Browse Prior Art Database

Angle-Change Parameter Improves Online Handwriting Recognition

IP.com Disclosure Number: IPCOM000120365D
Original Publication Date: 1991-Apr-01
Included in the Prior Art Database: 2005-Apr-02
Document File: 1 page(s) / 31K

Publishing Venue

IBM

Related People

Tappert, CC: AUTHOR

Abstract

Many online, handwriting recognition systems use elastic curve matching to match an unknown character against prototype (template) characters (*). The accuracy of these recognizers depends on the distance metric used in matching.

This text was extracted from an ASCII text file.
This is the abbreviated version, containing approximately 100% of the total text.

Angle-Change Parameter Improves Online Handwriting Recognition

      Many online, handwriting recognition systems use elastic
curve matching to match an unknown character against prototype
(template) characters (*).  The accuracy of these recognizers depends
on the distance metric used in matching.

      Disclosed is the use of an additional parameter, change in
direction angle, in the point-to-point distance metric. The improved
distance between point i in the unknown and point j in prototype k is

                            (Image Omitted)

where the first two terms are the Euclidean distance, the third term
is a constant (empirically determined) times the direction-angle
difference, and the fourth term is a constant (empirically
determined) times the difference of the change in direction angle.
The fourth term is new.

      Experiments on a significant amount of handwriting data
verified the superiority of this improved point distance. Fewer
errors are now made in discriminating close pairs, such as U-V and
2-Z, where the main difference is sharpness of angles.

      Reference
(1)  C. C. Tappert, C. Y. Suen, and T. Wakahara, "The state of the
art in on-line handwriting recognition," IEEE Trans. Pattern Analysis
and Machine Intelligence 12, 787-808 (August 1990).