Traffic sign recognition system using feature points

Abstract

The selection of features is an important element in image processing. The important features make it possible to obtain good performances in the recognition of traffic signals. This paper presents the significant features points for traffic sign recognition. As a difficult research problem for many years, the recognition of road signs suffers from the different illuminations. The aim of the proposed research is to develop TSDR system under lighting changes in real time. This system proposes RGB color thresholding for traffic signs detection and new significant features points (crossing points, termination point and bifurcation point) are proposed. The features points are recognized with Adaptive Neuro Fuzzy Inference System (ANFIS) system. This system provides good results under sunny, cloudy, drizzle rain weather and uses Myanmar Traffic Sign dataset.