Document Analysis and Recognition

, Volume 6, Issue 4, pp 248–262

Segmentation and recognition of handwritten dates: an HMM-MLP hybrid approach

  • Marisa Morita
  • Robert Sabourin
  • Flávio Bortolozzi
  • Ching Y. Suen
Article

DOI: 10.1007/s10032-003-0114-z

Cite this article as:
Morita, M., Sabourin, R., Bortolozzi, F. et al. IJDAR (2003) 6: 248. doi:10.1007/s10032-003-0114-z

Abstract.

This paper presents an HMM-MLP hybrid system for segmenting and recognizing complex date images written on Brazilian bank checks. Through the recognition process, the system makes use of an HMM-based approach to segment a date image into subfields. Then the three obligatory date subfields (day, month, and year) are processed. A neural approach has been adopted to decipher strings of digits (day and year) and a Markovian strategy to recognize and verify words (month). The final decision module makes an accept/reject decision. We also introduce the concept of metaclasses of digits to reduce the lexicon size of the day and year and improve the precision of their segmentation and recognition. Experiments show interesting results on date recognition.

Keywords:

Date processingMetaclassesHidden Markov modelsNeural networksSegmentationRecognition and verification

Copyright information

© Springer-Verlag Berlin/Heidelberg 2003

Authors and Affiliations

  • Marisa Morita
    • 1
    • 2
  • Robert Sabourin
    • 1
    • 2
    • 3
  • Flávio Bortolozzi
    • 3
  • Ching Y. Suen
    • 2
  1. 1.Laboratoire d’Imagerie, de Vision et d’Intelligence Artificielle (LIVIA)École de Technologie SupérieureMontrealCanada
  2. 2.Centre for Pattern Recognition and Machine Intelligence (CENPARMI)MontrealCanada
  3. 3.Pontíficia Universidade Católica do Paraná (PUCPR)CuritibaBrazil