ABSTRACT
With the growing need for vision-based vehicle guidance system, this paper is concentrated on gathering information about road signs. A robust algorithm for automatic detecting and identifying road signs from color images of outdoor road scenes is proposed. Usually, urban road and roadsides are so congested and colorful that we need to try more complicated method which considers line and color information in images. The proposed detection algorithm includes edges and color region extraction from images and the Hopfield neural networks. The identification algorithm uses seven invariant moments and parameters that present geometric characteristics. With this combined method we could successfully detect and identify the road signs.
