Identification of degraded traffic sign symbols by a generative learning method

Abstract

We present a novel training method for recognizing traffic sign symbols undergoing image degradations. In order to cope with the degradations, it is desirable to use similarly degraded images as training data. Our method artificially generates these data from an original image in accordance with the actual degradations. We experimentally confirmed the usefulness of our method for the camera-based traffic sign recognition. © 2006 IEEE.