EAGER: New Techniques for Recognition and Visualization of Inscriptions on Papyrological Documents

EAGER：纸卷文献铭文识别和可视化新技术

• 批准号: 1041949
• 负责人: Christopher Blackwell
• 金额: $ 9.99万
• 依托单位: Furman University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-09-01 至 2013-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1041949&HistoricalAwards=false
• 关键词: EAGER; New; Techniques; Recognition; Visualization

This project will apply innovative techniques of automated recognition to digital facsimiles of ancient Greek papyri. The project combines three new technological approaches in attempting to analyze the oldest surviving papyrus texts from the 3rd century BC. The first is the automated, statistical evaluation of letter-forms on ancient texts. The second is advanced automated workflows for high-definition digital imaging that result in registered datasets of multi-spectral 2d images aligned to 3d models of a document. And the third is new capabilities in digital library infrastructure that allow automated discovery and retrieval of digital images in registration with textual transcriptions based on generic queries and at a fine level of granularity. All of these involve high levels of computation combined with innovative methodologies. If successful the work can significantly extend and expand existing research capabilities for recovering content from ancient inscriptions, in cases where text is regularized with discrete characters, and dating of the source-documents is made easier by virtue of archaeological context.

该项目将把创新的自动识别技术应用于古希腊纸莎草纸的数字传真。该项目结合了三种新的技术方法，试图分析公元前3世纪现存的最古老的纸莎草纸文本。第一个是对古代文本的字母形式进行自动化的统计评估。第二种是用于高清晰度数字成像的高级自动化工作流程，其结果是将多光谱2D图像的配准数据集与文档的3D模型对齐。第三是数字图书馆基础设施中的新功能，允许自动发现和检索数字图像，并根据一般查询以精细的粒度与文本转录一起注册。所有这些都涉及高水平的计算和创新的方法。如果成功，这项工作可以极大地扩展和扩大现有的从古代铭文中恢复内容的研究能力，在文字以离散字符正规化的情况下，由于考古学背景，来源文件的年代测定变得更容易。