Faulty accumulations based on image processing

Abstract

In the era where automation is being applied on everything and contactless products are given the highest priority by companies. Computer vision applications can be used to provide contactless inspection, which are able to reach high production numbers without errors. In this paper. In this study, it was aimed to detect faulty bottle accumulations and remove them from the conveyer belt. Mineral water is bottled in factories and packaged to produce six-bottle and twenty-bottle packs transported on a conveyor belt. Faulty packages might cause a problem at packaging time. In this work, an image processing application is implemented which can detect faulty accumulations and remove them from the production line for a flawless production. Sobel filter is used for edge detection and Hough transform is used for calculation of number of bottles in packages. As a result of the experimental studies performed, it has been determined that the proposed approach gives fast, accurate and reliable results. The ones labelled as faulty accumulations are eliminated from conveyor belt by means of a boxer motor.