A Layout-Free Method for Extracting Elements from Document Images
DAS '98 Selected Papers from the Third IAPR Workshop on Document Analysis Systems: Theory and Practice
Universal Data Capture Technology from Semi-structured Form
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Document Understanding System Using Stochastic Context-Free Grammars
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
| Hi-index | 0.00 |
The document knowledge plays very importants roles in many currently proposed document image understanding methods. In these methods the document knowledge is utilized to classify/ extract individual item data interpretatively from paper-based sheets as a kind of document model. Of course, the document knowledge is classified into layout knowledge about locational information of composite item blocks, item sequence knowledge about compositional information of individual item fields, item property knowledge about characteristic information of item data and so on. Today, these knowledge are specified into the document image understanding system as ready-made information in advance.In this paper, we propose an experimental method to acquire the layout knowledge automatically from sample document images: especially, we focus on the acquisition subject for business cards. Our idea for this subject is to generate individual knowledge of layout structures of business cards from a predefined logical structure. Namely, the logical structure is used as a kind of meta-knowledge to interpretatively generate the layout knowledge of given business cards.