A study on traffic sign recognition in scene image using genetic algorithms and neural networks

This research is concerned with a new technology for the recognition of traffic signs from a scene image using genetic algorithms (GA) and neural networks (NN). First, an original video image is obtained as a binary image by using the smoothing filter and the Laplacian filter. Second, the traffic sign in a scene image is searched using a proposed GA. Third, if there exist two traffic signs in a video image, the method to detect the second traffic sign is developed based on the fitness of individuals. Finally, it can be recognized using NN what kind of traffic sign is taken. Through these recognition experiments, it can be shown that the new technology proposed here is sufficiently valid for the recognition of a traffic sign from a scene image.