Research On Detection System Of Cigarette Case Based On Machine Vision

The Detection System of Cigarette Case is an auto-detection which is designed and realized by applying optical, electric, mechanic, computer, image processing technology. It is applied broadly to high-speed auto product line in many industries such as tobacco, plastic, pharmacy and food, and it could be able to detect and remove metallic and non-metallic impurities from product manufacturing equipment. It has the high-speed, efficient, precise character. Its usage has greatly enhanced the degree of automation of product line, debased the labor intensity, and improved the work environment. Therefore, this system has the broad application prospect.In this paper, research on image processing such as Templates-Matching, Picture-Revolve, Texture-Analysis, Line-Detection is developed. For the sake of improving the detect precision and calculation efficiency of computer vision recognition (auto positioning) system, some relative fundamental algorithms were discussed. An improved rapid median filter is developed utilizing the relationship between the front and back filter windows; to compare with the traditional median filter, the improved rapid algorithm has a higher computing efficiency for it can prevent all the data in current window to participate in sorting calculation. The template matching method is to recognize the characters image printed on the top surfaces of the pistons to determine whether the four pistons assembled in one cylinder are of the same type to compared with the first one, this method possesses following advantages: more rapid recognition speed, higher efficiency, better universality and more wide application fields.At last, based on windows, VC++ language is used for developing the program for The Detection System of Cigarette Case.