一种判断印品套准偏差的插值亚像素检测方法  

Interpolation Subpixel Detection Method for Judging Printing Registration Deviation for Printing Products

作　　者：刘凯龙 邵宇鹰[2] 周文举 费敏锐 

机构地区：[1]上海市电站自动化技术重点实验室,上海200072 [2]国网上海市电力公司,上海200025

出　　处：《自动化仪表》2014年第4期8-10,14,共4页Process Automation Instrumentation

基　　金：上海市引进技术的吸收与创新计划基金资助项目(编号:11XI-32);上海市科委基础研究重点基金资助项目(编号:10JC1405000)

摘　　要：针对快速准确判断四色印品套准标记偏差的实际需要,采用了一种基于插值亚像素判断印品套准偏差的检测方法。考虑套准标记偏差检测要同时顾及运行速度和定位精度的特点,该检测方法首先通过改进区域分块算法去除套准标记的干扰图像,然后采用改进样条插值亚像素算法提取标记边缘,最后通过边缘参数计算套准标记偏差。试验结果表明,该检测方法不仅速度快、精度高,而且在有噪声干扰的情况下,该算法也能较快速、精确地实现偏差检测,优于传统的偏差检测方法。In order to meet the actual needs for precisely and rapidly judging the deviation of registration marks in four-color printing products, the detection method based on interpolation subpixel for judging the deviation of registration marks for printing products is adopted. Considering the operating speed and positioning accuracy have to be taken into account during such detection process, the interference image of the registration marks are firstly removed through improved region character separation （ RCS } algorithm, then the edge of registration mark is extracted by adopting spline interpolation subpixel algorithm, and the deviation of registration mark is calculated through edge parameters. The experimental result indicates that with this method, the speed and accuracy have been greatly improved, and even with noise interference, this method can detect deviation quickly and accurately, it is superior to the traditional deviation detection method.

关 键 词：机器视觉 套准标记 干扰图像 区域分块 偏差检测 边缘提取 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]