We describe a machine vision system for inspecting bearings, whichare an important part of electro-mechanical kWh meters. The systemconsists of a personal computer with a frame grabber, a black and whiteprogressive scan CCD camera, and a mechanical device with a steppermotor controlled by a special controller connected to the RS232 port ofthe personal computer. The quality of a bearing depends on theeccentricity of the needle and the length of the needle that extends outof the cylinder. These two parameters are robustly and accuratelydefined by the Hough transform and the regression methods. The resultspresented show that the proposed machine vision system allows accurate,reproducible, and robust inspection of bearings of electro-mechanicalkWh meters, and it may be a valuable tool for ensuring high-end-productquality
展开▼