Application of affine transformation in traffic sign detection

The main goal of traffic sign recognition system (STR) is the detection and recognition of every traffic sign present in the scene. One of the most used approaches for image detection is the shape-based approach. In this paper, we propose a shape correction algorithm to increase accuracy of traffic detection by using affine transformation. We utilize affine transformation to rectify the shape of traffic signs in the real images. The experimental result shows that the algorithm is a fast and effective method for shape correction.