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

该项目将采用创新的自动识别技术，对古希腊纸莎草纸的数字摹本进行识别。该项目结合了三种新的技术方法，试图分析公元前3世纪现存最古老的莎草纸文本。第一个是对古代文本字母形式的自动统计评估。第二种是用于高清数字成像的高级自动化工作流程，其结果是将多光谱2d图像的注册数据集与文档的3d模型对齐。第三是数字图书馆基础设施的新功能，它允许在基于通用查询和精细粒度的文本转录注册中自动发现和检索数字图像。所有这些都涉及与创新方法相结合的高水平计算。如果成功，这项工作可以大大扩展和扩展现有的研究能力，从古代铭文中恢复内容，在文本用离散字符进行正则化的情况下，并且由于考古背景，源文件的日期更容易确定。

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.