A comparison of two handwriting recognizers for pen-based computers

Authors:
Larry Chang;I. Scott MacKenzie
Affiliations:
Dept. of Computing & Information Science, University of Guelph;Dept. of Computing & Information Science, University of Guelph
Venue:
CASCON '94 Proceedings of the 1994 conference of the Centre for Advanced Studies on Collaborative research
Year:
1994

Citing 8
Cited 0

Charcoal sketching: returning control to the artist

ACM Transactions on Graphics (TOG)
Human performance engineering: using human factors/ergonomics to achieve computer system usability (2nd ed.)

Human performance engineering: using human factors/ergonomics to achieve computer system usability (2nd ed.)
Stylus user interfaces for manipulating text

UIST '91 Proceedings of the 4th annual ACM symposium on User interface software and technology
GEdit: a test bed for editing by contiguous gestures

ACM SIGCHI Bulletin
Touch-typing with a stylus

CHI '93 Proceedings of the INTERACT '93 and CHI '93 Conference on Human Factors in Computing Systems
Incremental recognition in gesture-based and syntax-directed diagram editors

CHI '93 Proceedings of the INTERACT '93 and CHI '93 Conference on Human Factors in Computing Systems
T-Cube: a fast, self-disclosing pen-based alphabet

CHI '94 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
User acceptance of handwritten recognition accuracy

CHI '94 Conference Companion on Human Factors in Computing Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

An experiment is described that compares two commercial handwriting recognizers with handprinted characters. Each recognizer was tested at two levels of constraint, one using lowercase letters (which were the only symbols included in the input text) and the other using both uppercase and lowercase letters. Two factors - recognizer and constraint - with two levels each, resulted in four test conditions. A total of 16 subjects performed text-entry tasks for each condition. Recognition accuracy differed significantly among conditions. Furthermore, the accuracy observed was far below the walk-up accuracy claimed by the developers of the recognizers. Entry speed was affected not by recognition conditions but by users' adaptation to the idiosyncrasies of the recognizers. User satisfaction results showed that recognition accuracy greatly affects the impression of walk-up users.