Coordinated Promotion Initiative for the Further Development of Optical Character Recognition (OCR) Techniques

进一步发展光学字符识别（OCR）技术的协调推进计划

• 批准号: 409784275
• 负责人: Professor Dr. Peter Burschel
• 金额: --
• 依托单位: Herzog August Bibliothek Wolfenbüttel
• 依托单位国家: 德国
• 项目类别: Research data and software (Scientific Library Services and Information Systems)
• 财政年份: 2018
• 资助国家: 德国
• 起止时间: 2017-12-31 至 2019-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/409784275?language=en
• 关键词: Coordinated; Promotion; Initiative; Further; Development

The aim of the coordinated promotion initiative is to describe procedures and develop guidelines in order to achieve an optimal workflow as well as a far-reaching standardization of OCR-related processes and metadata, and to prepare the conceptually complete transformation of the written German cultural heritage into a machine-readable form (structured full text). With this background, the project partners set up a coordination and support structure for projects in the second phase of the DFG's call for proposals (module project phase) in the first phase.According to the primary desideratum identified in the first phase of the project, it is necessary to fill the gap between research and practice. Accordingly, the coordinated promotion initiative sees its main task in supporting module projects, in particular in making the results of these projects available to a wide range of users in the simplest and most transparent form possible, thus significantly increasing the dissemination of the "new OCR world" that has developed over the past few years. The perspective of the initiative launched by the DFG to digitise the full text of the prints listed in the VDs is the availability of text and structural data that can be used scientifically in previously unattained dimensions. The work programme presented here represents the next step towards OCR 2.0.

协调推广计划的目的是描述程序并制定指南，以实现最佳工作流程以及 OCR 相关流程和元数据的深远标准化，并为德国书面文化遗产在概念上的彻底转变做好准备转换为机器可读的形式（结构化全文）。在此背景下，项目合作伙伴在第一阶段DFG征求建议书第二阶段（模块项目阶段）中建立了项目协调和支持架构。根据项目第一阶段确定的主要需求，有必要填补研究与实践之间的空白。因此，协调推广计划的主要任务是支持模块项目，特别是以尽可能简单和透明的形式向广大用户提供这些项目的结果，从而大大增加“新OCR”的传播世界”是过去几年发展起来的。 DFG 发起的将 VD 中列出的印刷品全文数字化的举措的目的是提供文本和结构数据，这些数据可以在以前未达到的维度上科学地使用。这里介绍的工作计划代表了 OCR 2.0 的下一步。