改进的车牌校正与识别算法  

Improved Algorithm for License Plate Correction and Recognition

作　　者：马嘉怡 谭振江[1] MA Jiayi;TAN Zhenjiang(School of Mathematics and Computer Science,Jilin Normal University,Siping,China,136000)

机构地区：[1]吉林师范大学数学与计算机学院,吉林四平136000

出　　处：《福建电脑》2024年第10期7-11,共5页Journal of Fujian Computer

摘　　要：为解决车牌存在图像背景噪声较大和车牌倾斜校正精度的问题,本文提出基于OpenCV的车牌校正与识别算法。基于形态学运算,对输入的图像进行车牌定位,并通过霍夫变换和透视变换进行倾斜校正,然后进行车牌字符分割,采取模板匹配技术对分割后的字符逐一进行比对识别,输出识别得到的车牌信息。实践结果显示了本文算法的系统性和实用性。To address the issues of high image background noise and accuracy in license plate tilt correction,this paper proposes a license plate correction and recognition algorithm based on OpenCV.Based on morphological operations,license plate localization is performed on the input image,and tilt correction is performed through Hough transform combined with perspective transform.Then,license plate character segmentation is performed,and template matching technology is used to compare and recognize the segmented characters one by one,outputting the recognized license plate information.The practical results demonstrate the systematicity and practicality of the algorithm.

关 键 词：车牌识别 车牌倾斜校正 形态学运算 

分 类 号：TP311.1[自动化与计算机技术—计算机软件与理论]