ROAD SIGN DETECTION AND RECOGNITION USING COLOUR SEGMENTATION, SHAPE ANALYSIS AND TEMPLATE MATCHING
The paper presents a system for detection and recognition of road signs with red boundaries and black symbols insied.The detection is invariant to varying lighting conditions and shadows.The algorithm is tested on RGB images taken from camera.These images are converted to HSV colour space.Colour segmentation for red regions is applied on the whole image.All red regions are labeled forming objects.Each of the red objects is tested for for its shape.Final image contains only those red objects which are triangular or circular in shape.Finding the black regions within the accepted red objects area,results in extrction of pictogram.This pictogram is then matched with templates in database,hence recognizing the meaning of road sign.The paper presents a revised edition of fuzzy shape detector and a recognition module that uses template matching to recognize rotated and affine transformed road signs.
Color segmentation Shadow Invariant Fuzzy shape detector Template matching Rotation Invariant
RABIA MALIK JAVAID KHURSHID SANA NAZIR AHMAD
Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, P.O.Nilore, Islamabad, Pakistan
国际会议
2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)
香港
英文
3556-3560
2007-08-19（万方平台首次上网日期，不代表论文的发表时间）