Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017)

A Method to Segment Strokes in Hand-drawn Sketches

Authors
Tuanfei Wang, Yanping Hu
Corresponding Author
Tuanfei Wang
Available Online April 2017.
DOI
10.2991/fmsmt-17.2017.122How to use a DOI?
Keywords
Stroke Segment; Natural Interfaces; Tangent Vertices Detection; Curvature
Abstract

In this article we present an approach based the type of curve for detecting tangent vertices. First, the geometric features is used to determinate the curve type of the sub-stroke after corners extraction. Second, approximated piecewise parametric curves are obtained and the analytic curvature is token as the extraction principle of tangent vertices between straight line and curves when the vector product and the discrete curvature are applied to find tangent vertices between curves. The expeirmental result shows that our approach achieves a better accuracy in finding tangent vertices.

Copyright
© 2017, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017)
Series
Advances in Engineering Research
Publication Date
April 2017
ISBN
978-94-6252-331-9
ISSN
2352-5401
DOI
10.2991/fmsmt-17.2017.122How to use a DOI?
Copyright
© 2017, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Tuanfei Wang
AU  - Yanping Hu
PY  - 2017/04
DA  - 2017/04
TI  - A Method to Segment Strokes in Hand-drawn Sketches
BT  - Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017)
PB  - Atlantis Press
SP  - 610
EP  - 616
SN  - 2352-5401
UR  - https://doi.org/10.2991/fmsmt-17.2017.122
DO  - 10.2991/fmsmt-17.2017.122
ID  - Wang2017/04
ER  -