一种有效的提高车牌字符分割率的方法  

Effective Way of Improving the Segmentation Rate of License Plate’s Character

作　　者：吕文强 王启爱 Lv Wenqiang Wang Qiai(The 28th Research Institute of China Electronics Group Corporation, Nanjing 210007, China)

机构地区：[1]中国电子科技集团公司第28研究所,南京210007

出　　处：《信息化研究》2017年第4期42-45,共4页INFORMATIZATION RESEARCH

摘　　要：车牌字符分割率是指在大量的车牌图像中能够准确地将每个车牌字符分割出来的成功率。在车牌识别系统中,字符分割的好坏会直接影响到整个系统的性能。文章首先对字符分割前图像的预处理方法进行概括,然后介绍了几种常用的字符分割方法,最后详细说明文章提出的采用基于相邻字符最大间隔宽度的车牌字符分割方法。为了保证实验结果的准确性,本文对采集的3 000幅不同环境下的车牌图像进行了实验分析。The license plate character segmentation rate refers to the success rate of the segmentation of each license plate character in a large number of license plate images. The character segmentation can directly affect the ;performance of the license plate recognition system. Firstly, we introduce several pretreatment meth- ods of license plate images in this paper, and then introduce some common character segmentation methods; fi- nally, this paper describes the method of using license plate character segmentation based on the maximum in- terval wi＆h of adjacent characters. In order to ensure the accuracy of the experimental results, this paper con- ducted experiments on license plate images in 3,000 different environments.

关 键 词：字符分割 二值化 车牌识别 字符间隔 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]