Automatic recognition of road signs: contribution to recognition in bad weather conditions

Abstract

In order to improve road safety and signi cantly reduce the risk of accidents due to poorly visible road signs because of bad weather conditions, numerous works have been undertaken. In this work, we propose a contribution to this issue by taking advantage of the remarkable results of deep ConvNet in computer vision. We propose an automatic recognition system of road signs based on a modi ed model inspired by LeNet model. The results obtained by comparison of LeNet model and two proposed modi ed models on the German tra c dataset is about 99 % accuracy which is promising compared to the state-of-the-art results which also showed promising results on classifying tra c signs with bad weather conditions.