Automatic road sign detection and recognition based on SIFT feature matching algorithm

Abstract

The paper presents a safety and comfort driving assistance system to help driver in analyzing the road sign boards. The system assists the drivers by detecting and recognizing the sign boards along roadside from a moving vehicle. Signboards are detected using color and shape detection techniques, and they are recognized by matching the extracted scale invariant features with the features in the database. The proposed method based on SIFT feature detects 90% of road sign boards accurately. Experimental analysis carried out using C/C++ and Open CV Libraries shows better performance in detecting and recognizing sign boards when real-time video frames are given as input.