摘要
在线质量检测系统作为提升印钞产品质量的有效辅助设备,已经在行业内广泛应用。由于纸张交接、偏移、套印等问题,将待检测图像跟模板图像相应区域精确定位,成为提高系统检测能力、降低误检的必要前提条件。基于互相关匹配的图像定位算法具有非常高的定位精度,而基于灰度投影的一维模板匹配算法能够在不降低定位精度的基础上极大减少运算量。检测系统采用该算法,经大生产验证,耗时能够满足生产需求,并且具有良好鲁柔性。系统采用多级搜索定位策略,进一步提升了检测能力。
Online quality inspection system has been widely used in the industry as an effective auxiliary equipment for improving the quality of printed banknote products.Due to problems such as paper handover,offset,overprinting,etc.,accurately positioning the image to be detected and the corresponding area of the template image becomes a necessary precondition for improving the system detection capability and reducing false detection.The image localization algorithm based on cross-correlation matching has very high positioning accuracy,and the one-dimensional template matching algorithm based on gray projection can greatly reduce the computational complexity without reducing the positioning accuracy.The detection system adopts this algorithm,which is verified by large production,can meet the production requirements in a time-consuming manner,and has good robustness.The system adopts a multi-level search and positioning strategy to further improve the detection capability.
作者
蒲明玥
PU Mingyue(Chengdu Banknote Printing Co.,Ltd,Sichuan Chengdu,611130,China)
出处
《数码设计》
2018年第2期11-12,共2页
Peak Data Science
关键词
在线检测系统
图像定位匹配算法
相关匹配
图像投影
online detection system
image location matching algorithm
correlation matching
image projection
