Research On Two-Dimensional Dimension Measurement Technology Of Mobile Phone Based On Machine Vision

In the era with rapid development of information technology,mobile phones have become an important tool for people to access information and communication,while its demand and production is extremely large,which makes the competition between mobile phone manufacturers more and more intense?Thus to ensure the quality of mobile phones,production efficiency is an important means for mobile phone manufacturers to survive in the competition.In the mobile phone production process,the enterprise will set the standard parts of the mobile phone requirements,such as the size of the gap between screen and the shell,the length and width of the inner shell,the size of decorative pieces,etc.,to determine whether the mobile phone to meet the factory requirements.Inefficient,time-consuming,measurement accuracy of the manual measurement technology is clearly unable to adapt to the requirements of efficient,high-speed,high-precision modern production.Therefore,aiming at the shortcomings of artificial measurement technology,this paper developed a two-dimensional measurement system based on machine vision,and proposed a method to extract the specified edge in the complicated environment,so as to realize the automatic measurement of the two-dimensional size of the mobile phone.The main research work and innovation of this paper are summarized as follows:1.According to the requirements of mobile phone size measurement,the system design includes image acquisition,motion control and software.Then,the hardware model,software development platform and image processing function library are selected according to the actual requirements.2.For different measurement parts of the imaging characteristics of the design and selection of appropriate lighting programs,highlighting the image of the target edge characteristics.3.In order to extract the target edge of the image,the visual measurement algorithm of the two-dimensional size of the mobile phone is studied.A method of target edge extraction is proposed,which is to set the standard region of interest in advance,and use the gray scale distribution of H and S channel images in the standard area as the template to match the region witch contain the target edge.And then the target edge feature points are extracted by the canny operator and the gradient of the pixels on the auxiliary line.Finally,the least squares method is used to fit the target edge.4.Use the camera calibration technology to convert the image size to actual size.The innovation of this paper is to propose an edge extraction method based on template matching,canny operator,auxiliary straight line and least squares method,and it can be applied to the two-dimensional measurement of mobile phone,which can accurately extract the target edge in complicated environment.