Defect detection on the surface of the technical ceramics using image processing and deep learning algorithms

A digital microscope is considered as an instrument for ceramic disks evaluation process automatization in the production cycle. It provides an opportunity for visual defect detection in range 50 to 500 μm, The use of digital filtration, adaptive histogram equalization, threshold function, feature detection as a classical approach showed a great result. Deep learning has proven its effectiveness, selecting features of the defect and presented more stable results in defect detection.