复杂光照下的车牌图像二值化新方法

摘要

为解决车牌识别系统中,车牌区域由于受到光照过度、不足和不均等复杂光照的影响,使得车牌图像的二值化效果不理想的问题,文中提出一种复杂光照车牌图像的二值化新方法。根据国内车牌颜色特点,重新分配R、G、B颜色分量的权重来构造新灰度图,并设计不同颜色车牌灰度图转化的规则。采用全局和局部阈值相结合的双阈值方法实现车牌图像二值化,同时利用空域同态滤波进一步提高图像对光照的鲁棒性。实验结果表明,文中方法运算时间仅为传统方法的61.95%,同时能更有效地克服不均匀光照对车牌图像二值化的干扰,使二值图像的汉字和字符更清晰,鲁棒性更好。%In view of excessive,inadequate,or non-uniform（i.e.,shading） illumination of complex illumination conditions,the traditional binarization algorithm effects is poor.This paper develops a novel approach for complex illumination license plate binarization.Using re-weighting the RGB channels to obtain new grayscale plate images,and design the rules of different color license plates into gray image.Binarization step based on global and local thresholds,and applying spatial homomorphic filtering techniques to improve its robustness under different lighting conditions.Experimental results show that computing time of our proposed method is only 61.95% of traditional methods,and can effectively improve effect of binary plate images with the characters and the characters more clearly,better robustness.