TY - GEN
T1 - Manifold learning based on multi-feature for road-sign recognition
AU - Zhang, Qieshi
AU - Kamata, Sei Ichiro
PY - 2011/1/1
Y1 - 2011/1/1
N2 - In this paper, a multi-feature selection and application based manifold learning metric method is proposed for Road-Sign Recognition (RSR). Firstly, the manifold metric between manifold from subspace is discussed in detail. After that, the multi-feature analyzing, selection, classification and application are introduced for rough recognition and create the manifold. Then the proposed method is used to evaluate the distance between the manifolds. Finally, the RSR results suggest that the proposed method is robust than other methods.
AB - In this paper, a multi-feature selection and application based manifold learning metric method is proposed for Road-Sign Recognition (RSR). Firstly, the manifold metric between manifold from subspace is discussed in detail. After that, the multi-feature analyzing, selection, classification and application are introduced for rough recognition and create the manifold. Then the proposed method is used to evaluate the distance between the manifolds. Finally, the RSR results suggest that the proposed method is robust than other methods.
KW - Feature Analyzing
KW - Feature Selection
KW - Manifold Learning
KW - Road-Sign Recognition (RSR)
UR - http://www.scopus.com/inward/record.url?scp=81255123396&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=81255123396&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:81255123396
SN - 9784907764395
T3 - Proceedings of the SICE Annual Conference
SP - 1143
EP - 1146
BT - SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts
PB - Society of Instrument and Control Engineers (SICE)
T2 - 50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011
Y2 - 13 September 2011 through 18 September 2011
ER -