Shape-based Road Sign Detection and Recognition for Embedded Application Using MATLAB

• Main Authors: Md Sallah, Siti Sarah, Hussin, Fawnizu Azmadi, Yusoff, Mohd Zuki
• Format: Conference or Workshop Item
• Published: 2010
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.utp.edu.my/2091/1/1569283779.pdf; http://eprints.utp.edu.my/2091/
• Institution: Universiti Teknologi Petronas

In this paper, we propose a road sign detection and recognition algorithm for an embedded application. The algorithm is based on the Hough transform method to detect lines in order to identify and determine the shape of the road sign. Shape measurements are currently employed to identify the road sign ratios of area and perimeter. The variables are compared with the template library which we have developed. In order to evaluate the accuracy, the proposed algorithm was tested on most of the Malaysian road signs, and the results are reported in this paper. Successful detection and recognition rate is about 83.67%.