Hierarchical traffic sign recognition system based on improved shape context
Qin Ji · Jisuanji gongcheng yu sheji · 2014
To recognize the traffic signs in natural scenes,a hierarchical traffic sign recognition system based on improved Shape Context is proposed.Firstly,the image segmentation in RGB space extracts the interested region(ROI).Then the signature of the ROI is extracted as the shape feature for the coarse classification.Finally,the improved Shape Context is used to classify the inner traffic sign images,the traffic sign is recognized by the hierarchical system.The experimental results show that the method proposed can effectively detect and recognize the traffic signs in natural scenes.