Road sign detection and shape recognition invariant to sign defects

This paper proposes an automated method for road sign detection and shape recognition based on the color of the road sign and its geometric attributes. Our proposed shape recognition algorithm can be part of a driver assistant system (DAS), autonomous vehicles, or road sign maintenance system to improve both recognition and processing time efficiency by categorizing road sign database to smaller groups according to their colors and shapes. The method consists of three stages: 1) the color based segmentation stage; 2) the detection of the region of interest (ROI) using geometric means; and 3) the shape recognition of the road sign stage using geometric dimensions of symmetrical sign shape outlines. Our results show that this method has the ability to detect and recognize rectangular, octagonal, triangular, diamond, and pentagonal shapes. The significance of this work is in its ability to detect and recognize the shapes of signs that are defective such as when the sign is partially occluded, scaled, or tilted.