Detection of quality is a necessary procedure in the processing of machining punched sheets. It includes detection of the size of the holes and the distance of neighbored holes on the punched sheets and other machining parameters. Detection completed by workers is the traditional method which is low precision and low efficiency. According to the requirement of real industrial production this paper approaches a detection system based on machine vision which is used to detect the machining quality of punched sheets. The system is including the methods of detection of sub-pixel edge and circle fitting, and is used to improve the precision of detection. Experiment suggests that the detection result of this system is better.