INFORMys: A Flexible Invoice-Like Form-Reader System
IEEE Transactions on Pattern Analysis and Machine Intelligence
Message Extraction from Printed Documents - A Complete Solution
ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Facsimile Processing for a Messaging Server
DEXA '99 Proceedings of the 10th International Workshop on Database & Expert Systems Applications
Location of name and address on fax cover pages
ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2) - Volume 2
Name Block Location in Facsimile Images Using Spatial/Visual Cues
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Incremental construction of minimal acyclic finite-state automata
Computational Linguistics - Special issue on finite-state methods in NLP
A method of chinese fax recipient’s name recognition based on hybrid neural networks
ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
| Hi-index | 0.00 |
In the frame of a Unified Messaging System, acrucial task of the system is to provide the user with keyinformation on every message received, like keywordsreflecting the object of the message, or the name of thesender. However, in the case of facsimiles, thisinformation is not as easy to detect as in the case of e-mails,since no standard headers are defined. The aimof the present work is to identify and extract a specificinformation (the name of the sender) from a fax coverpage. For this purpose, methods based on imagedocument analysis (OCR recognition, physical blocksselection), and text analysis methods (optimiseddictionary lookup, local grammar rules), areimplemented to work in parallel. The fusion of theirresults brings a more accurate guess than any of themethods would achieve separately.