Detection and Recognition of Road Traffic Signs - A Survey

Abstract

This paper presents a survey on the detection and recognition of traffic signs which has a number of important application areas that include advanced driver assistance systems, road surveying and autonomous vehicles. This has been thoroughly studied for a long time. But still it remains a challenging problem in computer vision due to the different types and the huge variability of informations present in them. This problem can be divided into two stages; first stage will be detection of region that cantains traffic sign candidates and second will be character recognition. For the detection and recognition of text and sign from traffic boards, appropriate methods must be applied to obtain accuracy. This method can be achieved by doing a survey on different methods used to detect and recognize text and signs from traffic boards. In this paper, various techniques for the detection and recognition of traffic signs are explained. A comparitive study is performed on these techniques and their performance is explained.