In this communication, we propose a method for the automatic extraction of numerical fields in handwritten documents. The approach exploits the known syntactic structure of the numerical field to extract, combined with a set of contextual morphological features to find the best label to each connected component. Applying an HMM based syntactic analyzer on the overall document allows to localize/extract fields of interest. Reported results on the extraction of zip codes, phone numbers and customer codes from handwritten incoming mail documents demonstrate the interest of the proposed approach.
Numerical sequence extraction in handwritten incoming mail documents
01.01.2003
409136 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Numerical Sequence Extraction in Handwritten Incoming Mail Documents
British Library Conference Proceedings | 2003
|In search of cleaner mail Methods to police incoming mail
British Library Online Contents | 2004
Indexing and retrieval of on-line handwritten documents
IEEE | 2003
|Indexing and Retrieval of On-line Handwritten Documents
British Library Conference Proceedings | 2003
|Keywords image retrieval in historical handwritten Arabic documents
British Library Online Contents | 2013
|