Grain and Grain Boundary Segmentation using Machine Learning with Real and Generated Datasets
This work addresses the time-consuming and inaccurate segmentation in materials science, offering a more efficient and accurate method for analyzing microstructures, though it is incremental as it builds on existing machine learning approaches.
The paper tackles the problem of grain and grain boundary segmentation in microstructure images by using Convolutional Neural Networks trained on a mix of real and generated data, achieving significantly improved accuracy compared to existing computational methods, with benchmarks provided for over 400 manually segmented images.
We report significantly improved accuracy of grain boundary segmentation using Convolutional Neural Networks (CNN) trained on a combination of real and generated data. Manual segmentation is accurate but time-consuming, and existing computational methods are faster but often inaccurate. To combat this dilemma, machine learning models can be used to achieve the accuracy of manual segmentation and have the efficiency of a computational method. An extensive dataset of from 316L stainless steel samples is additively manufactured, prepared, polished, etched, and then microstructure grain images were systematically collected. Grain segmentation via existing computational methods and manual (by-hand) were conducted, to create "real" training data. A Voronoi tessellation pattern combined with random synthetic noise and simulated defects, is developed to create a novel artificial grain image fabrication method. This provided training data supplementation for data-intensive machine learning methods. The accuracy of the grain measurements from microstructure images segmented via computational methods and machine learning methods proposed in this work are calculated and compared to provide much benchmarks in grain segmentation. Over 400 images of the microstructure of stainless steel samples were manually segmented for machine learning training applications. This data and the artificial data is available on Kaggle.