Mode detection in online pen drawing and handwriting recognition
D. Willems, S. Rossignol, and L. Vuurpijl. Proceedings of the Eight international conference on document analysis and recognition, page 31-35. (2005)
Abstract
On-line pen input benefits greatly from mode detection when the user is in a
free writing situation, where he is allowed to write, to draw, and to generate
gestures. Mode detection is performed before recognition to restrict the
classes that a classifier has to consider, thereby increasing the performance
of the overall recognition. In this paper we present a hybrid system which is
able to achieve a mode detection performance of 95.6\% on seven classes;
handwriting, lines, arrows, ellipses, rectangles, triangles, and diamonds. The
system consists of three kNN classifiers which use global and structural
features of the pen trajectory and a fitting algorithm for verifying the
different geometrical objects. Results are presented on a significant amount of
data, acquired in different contexts like scribble matching and design
applications.
%0 Conference Paper
%1 WillemsICDAR2005
%A Willems, D.J.M.
%A Rossignol, S.Y.P.
%A Vuurpijl, L.G.
%B Proceedings of the Eight international conference on document analysis and recognition
%D 2005
%K classifiers, detection, extraction, features gesture handwriting kNN matching mode online pen recognition, shape
%P 31-35
%T Mode detection in online pen drawing and handwriting recognition
%X On-line pen input benefits greatly from mode detection when the user is in a
free writing situation, where he is allowed to write, to draw, and to generate
gestures. Mode detection is performed before recognition to restrict the
classes that a classifier has to consider, thereby increasing the performance
of the overall recognition. In this paper we present a hybrid system which is
able to achieve a mode detection performance of 95.6\% on seven classes;
handwriting, lines, arrows, ellipses, rectangles, triangles, and diamonds. The
system consists of three kNN classifiers which use global and structural
features of the pen trajectory and a fitting algorithm for verifying the
different geometrical objects. Results are presented on a significant amount of
data, acquired in different contexts like scribble matching and design
applications.
@inproceedings{WillemsICDAR2005,
abstract = {On-line pen input benefits greatly from mode detection when the user is in a
free writing situation, where he is allowed to write, to draw, and to generate
gestures. Mode detection is performed before recognition to restrict the
classes that a classifier has to consider, thereby increasing the performance
of the overall recognition. In this paper we present a hybrid system which is
able to achieve a mode detection performance of 95.6\% on seven classes;
handwriting, lines, arrows, ellipses, rectangles, triangles, and diamonds. The
system consists of three kNN classifiers which use global and structural
features of the pen trajectory and a fitting algorithm for verifying the
different geometrical objects. Results are presented on a significant amount of
data, acquired in different contexts like scribble matching and design
applications.},
added-at = {2009-04-04T18:01:35.000+0200},
author = {Willems, D.J.M. and Rossignol, S.Y.P. and Vuurpijl, L.G.},
biburl = {https://www.bibsonomy.org/bibtex/22efac7dabf29a356d219e04634ed73cd/dieudonnew},
booktitle = {Proceedings of the Eight international conference on document analysis and recognition},
date-added = {2007-01-07 15:43:26 +0100},
date-modified = {2007-01-07 15:43:26 +0100},
interhash = {82118316f6b507dd2727acb087b6f035},
intrahash = {2efac7dabf29a356d219e04634ed73cd},
keywords = {classifiers, detection, extraction, features gesture handwriting kNN matching mode online pen recognition, shape},
pages = {31-35},
timestamp = {2009-04-04T18:01:35.000+0200},
title = {Mode detection in online pen drawing and handwriting recognition},
year = 2005
}