A tutorial on hidden Markov models and selected applications in speech recognition
Readings in speech recognition
Beatrix: a self-learning system for off-line recognition of handwritten texts
Pattern Recognition Letters
An Off-Line Cursive Handwriting Recognition System
IEEE Transactions on Pattern Analysis and Machine Intelligence
On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Full English Sentence Database for Off-Line Handwriting Recognition
ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
Handwritten Sentence Recognition
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
MAP estimation of continuous density HMM: theory and applications
HLT '91 Proceedings of the workshop on Speech and Natural Language
Recognition of Cursive Roman Handwriting - Past, Present and Future
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Unsupervised writer adaptation of whole-word HMMs with application to word-spotting
Pattern Recognition Letters
Reducing costs for digitising early music with dynamic adaptation
ECDL'07 Proceedings of the 11th European conference on Research and Advanced Technology for Digital Libraries
Hi-index | 0.12 |
This work presents the application of HMM adaptation techniques to the problem of Off-Line Cursive Script Recognition. Rather than training a new model for each writer, one first creates a unique model with a mixed database and then adapts it for each different writer using his own small dataset.Experiments on a publicly available benchmark database show that an adapted system has an accuracy higher than 80% even when less than 30 word samples are used during adaptation, while a system trained using the data of the single writer only needs at least 200 words in order to achieve the same performance as the adapted models.