抄録
In the manufacturing process of machine products, it is very important to automate the manual visual inspection in detecting microscopic surface defects in order to improve the efficiency and eliminate human errors as well. We present an automatic system to detect such surface defects based on iterative photometric stereo techniques. Our system consists of a high-resolution camera equipped with a telecentric lens, and a device to change light directions using 60 LED light bulbs. In this paper, we propose a convergence condition based on the change of amount of albedo. Examples are provided to demonstrate the effectiveness of the proposed method.
