An Experimental Study Of Glass Defects Detecting System

In the glass production line, it's not allowed for a large number of obvious defections on the glasses, it would affect its quality. Therefore, it has great value to develop a low-cost inspection system. This paper is the premier experimental work done by the manufactures for the development of detection system.As to glass defection, the author concentrate on developing a detection system with excellent result—lower price and better performance. This paper introduces image processing technique including image filtering and image segmentation in detail and ameliorates the typical median filtering arithmetic and identification method. The paper seeks out the fastest image segmentation technique by analyzing and comparing a variety of image segmentation technique, so as to found a foundation for distilling and analyzing the blemish. The paper analyses a variety of image processing technique and identification method, then raises a specific scheme for the detection of the glass defection detection system.The hardware part of the system has main components as following: the camera, image acquisition card, micro-computer components. Software system mainly uses Visual C + + 6.0 programming environment. Glass has been initially completed the detection system of early experiments. After testing, it has the initial high-performance in precise targets, and it can quickly and accurately detect the glass defects. The experimental work laid a solid foundation for the latter part of the production line.