Grain and Grain Boundary Segmentation using Machine Learning with Real and Generated Datasets

TL;DR

This paper improves grain boundary segmentation accuracy in microstructure images by training CNNs on a combined dataset of real and artificially generated images, outperforming existing computational methods.

Contribution

It introduces a novel artificial grain image fabrication method and demonstrates enhanced segmentation accuracy using CNNs trained on combined real and synthetic data.

Findings

CNN-based segmentation outperforms traditional computational methods

Synthetic data improves training and accuracy

Dataset and models are publicly available on Kaggle

Abstract

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.