Research On High Precision Measuring Technology Of Workpiece Size Based On Machine Vision

With the rapid development of intelligent manufacturing,the demand for workpieces in enterprise production design has become larger,and the accuracy requirements of workpieces have become higher and higher.For the detection of workpieces,traditional manual measurement technology has been unable to meet the required measurement accuracy of workpieces.The workpiece measurement technology based on machine vision not only has fast detection speed and high efficiency,but also can measure the workpiece size more accurately,and it is easier to realize online detection.This paper takes circular gear workpiece as the research object.The high-precision measurement system of workpiece size based on machine vision has been researched and designed,and this system was applied to complete the measurement of gear workpiece size.In this paper,algorithms for image preprocessing,feature extraction,curve fitting,angle measurement and other technologies are studied.The main research contents are as follows:Firstly,the preprocessing algorithm of the workpiece image is studied.Aiming at the problem of uneven illumination of images,the Laplace transform algorithm is proposed to enhance the illumination.The image filtering process uses bilateral filtering for processing,which can both remove noise and protect the target edge.Secondly,the algorithm of workpiece image feature extraction is studied.Researches on corner and edge detection,image segmentation and contour extraction algorithms were conducted respectively.For the image segmentation of the workpiece,a local threshold segmentation algorithm is selected.Because the OTSU segmentation algorithm will cause defects and glitches,so the local threshold segmentation is selected for accurate image segmentation.In terms of corner and edge detection,this paper proposes an improved Harris algorithm for edge and corner detection of workpiece images.Experimental results show that the improved Harris algorithm detects edges and corners accurately.For contour extraction,the eight-neighbor contour tracking algorithm was adopted,and the workpiece contour was better extracted.Then,the researches on the curve fitting and angle measurement of the workpiece image were carried out.In this paper,Hough circle fitting is used for curve fitting of circular gear workpiece.First of all,the curve fitting of the addendum circle,the root circle,the graduation circle and the inner circle was done by Hough fitting algorithm,and the center and radius of the four circles were measured.Through experiments and data comparison,it can be seen that the algorithm can accurately fit the size.After that,the gear angle was measured by straight line fitting.Finally,the design of high-precision measurement system based on machine vision workpiece size is completed.The hardware platform of the system was built first,and then the system software was developed.The system debugging is realized by measuring the size of the gear workpiece,and the error of the size measurement is analyzed.