Centroid Based Detection Algorithm for Hybrid Traffic Sign Recognition System

Automatic traffic sign recognition system can help the driver to make a right decision at the right time for safe driving. This paper presents an algorithm for detection of traffic sign using color centroid matching. This algorithm detects the traffic sign from the images captured from the complex road environment. YCbCr color space is used for color segmentation to make the detection process independent of variable illumination characteristic. The proposed method extracts and classifies the detected sign according to colors of the traffic sign. The sign is extracted by considering the maximum distance of boundary pixels from centroid. The sign is further classified into its sub-group according to its shape. The minimum Euclidean distance classifier is used to detect the shape of sign. Perceptron Neural Network (NN) is employed to recognize the classified sign. Results show that the developed algorithm has color classification rate of 100% while shape classification rate about 98% when tested on several outdoor images for traffic sign detection. The overall recognition rate of the developed algorithm is observed around 92%.