Numerical sequence extraction in handwritten incoming mail documents

Author

Koch, G. ; Heutte, L. ; Paquet, T.

Author_Institution

Lab. PSI, Univ. de Rouen, France

fYear

2003

fDate

3-6 Aug. 2003

Firstpage

369

Abstract

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.

Keywords

computational linguistics; feature extraction; handwritten character recognition; hidden Markov models; mailing systems; HMM based syntactic analyzer; automatic extraction; contextual morphological features; customer codes; handwritten documents; handwritten incoming mail documents; numerical fields; numerical sequence extraction; phone numbers; syntactic structure; zip codes; Context; Data mining; Dispatching; Face recognition; Filters; Handwriting recognition; Hidden Markov models; Labeling; Postal services; Text processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2003. Proceedings. Seventh International Conference on

Print_ISBN

0-7695-1960-1

Type

conf

DOI

10.1109/ICDAR.2003.1227691

Filename

1227691