Writer dependent recognition of on-line unconstrained handwriting

Author

Subrahmonia, Jayashree ; Nathan, Krishna ; Perrone, Michael P.

Author_Institution

IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA

Volume

6

fYear

1996

fDate

7-10 May 1996

Firstpage

3478

Abstract

In this paper, we present a framework for adapting a writer independent system to a user from samples of the user´s writing. The writer independent system is modeled using hidden Markov models. Training for a writer involves recomputing the topology and parameters of the hidden Markov models using the writer´s data. The framework uses the writer independent system to get an initial alignment of the writer´s data. The system described reduces the error rate by an average of 65%. For the results presented, no language model was used

Keywords

character recognition; error statistics; hidden Markov models; learning (artificial intelligence); error rate; hidden Markov models; initial alignment; on-line unconstrained handwriting; samples; topology; training; user´s writing; writer dependent recognition; Error analysis; Handwriting recognition; Hidden Markov models; Maximum a posteriori estimation; Productivity; Text recognition; Topology; Training data; Vocabulary; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on

Conference_Location

Atlanta, GA

ISSN

1520-6149

Print_ISBN

0-7803-3192-3

Type

conf

DOI

10.1109/ICASSP.1996.550777

Filename

550777