基于机器视觉的LED数码管检测  

LED Digital Tube Detection Based on Machine Vision

作　　者：甘艳平[1] GAN Yanping(College of Mechanical and Electrical Engineering,Nanjing Vocational College of Information Technology,Nanjing 210023,China)

机构地区：[1]南京信息职业技术学院机电学院,南京210023

出　　处：《机械工程师》2020年第6期93-95,98,共4页Mechanical Engineer

基　　金：江苏省高职院校青年教师企业实践培训资助项目(2018S74)。

摘　　要：针对LED数码管人工检测效率低、精度低、成本高的特点,探索一种基于机器视觉的LED数码管亮度检测方案。将待测LED数码管亮灯状态下的图像,与正常LED数码管亮灯状态下的图像进行比对,采用横向投影直方图方法,将正常LED数码管与待测LED数码管的横向投影直方图相减取绝对值,求偏差,再求平均值和方差,做统计分析,得到亮度偏差的情况,求出两横向投影直方图曲线的相关系数,分析其相似性,从而判断待测LED数码管是否合格。该检测方案能快捷、有效、量化、标准化LED数码管检测,克服了人工检测主观性强、易误判等缺点,降低了企业的生产成本。Aiming at the characteristics of low-efficiency,low-accuracy,and high-cost manual detection of LED digital tubes,a machine vision-based LED digital tube brightness detection scheme is explored.This paper compares the image of the LED digital tube under test with the image of the normal LED digital tube.The horizontal projection histogram method is used to subtract the absolute value of the horizontal projection histogram of the normal LED digital tube and the LED digital tube under test,find the deviation,and then calculate the average and variance.Statistical analysis is used to obtain the brightness deviation.The correlation coefficients of the two horizontally projected histogram curves are obtained,and their similarities are analyzed to determine whether the LED digital tube under test is qualified.The detection scheme can quickly,effectively,quantitatively,and standardizedly test the LED digital tube,overcome the shortcomings of manual detection,such as being subjective,and easy to misjudge,and reduce the production cost of the enterprise.

关 键 词：机器视觉 LED数码管 检测装置 横向投影直方图 

分 类 号：TN312[电子电信—物理电子学]