... segmentation which combines object detection and semantic segmentation. This study focused on practical matters such as building data set consist of various kinds of wear debris, architecture setting and testing of transfer learning procedure. State-of-art accuracy of identifying as well as localizing debris...

... sliding wear particles, which are similar in morphology while different in wear mechanism. Design/methodology/approach A CNN model named DWear is proposed to semantically segment fatigue, severe sliding particles and four other types of particles, that is, chain, spherical, cutting and oxide particles...