Object Recognition based on a Simplified PCNN
Yuli Chen, Yide Ma, Dong Hwan Kim, Sung-Kee Park
2012
Abstract
The aim of the paper is to propose a region-based object recognition method to identify objects from complex real-world scenes. The proposed method firstly performs a colour image segmentation by a simplified pulse coupled neural network (SPCNN) model, and the parameters of the SPCNN are automatically set by our previously proposed parameter setting method. Subsequently, the proposed method performs a region-based matching between a model object image and a test image. A large number of object recognition experiments have proved that the proposed method is robust against the variations in translation, rotation, scale and illumination, even under partial occlusion and highly clutter backgrounds. Also it shows a good performance in identifying less-textured objects, which significantly outperforms most feature-based methods.
DownloadPaper Citation
in Harvard Style
Chen Y., Ma Y., Kim D. and Park S. (2012). Object Recognition based on a Simplified PCNN . In Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-8565-22-8, pages 223-229. DOI: 10.5220/0004013102230229
in Bibtex Style
@conference{icinco12,
author={Yuli Chen and Yide Ma and Dong Hwan Kim and Sung-Kee Park},
title={Object Recognition based on a Simplified PCNN},
booktitle={Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2012},
pages={223-229},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004013102230229},
isbn={978-989-8565-22-8},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - Object Recognition based on a Simplified PCNN
SN - 978-989-8565-22-8
AU - Chen Y.
AU - Ma Y.
AU - Kim D.
AU - Park S.
PY - 2012
SP - 223
EP - 229
DO - 10.5220/0004013102230229