Road Sign Detection and Recognition Using Hidden Markov Model

10.6412/AJHIS.200604.0085

Jung-Chieh Hsien；Yi-Sheng Liou；Shu-Yuan Chen

road sign detection ； road sign recognition ； advanced safety vehicle ； projection ； hidden Markov model

Asian Journal of Health and Information Sciences

1卷1期（2006 / 04 / 01）

85 - 100

英文

This paper proposes a novel road sign detection and recognition method. The position of a road sign in an image is detected using the projection technique. The hidden Markov model is then used to match the detected road sign with those in the database so that the goal of road sign recognition can be achieved. More specifically, the color images in terms of the RGB color system are first converted to the HSV color system and then quantized into specific colors. The horizontal and vertical projections of whole images in the specific colors existing in road signs are then used to detect the positions of road signs. In the recognition stage, only local features around the detected positions are used and a two-step strategy is adopted. The horizontal and vertical projections of background in the local area are used to prune irrelevant road signs. The candidate road signs are then sorted using the hidden Markov model. The one with the first rank is regarded as the recognition result. The effectiveness of the proposed method has been demonstrated by various experiments.