The aim of VirtualOffice is research and development of innovative solutions for document analysis and understanding (DAU) and their integration into workflow management systems (WFMS). Although, contemporary WFMS offer integrated solutions for efficient business process handling, they are obviously lacking in technology for automatically integrating informal documents into the formal concepts of a workflow. But this is an important requirement to overcome the weakness of interacting with documents in separate worlds - the physical world of the desk and the electronic world of the computer.
The central topics of our research in the Virtual Office project are:
- Exploitation of corporate knowledge: Basically DAU strongly benefits from knowledge about a given domain. In Virtual Office we address this issue by relying on corporate knowledge including predefined workflows as well as database relations.
- Design and implementation of modular and configurable DAU specialists: In order to be able to solve different DAU problems, we aim to develop a technology workbench providing a collection of software specialists for the various DAU subtasks.
- Evaluation and development of capabilities for individually teaching DAU specialists: Due to the fact that different applications are characterized by different conditions, DAU specialists have to be emphasized by mechanisms allowing for an interactive parametrization as well as teaching of document and problem solving knowledge.
- Exploration of new document image features: In order to take into account new capabilities of printing devices, we further investigate the employment of image features as they are contained in gray level and color document images. By interlocking this knowledge with text analysis techniques, we expect to achieve better as well as additional results.
The VirtualOffice prototype consists of a commercial WFMS and the DAU system (interplay (image)).
A final presentation and system demo of the VirtualOffice Prototype (VOPR) can be found here.
(Team photo) From left to right: Andreas Lauer, Claudia Wenzel, Jürgen Lichter, Heiko Maus, Michael Malburg, Tino Sarodnik
- Claudia Wenzel (project lead, researcher): information extraction by pattern matching and pattern learning, knowledge-based table analysis
- Andreas Lauer (software engineer): implementation of our knowledge representation for documents and the integration of document analysis components in an overall DAU system
- Jürgen Lichter (researcher): segmentation of color images and object recognition
- Michael Malburg (researcher): information extraction by parsing
- Heiko Maus (researcher): the integration of the DAU system into workflow management systems and workflow context
- Tino Sarodnik (software engineer): configuration of DAU components