In order to improve the accuracy and efficiency of the measurement of the Shell Case size, a measurement system based on machine vision is introduced. Through the preprocessing, threshold segmentationSalgorithm and edge detection of the shell case image. Correlated size measurement of lines and circles in contour using binary search method and Hough transform. The experiment of detecting four sizes of 100 qualified shells shows that the system can realize the rapid and accurate detection of shell casings, and can be used to assess their quality performance. It effectively improves the detection efficiency and further improves the automation level of detection, which has a good application prospect.