Recognition of traffic signs by artificial neural network

Abstract

An artificial neural network system for traffic sign recognition is proposed in the paper. The input image is first processed for extraction of color and geometric information. A morphological filter is applied to increase the saliency by eliminating smaller objects and by linking together objects broken in disjoint parts due to noise. The coordinates of the resulting objects are determined, and the objects are isolated from the original image according to these coordinates. After this, the objects are normalized and sent to the neural network which performs the recognition. The neural network consists of classification subnetwork, winner-takes-all subnetwork (Hopfield network), and validation subnetwork. By introducing the new concept of a validation sub-network, the network enhance the capability to correctly classify the different traffic signs and avoid misclassifying nontraffic signs into a traffic sign. The system is tested by simulation as a whole and in part on a large amount of data acquired by a video camera attached to a vehicle frame by frame. The performance is encouraging. It produced excellent results except for the images under very poor illumination such that the color threshold (preprocessing) fails to extract the color information.