An Image-Based System for Measuring Workpieces

Aiming at the problems in parameter measuring of small-size workpieces, a real-time detection system is developed based on machine vision. The system's hardware composition and software design proposal are introduced, and the method of using digital image processing technology to measure geometrical size is elaborated. First, the image is acquired through industrial camera in the system. Then, the image is sent to the processing unit for processing, including the image filtration, template matching and image edge detection. Finally, the geometrical sizes are measured based on the calibration information of the system. The experiment shows that the system has a measurement error of less than +/- 0.05 mm and has the advantages of non-contact, rapid speed, high precision and strong anti-interference capability, which provides a new approach for the online non-defective detection of the workpieces.