学习，(2)统计图像建模技术可用于自动语言索引和概念词典构建。------