一种复杂背景下的车牌快速定位算法

针对复杂环境下的车牌定位问题,提出一种基于提升小波与形态学相结合的快速定位方法。该方法首先对车辆图像进行预处理,包括图像灰度化,利用新的提升小波算法进行边缘检测以及二值化,然后对图像进行腐蚀、膨胀等一系列形态学处理,得到一些规则的连通区域,其次删除小连通区域,合并邻近区域,得到车牌的候选区域,最后采用可信度评价来度量候选区和车牌区的相似度确定车牌位置,最终实现车牌的快速定位。计算机仿真结果表明,对于背景复杂的车辆图像,该方法运行速度快,车牌定位准确率高。

Fast Locating Algorithm of Vehicle License Plate Under Complex Scenes

Based on lifting wavelet and morphology,a vehicle plate location algorithm under complex scenes is presented.Firstly,preprocessing is used on the vehicle image.A new lifting wavelet algorithm is used for extraction of edge and binary transformation is used.Then a series of morphological operations are used to look for candidate regions that probably contain characters in range of sizes.Finally,the vehicle license plate can be found according to credibility evaluation.Computer simulations show that the propo...