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.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Received September 3, 2000 / Revised October 9, 2000
Rights and permissions
About this article
Cite this article
Jaeger, S., Manke, S., Reichert, J. et al. Online handwriting recognition: the NPen++ recognizer. IJDAR 3, 169–180 (2001). https://doi.org/10.1007/PL00013559
Issue Date:
DOI: https://doi.org/10.1007/PL00013559