Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science

A GBVS Based Object Recognition Algorithm

Authors
Faxu Wang, Xiaonian Wang, Zhuping Wang, Jin Zhu
Corresponding Author
Faxu Wang
Available Online July 2015.
DOI
https://doi.org/10.2991/lemcs-15.2015.78How to use a DOI?
Keywords
Component; Object recognition; GBVS; Tree matching; Edit distance; Region of interest
Abstract

Object recognition has always been regarded as hot research area in image field; especially there are many research difficulties of recognition in multiple objects scene. This paper puts forward an object recognition algorithm based on hierarchical decomposition GBVS. Firstly, get saliency map of current scene according to GBVS algorithm, and acquire multi focused areas according to its multiple peak features. Then, obtain object and scene described by tree via hierarchical focusing process. Thereafter, utilize edit distance to evaluate similarities among tress so as to realize object recognition. Finally, use real scene to verify method feasibility.

Copyright
© 2015, 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 International Conference on Logistics, Engineering, Management and Computer Science
Series
Advances in Intelligent Systems Research
Publication Date
July 2015
ISBN
978-94-6252-102-5
ISSN
1951-6851
DOI
https://doi.org/10.2991/lemcs-15.2015.78How to use a DOI?
Copyright
© 2015, 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  - Faxu Wang
AU  - Xiaonian Wang
AU  - Zhuping Wang
AU  - Jin Zhu
PY  - 2015/07
DA  - 2015/07
TI  - A GBVS Based Object Recognition Algorithm
BT  - Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science
PB  - Atlantis Press
SP  - 403
EP  - 407
SN  - 1951-6851
UR  - https://doi.org/10.2991/lemcs-15.2015.78
DO  - https://doi.org/10.2991/lemcs-15.2015.78
ID  - Wang2015/07
ER  -