Standard Databases for Recognition of Handwritten Digits, Numerical Strings, Legal Amounts, Letters and Dates in Farsi Language - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Standard Databases for Recognition of Handwritten Digits, Numerical Strings, Legal Amounts, Letters and Dates in Farsi Language

Résumé

This paper describes an important step towards the standardization of the research on Optical Character Recognition (OCR) in Farsi language. It describes formations of novel and standard handwritten databases including isolated digits, letters, numerical strings, Legal amounts (used for cheques), and dates. Despite conventional research and an Internet search, no publicly accessible Farsi database was found. Hence, it was decided that it would be a worthwhile academic effort to create several Farsi databases that could stand on their own merit functioning as useful tools for OCR researchers. Also, in order to show the potential uses of our new databases we also conducted some experiments on the recognition of handwritten isolated Farsi digits.
Fichier principal
Vignette du fichier
cr102982914147.pdf (632.51 Ko) Télécharger le fichier
Loading...

Dates et versions

inria-00103983 , version 1 (05-10-2006)

Identifiants

  • HAL Id : inria-00103983 , version 1

Citer

Farshid Solimanpour, Javad Sadri, Ching Y. Suen. Standard Databases for Recognition of Handwritten Digits, Numerical Strings, Legal Amounts, Letters and Dates in Farsi Language. Tenth International Workshop on Frontiers in Handwriting Recognition, Université de Rennes 1, Oct 2006, La Baule (France). ⟨inria-00103983⟩

Collections

IWFHR10
704 Consultations
1058 Téléchargements

Partager

Gmail Facebook X LinkedIn More