电子元器件外形尺寸机器视觉测量系统设计

The Design of Machine Vision Measurement System for the Dimension of Electronic Components

电子元器件是电路的基本组成部分,有着广泛的应用。传统的人工检测存在很多不足,机器视觉尺寸测量技术由此应运而生,机器视觉由于自身具备高灵敏度、高精度及高耐用性的特性,对于提高工业自动化水平和工业生产效率有极大助力。根据课题要求,以单片机芯片为研究对象,以检测单片机芯片二维平面上的长度与宽度为研究目标,设计了基于机器视觉的单片机芯片检测系统的硬件方案,硬件组成包括光源与照明方式的选择,以及相机与镜头的选择。完成硬件平台搭建后,同时制作了应用于相机标定的标定板并在调试完成的硬件平台上拍摄了三十张左右的标定图片。利用MATLABR2016A作为系统的软件处理平台,一方面应用MATLAB标定箱对标定图做相机标定,另一方面编写用于单片机芯片尺寸测量的图像处理代码及测量代码。其中,在图像处理环节主要包括图像滤波、二值化处理和边缘提取等步骤。单片机芯片的尺寸测量实验完成后将实验结果与真实尺寸的对比,可以看出构建的基于机器视觉的电子元器件外形尺寸测量系统满足了课题设定目标。

Electronic components are the basic components of circuits and have a wide range of applications. Traditional manual inspection has many shortcomings, and machine vision size measurement technology came into being. Because of its high sensitivity, high precision and high durability, machine vision has a great help to improve the level of industrial automation and industrial production efficiency. According to the requirements of the subject, taking the single-chip microcomputer chip as the research object and detecting the length and width on the two-dimensional plane of the single-chip microcomputer chip as the research goal, the hardware scheme of the single-chip detection system based on machine vision is designed. The hardware composition includes the selection of light source and lighting method, and the choice of camera and lens. After completing the hardware platform construction, at the same time, a calibration board for camera calibration was produced and about 30 calibration pictures were taken on the debugged hardware platform. Using MATLAB R2016A as the system’s software processing platform, on the one hand, the MATLAB calibration box is used to calibrate the camera on the calibration map, and on the other hand, the image processing code and measurement code for the measurement of the single-chip chip size are written. Among them, the image processing link mainly includes image filtering, binarization and edge extraction. After the size measurement experiment of the single-chip microcomputer chip is completed, the experimental results are compared with the real size, and it can be seen that the built-up machine vision-based measurement system for the dimensions of electronic components meets the set goals of the subject.