Advertisement

Online handwriting recognition: the NPen++ recognizer

  • S. Jaeger
  • S. Manke
  • J. Reichert
  • A. Waibel
Original papers

Abstract.

This paper presents the online handwriting recognition system NPen++ developed at the University of Karlsruhe and Carnegie Mellon University. The NPen++ recognition engine is based on a multi-state time delay neural network and yields recognition rates from 96% for a 5,000 word dictionary to 93.4% on a 20,000 word dictionary and 91.2% for a 50,000 word dictionary. The proposed tree search and pruning technique reduces the search space considerably without losing too much recognition performance compared to an exhaustive search. This enables the NPen++ recognizer to be run in real-time with large dictionaries. Initial recognition rates for whole sentences are promising and show that the MS-TDNN architecture is suited to recognizing handwritten data ranging from single characters to whole sentences.

Key words: Online handwriting recognition – Neural networks – Pen-based computing – Pattern recognition – Human-computer interaction 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • S. Jaeger
    • 1
  • S. Manke
    • 1
  • J. Reichert
    • 1
  • A. Waibel
    • 1
  1. 1.Interactive Systems Laboratories, University of Karlsruhe, Computer Science Department, 76128 Karlsruhe, Germany; e-mail: stefan.jaegar@ira.uka.de DE

Personalised recommendations