ALL PuBlications

University of Computer Studies, Mandalay


Kay Thinzar Phu  | Lwin Lwin Oo


This paper proposes an efficient feature points for traffic sign recognition (TSR) system. This system composed of adaptive thresholding method based on RGB color detection, shape validation, feature extraction and adaptive neuro fuzzy inference system (ANFIS). There are some important issues for real-time TSR system such as; lighting conditions, faded color traffic signs and weather conditions. The proposed adaptive thresholding method overcomes various illumination and poor contrast color. Features play main role in TSR system. The significant feature points such as termination points, bifurcation points and crossing points are proposed. This proposes feature points provide good accuracy in TSR system. Lastly ANFIS is used to recognize the proposed feature points. This system showed that this proposed method can achieve cloudy and drizzle rain condition. In this system, this proposed method is used to evaluate on Myanmar Traffic Sign data.

Date: 1st June, 2019 | Proceedings | Weblink