一种新型车牌定位算法的研究

摘要

In the process of car license plate location,the camera can't obtain high quality images easily due to illumination condition, viewpoint, vehicle motion and complex background. In order to alleviate the impact of these problems on car license plate location,a new color edge detection algorithm is proposed using fused filtering and fuzzy operator, This method is effective to overcome the influence of noise of the license plate area. Experiments were carried out with 300 actual images acquired under different environments. Experiment results show that the proposed algorithm can effectively improve the image quality of license plate and the object location accuracy is 98. 3%. That proves the proposed method is effective and robust.%车牌定位过程中,由于光照变化、视点和距离变化、复杂背景等原因,图像传感器很难获取到高质量的图像.为了克服这些问题,本文在融合滤波的基础上,将一种基于模糊算子的彩色图像边缘检测方法用于车牌定位中,结合数学形态法和改进后的4-邻域标记法,以及车牌文本区的先验知识找到车牌的准确位置.本文用影像传感器对不同环境条件下获取的300多幅图像进行实验,结论验证了这种方法有效地克服了非车牌区域噪声的干扰,提高了图像质量,而且车牌定位准确率达到98.3％,证明了算法的有效性和鲁棒性.