A Flexible Recognition Engine for Complex On-line Handwritten Character Recognition

Authors:
Sanparith Marukatat;Rudy Sicard;Thierry Artières;Patrick Gallinari
Affiliations:
-;-;-;-
Venue:
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Year:
2003

Citing 3
Cited 0

Recognition accuracy and user acceptance of pen interfaces

CHI '95 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Visual similarity of pen gestures

Proceedings of the SIGCHI conference on Human Factors in Computing Systems
Stroke Level HMMs for On-Line Handwriting Recognition

IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)

Quantified Score

Hi-index	0.00

Visualization

Abstract

A major feature of new mobiles terminals using pen-basedinterfaces, such as personal assistants or e-book, istheir personal character, implying that a good interfaceshould be easily customizable in order to meet varioususers' needs. We proposed recently a new recognitionengine with strong adaptation abilities that allowslearning a user's writing style or new symbols easily. Itdealt with characters with simple shape only; we describehere an extension of this recognition system that deals withmore complex graphical symbols. We propose an adaptivelearning scheme that can learn more and more as thewriter gives new samples.