January_2021_AMP_Digital

A D V A N C E D M A T E R I A L S & P R O C E S S E S | J A N U A R Y 2 0 2 1 1 6 M A C H I E L E A R N I N G MACHINE LEARNING FOR MICROSTRUCTURE CLASSIFICATION: HOW TO ASSIGN THE GROUND TRUTH IN THE MOST OBJECTIVE WAY Martin Müller, Dominik Britz,* and Frank Mücklich, FASM* Saarland University, Germany The application of machine learning to the classification and segmentation of complex microstructures requires special attention when assigning the ground truth. Despite all progress in artificial intelligence, materials science knowledge is still indispensable in this process. *Member of ASM International Degenerate Pearlite Upper Bainite Lower Bainite Debris of Cementite Incompl. Trans- form. Product