In this study, we have developed a movable defect detection system based on a vision module with machine-learning algorithm for distinguishing product quality. Machine-learning model determined the results in good or no good through images acquired from the vision module consisting of a camera, processor unit, and lighting. To ensure versatility for use in a variety of settings, we have integrated a robot arm and cart for the movable defect detection system, and the robot arm that adjusts the focus length is made to be able to rotate in all directions. The type of defect was divided into eccentricity defect and printing defect. As a result, it was confirmed that classification accuracy showed 0.9901 in our developed device.

• 심재삼(한국생산기술연구원) | Jaesam Sim Corresponding author
• 양승진(전남대학교) | S. J. Yang
• 박정수(조선대학교) | JUNGSOO PARK