Machine Vision based Identification and Dimensional Measurement of Electronic Components

Abstract

Machine Vision is an emerging area related to real-time capturing, processing, and analyzing the images for various kinds of scientific and industrial applications. It is robust computing tool, which provides the electronic processing of real time images underpinning for a global society in electronic business and research. It provides services in number of applications in the fields where the identification and measurements of manufactured goods such as that of semiconductor chips, automobile parts etc., is required. Manual measurement of large number of objects in any of these applications can be a tedious and time consuming process, prone to human errors. This can be automated using Machine Vision concepts. In my thesis, I propose a technique of “Machine Vision Based Identification and Dimensional Measurement of Electronic Components” which is based on color pattern matching approach, that enables identification of an electronic component present in a group and gauging gives the dimensional measurement of the electronic component. In Machine Vision it is important to determine which course of action suits the best for processing of images in shortest amount of time, using the resources most efficiently and minimizing the cost. Image processing can be done by developing softwares using Ccompiler, Matlab etc. but these methods are quite cumbersome and require great deal of programming skills. We have made use of National Instrument’s Machine Vision tool Vision Assistant 7.1 to make the programming easy, fast and accurate. The electronic components are matched with the previously saved templates, in which their own characteristics are saved.