Part inspection machines of industrial manufacturing systems are being newly evolved as intelligent machines with the technology innovation of artificial intelligence. Due to the characteristics of the cast product surfaces, the success rate of a conventional 2D detect detection system is easily affected by illumination location and angle for uneven surfaces and small defects. To solve this problem, a photometric stereo system to generate its reflectance, roughness and slope information is used to generate feature fusion data. This dataset is used to improve the defect detection performance of automatic inspection machines for casting products with a deep learning model. 

J.H. Lee, B.H. Kim, H,K, Lee, and M.Y. Kim, "Multi-Channel Deep-learning Based Auto Defect Detection System using Feature Fused Illumination Images."