Additional Project Partner of the Coordinated Funding Initiative for the Further Development of Optical Character Recognition Processes (OCR-D)

“进一步发展光学字符识别过程（OCR-D）协调资助计划”已于2015年5月6日获得DFG批准。我们建议增加一名成员，扩大国际开放组织联盟。在过去的几年中，OCR-D的定位得到了改进。因此，审稿小组建议根据DFG （Skalierbare Verfahren der Text- und Strukturerkennung fgr die Volltextdigitalisierung historischer Drucke）及时推进模块结果的整合。本提案通过软件技术和开发、工作流互操作性和接口扩展了OCR-D合作伙伴的能力。主要目标是确保由模块结果组成的复杂OCR工作流的技术可行性。提出的OCR- d技术框架包括一个OCD研究数据存储库，用于保存各模块的结果数据和中间数据；一个工作流引擎，用于组成OCR工作流并记录工作流的来源；以及定义软件接口，以保证各模块的互操作性。产生的OCR结果将被存储并准备出版和存档。

The Coordinated Funding Initiative for the Further Development of Optical Character Recognition Processes (OCR-D) has been approved by the DFG at 6 May 2015. We propose to extend the consortium of OCR-D by an additional member.In the last years the orientation of OCR-D has refined. Therefore the reviewer panel has recommended to move up in time the integration of the module results according to the DFG call Skalierbare Verfahren der Text- und Strukturerkennung für die Volltextdigitalisierung historischer Drucke. The present proposal extends the competences of the OCR-D partners by software technologies and development, workflow interoperability, and interfaces. The main objective is to assure the technical feasibility of a complex OCR workflow consisting of the module results. The proposed technical OCR-D framework consists of an OCD research data repository to preserve the resulting and intermediate data of the modules, a workflow engine to compose the OCR workflow and to chronicle the workflow provenance, and the definition of software interfaces to guarantee the interoperability of the modules. The resulting OCR results will be stored and prepared for publication and archival.