A Modified Method For Road Sign Detection & Recognition

Road sign detection is an important for regulating the traffic. In this paper oversegmentation technique is used for the detection and recognition of a road sign with the integration of shape analysis. The main focus is on the implementation and efficiency aspect of this technique. There is a detailed analysis of oversegmentation has been shown. This proposed algorithm can be used as a part of driver assistant system. The proposed algorithm can detect road signs with any color and any of the shapes (circle, triangle, rectangle, diamond, pentagon, or octagon). The key feature of oversegmention is to make much of segmentation of the image so that the object and background can be distinguished easily .There is also a creation of predefined database of shapes based on various features which is explained in details in following paper .The accuracy also measures for the detection of road sign. Therefore the proposed technique will address to a wide range of problem for detection of the road sign when the sign is partially occluded, rotated, scaled and tilted.