TY - GEN
T1 - New Hybrid Technique for traffic sign recognition
AU - Lim, King Hann
AU - Ang, Li Minn
AU - Seng, Kah Phooi
PY - 2009
Y1 - 2009
N2 - A hybrid traffic sign recognition scheme combining of knowledge-based analysis and radial basis function neural classifier (RBFNN) is proposed in this paper. Initially, traffic signs are detected from the road scenes using color segmentation method. The extracted signs are then passed to the recognition system for classification. The proposed recognition technique composes of three stages: (i) color histogram classification, (ii) shape classification and, (iii) RBF neural classification. Based on the unique color and shape of traffic signs, they can be classified into smaller subclasses and can be easily recognized using RBFNN. Before feeding traffic sign into the RBFNN, traffic sign features are extracted by Principle Component Analysis (PCA) in order to reduce the dimensionality of the original images. This is followed by the Fisher's Linear Discriminant (FLD) to further obtain the most discriminant features. The performance of the proposed hybrid system is evaluated and compared to the purely neural classifier. The experimental results demonstrate that the proposed method has better recognition rate.
AB - A hybrid traffic sign recognition scheme combining of knowledge-based analysis and radial basis function neural classifier (RBFNN) is proposed in this paper. Initially, traffic signs are detected from the road scenes using color segmentation method. The extracted signs are then passed to the recognition system for classification. The proposed recognition technique composes of three stages: (i) color histogram classification, (ii) shape classification and, (iii) RBF neural classification. Based on the unique color and shape of traffic signs, they can be classified into smaller subclasses and can be easily recognized using RBFNN. Before feeding traffic sign into the RBFNN, traffic sign features are extracted by Principle Component Analysis (PCA) in order to reduce the dimensionality of the original images. This is followed by the Fisher's Linear Discriminant (FLD) to further obtain the most discriminant features. The performance of the proposed hybrid system is evaluated and compared to the purely neural classifier. The experimental results demonstrate that the proposed method has better recognition rate.
UR - http://www.scopus.com/inward/record.url?scp=66749178565&partnerID=8YFLogxK
U2 - 10.1109/ISPACS.2009.4806678
DO - 10.1109/ISPACS.2009.4806678
M3 - Conference Proceeding
AN - SCOPUS:66749178565
SN - 9781424425655
T3 - 2008 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2008
BT - 2008 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2008
PB - IEEE Computer Society
T2 - 2008 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2008
Y2 - 8 February 2009 through 11 February 2009
ER -