A General Approach to Quality Evaluation of Document Segmentation Results
DAS '98 Selected Papers from the Third IAPR Workshop on Document Analysis Systems: Theory and Practice
Databases and competitions: strategies to improve Arabic recognition systems
SACH'06 Proceedings of the 2006 conference on Arabic and Chinese handwriting recognition
Hi-index | 0.00 |
This paper is a contribution to the discussion of the structure and the elements of databases for document analysis tasks and the tools needed for database creation. It is pointed out that it is desirable to have a uniform document database that allows access to different kinds of data for different sub tasks within a complete document analysis system. Conceptual ideas pertaining to the data structure are discussed on the assumption of a hierarchical document structure. A description of an implemented data structure: is also included that may serve as a starting point for further investigation and discussion. Finally, we present INSEGD, an experimental system for interactive segmentation and labelling of arbitrary documents, which is still under development along with a tool box for automatically and semi-automatically generating segmentations for support in data generation.