LeRec: a NN/HMM hybrid for on-line handwriting recognition
Neural Computation
On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
In-Service Adaptation of Multilingual Hidden-Markov-Models
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Writer Adaptation of a HMM Handwriting Recognition System
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Robust OCR of Degraded Documents
ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
NPen/sup ++/: a writer independent, large vocabulary on-line cursive handwriting recognition system
ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1) - Volume 1
Evaluation of Confidence Measures for On-Line Handwriting Recognition
Proceedings of the 24th DAGM Symposium on Pattern Recognition
| Hi-index | 0.00 |
In this paper an on-line handwriting recognition system with focus on adaptation techniques is described. Our Hidden Markov Model (HMM) -based recognition system for cursive German script can be adapted to the writing style of a new writer using either a retraining depending on the maximum likelihood (ML)-approach or an adaptation according to the maximum a posteriori (MAP)-criterion. The performance of the resulting writer-dependent system increases significantly, even if only a few words are available for adaptation. So this approach is also applicable for on-line systems in hand-held computers such as PDAs. This paper deals with the performance comparison of two different adaptation techniques either in a supervised or an unsupervised mode with the availability of different amounts of adaptation data ranging from only 6 words up to 100 words per writer.