Enhancing Training Data for Handwriting Recognition of Whiteboard Notes with Samples from a Different Database

Authors:
Marcus Liwicki;Horst Bunke
Affiliations:
University of Bern, Switzerland;University of Bern, Switzerland
Venue:
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Year:
2005

Citing 7
Cited 1

Writer adaptation techniques in HMM based off-line cursive script recognition

Pattern Recognition Letters
Recognition of On-line Handwritten Mathematical Formulas in the E-Chalk System

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Combining Online and Offline Handwriting Recognition

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Optimizing the Integration of a Statistical Language Model in HMM based O .ine Handwritten Text Recognition

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
A survey of table recognition: Models, observations, transformations, and inferences

International Journal on Document Analysis and Recognition
MAP estimation of continuous density HMM: theory and applications

HLT '91 Proceedings of the workshop on Speech and Natural Language
Accumulated-recognition-rate normalization for combining multiple on/off-line Japanese character classifiers tested on a large database

MCS'03 Proceedings of the 4th international conference on Multiple classifier systems

Adapting handwriting recognition for applications in algebra learning

Proceedings of the international workshop on Educational multimedia and multimedia education

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recognition of unconstrained handwritten text is still a challenge. In this paper we consider a new problem, which is the recognition of notes written on a whiteboard. Our recognizer is based on Hidden Markov Models (HMMs). As it is difficult to acquire sufficient amounts of training data for the HMMs we propose two strategies for enlarging the training set. Both strategies are based on an existing database of off-line handwritten text, which includes handwriting samples different from whiteboard data. The two proposed strategies are MAP adaptation and merging of training sets. With these methods we can achieve improvements of the word recognition rate of up to 5.7%.