Proceedings of the 2016 International Conference on Computer and Information Technology Applications

Video image caption location based on FAST corner detection

Authors
Huibai Wang, Wen Yuan
Corresponding Author
Huibai Wang
Available Online May 2016.
DOI
10.2991/iccita-16.2016.7How to use a DOI?
Keywords
FAST corner detection, Caption location, Caption detection
Abstract

It is well known that the caption information is significantly important upon video and image retrieval analysis. A caption location method based on FAST (Features From Accelerated Segment Test) corner detection algorithm is illustrated in this paper. This method use FAST corner detection algorithm to get the corners information, then position the row and column respectively through the analysis of the horizontal integral projection and connected region, finally get validation by heuristic rules and locate the caption region. The experimental results show the performance of our method.

Copyright
© 2016, 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 2016 International Conference on Computer and Information Technology Applications
Series
Advances in Computer Science Research
Publication Date
May 2016
ISBN
10.2991/iccita-16.2016.7
ISSN
2352-538X
DOI
10.2991/iccita-16.2016.7How to use a DOI?
Copyright
© 2016, 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  - Huibai Wang
AU  - Wen Yuan
PY  - 2016/05
DA  - 2016/05
TI  - Video image caption location based on FAST corner detection
BT  - Proceedings of the 2016 International Conference on Computer and Information Technology Applications
PB  - Atlantis Press
SP  - 36
EP  - 41
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccita-16.2016.7
DO  - 10.2991/iccita-16.2016.7
ID  - Wang2016/05
ER  -