Efficient Phase Segmentation of Light-Optical Microscopy Images of Highly Complex Microstructures Using a Correlative Approach in Combination with Deep Learning Techniques
Open Access
Abstract
Reliable microstructure characterization is essential for establishing process–microstructure–property links and effective quality control. Traditional manual microstructure analysis often struggles with objectivity, reproducibility, and scalability, particularly in complex materials. Machine learning methods offer a promising alternative but are hindered by the challenge of assigning an accurate and consistent ground truth, especially for complex microstructures. This paper introduces a methodology that uses correlative microscopy—combining light optical microscopy, scanning electron microscopy, and electron backscatter diffraction (EBSD)—to create objective, reproducible pixel-by-pixel annotations for ML training. In a semi-automated manner, EBSD-based annotations are employed to generate an objective ground truth mask for training a semantic segmentation model for quantifying simple light optical micrographs. The training masks are directly derived from raw EBSD data using modern deep learning methods. By using EBSD-based annotations, which incorporate crystallographic and misorientation data, the correctness and objectivity of the training mask creation can be assured. The final approach is capable of reproducibly and objectively differentiating bainite and martensite in optical micrographs of complex quenched steels. Through the reduction in the microstructural evaluation to light optical micrographs as the simplest and most widely used method, this way of quantifying microstructures is characterized by high efficiency as well as good scalability.Keywords
This publication has 54 references indexed in Scilit:
- A unified microstructure segmentation approach via human-in-the-loop machine learningActa Materialia, 2023
- A deep learning-based method for segmentation and quantitative characterization of microstructures in weathering steel from sequential scanning electron microscope imagesJournal of Iron and Steel Research International, 2022
- Overview: Computer Vision and Machine Learning for Microstructural Characterization and AnalysisMetallurgical and Materials Transactions A, 2020
- Model Selection and Evaluation for Machine Learning: Deep Learning in Materials ProcessingIntegrating Materials and Manufacturing Innovation, 2020
- Exploring the microstructure manifold: Image texture representations applied to ultrahigh carbon steel microstructuresActa Materialia, 2017
- Computer Vision and Machine Learning for Autonomous Characterization of AM Powder FeedstocksJOM, 2016
- Structural characterization of low-carbon multiphase steels merging advanced research methods with light optical microscopyArchives of Civil and Mechanical Engineering, 2016
- Scanning electron microscopy (SEM) and transmission electron microscopy (TEM) for materials characterization2016
- Characterization and quantification methods of complex BCC matrix microstructures in advanced high strength steelsJournal of Materials Science, 2012
- Hot rolling texture development in CMnCrSi dual-phase steelsMetallurgical and Materials Transactions A, 2002