Skip to main navigation Skip to search Skip to main content

Recognition of handwritten dates on bank checks using an HMM approach

  • Marisa Emika Morita
  • , Edouard Letheuer
  • , Abdenaim El Yacoubi
  • , Flávio Bortolozzi
  • , Robert Sabourin
  • Pontifícia Universidade Católica do Paraná
  • École de technologie supérieure

Research output: Contribution to Book/Report types › Contribution to conference proceedings › peer-review

10 Citations (Scopus)

Abstract

This article presents the first results of our system applied to recognize automatically the handwritten dates on Brazilian bankchecks. Considering the omni-writer context, we detail here our recognition module dedicated to process the month field. This module is based on the combination of holistic and analytical approaches with a fixed lexicon. Both approaches operate with a single explicit segmentation technique to provide a grapheme sequence for the purposed Hidden Markov Models of each recognizer. We show the significative improvements in combining both modules to get a satisfactory recognition rate considering the small database images we work with. Finally, we present various perspectives for our future works.

Original languageEnglish
Title of host publicationProceedings - 13th Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2000
EditorsMarcelo Walter, Paulo Cezar Carvalho
PublisherIEEE Computer Society
Pages113-120
Number of pages8
ISBN (Electronic)0769508782
DOIs
Publication statusPublished - 2000
Externally publishedYes
Event13th Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2000 - Gramado, Brazil
Duration: 17 Oct 2000 → 20 Oct 2000

Publication series

NameBrazilian Symposium of Computer Graphic and Image Processing
Volume2000-January
ISSN (Print)1530-1834

Conference

Conference13th Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2000
Country/TerritoryBrazil
CityGramado
Period17/10/00 → 20/10/00

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Signal Processing
  • Software

Fingerprint

Dive into the research topics of 'Recognition of handwritten dates on bank checks using an HMM approach'. These topics are generated from the title and abstract of the publication. Together, they form a unique fingerprint.

Cite this