首页|基于Canny边缘检测的银行卡号识别研究

基于Canny边缘检测的银行卡号识别研究

扫码查看
为了快速准确地获取银行卡号信息,论文提出了一种基于Canny边缘检测的模板匹配算法来对银行卡号进行识别.首先,对数字模板进行灰度图操作,二值化操作,然后提取外轮廓信息,并对模板上的数字进行排序.然后对待检测银行卡的图像进行一些列形态学操作,根据绘制的轮廓大小比例锁定银行卡卡号的位置,并经过图像切割得到单个数字,最终将单个数字与模板进行匹配识别.实验结果表明,基于Canny算子边缘检测的模板匹配法识别准确率达93.2%.其识别准确率优于Sobel算子的模板匹配法.
Research on Bank Card Number Recognition Based on Canny Edge Detection
In order to obtain bank card number information quickly and accurately,this paper proposes a method based on Canny edge detection to extract bank card contour information.Firstly,this paper performs the gray-scale operation and binarization operation on the digital template,then extracts the outer contour information,and sorts the numbers on the template.Then a series of morphological operations on the image of the bank card to be detected are performed,the position of the bank card number is locked according to the drawn outline size ratio,and a single number is obtained through image cutting,and finally the single num-ber with the template is matched and recognized.Experimental results show that the recognition accuracy of the template matching method based on Canny operator edge detection reaches 93.8%.Its recognition accuracy is better than the template matching method based on Sobel operator.

bank card recognitionmorphological processingCanny edge detectiontemplate matching

张航、余粟

展开 >

上海工程技术大学机械与汽车工程学院 上海 201620

上海工程技术大学工程实训中心 上海 201620

银行卡识别 形态学处理 Canny边缘检测 模板匹配

国家科技部"十二五"支撑计划项目

2015BAF10B00

2024

计算机与数字工程
中国船舶重工集团公司第七0九研究所

计算机与数字工程

CSTPCD
影响因子:0.355
ISSN:1672-9722
年,卷(期):2024.52(6)
  • 9