On-line cursive handwriting recognition using hidden Markov models and statistical grammars

Authors:
John Makhoul;Thad Starner;Richard Schwartz;George Chou
Affiliations:
BBN Systems and Technologies, Cambridge, MA;BBN Systems and Technologies, Cambridge, MA;BBN Systems and Technologies, Cambridge, MA;BBN Systems and Technologies, Cambridge, MA
Venue:
HLT '94 Proceedings of the workshop on Human Language Technology
Year:
1994

Citing 3
Cited 4

The State of the Art in Online Handwriting Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-site data collection for a spoken language corpus

HLT '91 Proceedings of the workshop on Speech and Natural Language
The design for the wall street journal-based CSR corpus

HLT '91 Proceedings of the workshop on Speech and Natural Language

A Handwriting Recognition System Based on Visual Input

ICVS '01 Proceedings of the Second International Workshop on Computer Vision Systems
Tree-Based State Clustering Using Self-Organizing Principles for Large Vocabulary On-Line Handwriting Recognition

ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 2 - Volume 2
An Open Source Framework for Real-Time, Incremental, Static and Dynamic Hand Gesture Learning and Recognition

Proceedings of the 13th International Conference on Human-Computer Interaction. Part II: Novel Interaction Methods and Techniques
Painting in the air with Wii Remote

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

The BYBLOS continuous speech recognition system is applied to on-line cursive handwriting recognition. By exploiting similarities between on-line cursive handwriting and continuous speech recognition, we can use the same base system adapted to handwriting feature vectors instead of speech. The use of hidden Markov models obviates the need for segmentation of the handwritten script sentences before recognition. To test our system, we collected handwritten sentences using text from the ARPA Airline Travel Information Service (ATIS) and the ARPA Wall Street Journal (WSJ) corpora. In an initial experiment on the ATIS data, a word error rate of 1.1% was achieved with a 3050-word lexicon, 52-character set, collected from one writer. In a subsequent writer-dependent test on the WSJ data, error rates ranging between 2%-5% were obtained with a 25,595-word lexicon, 86-character set, collected from six different writers. Details of the recognition system, the data collection process, and analysis of the experiments are presented.