一种基于投影法和形态学梯度的车牌定位算法

A vehicle plate segmentation based on projection and mophological gradient

车辆牌照自动识别系统的研究与开发是现代交通控制管理系统中备受关注的问题,而车牌定位又是车牌识别的关键。在分析和研究目前有代表性的车牌定位算法的基础上,提出了一种基于投影法和形态学梯度的车牌定位算法,49个原始图像的实验结果表明,正确分割率由传统方法的91.84%提高到97.96%。

The automatic recognition system of vehicle license plate plays an improtant role in the intelligent control and management of the modern traffic. As the key technology of vechicle indentification, the license plate recognition（LPR） has attracted more and more attention. Furthermore, location of the license plate is the key of the LPR technology. An algortithm was proposed about the location of license plate. Based on the projection and morphological gradient, experiments of 49 original graphs show that recognition rate inceases from 91.84% to 97.96%.