The Whole Scheme And System Design Of PCB Board Defect Detection Based On Machine Vision

With the rapid development of electronic industry,the demand for PCB board is more and more large,and the requirement for PCB quality is more and more strict.Therefore,the defect detection of PCB board becomes more and more important.The defect detection of PCB board will be realized by automatic optical technology(AOI).By collecting the image,the software algorithm is used to realize the processing of the image data,so as to realize the defect detection,which has the advantages of no damage,fast speed and high precision.In this paper,through the PCB bare board surface defect detection research,designed a set of AOI detection scheme.First is the most important part of image acquisition.In order to capture high quality PCB board images,the selection,installation,adjustment principle and camera calibration of hardware such as camera,lens and light source are introduced in detail.High quality images will simplify the detection algorithm,improve efficiency and save resources.Secondly,Sobel algorithm is improved to extract the edge of PCB image,and the binarization algorithm is used to obtain clearer image edge contour.Finally,aiming at the detection of PCB board defects,the high quality images collected by the camera are used to process the contour images with high contrast and clear edges by combining with Sobel algorithm.The template matching algorithm is proposed to locate the image,and then the defect detection of the image is carried out by BLOB algorithm and least square method.For the common circuit break,short circuit,sag,bulge and other defects are tested and verified.The experimental results show that the detection scheme designed in this paper can detect the common defects of PCB board quickly and accurately.