Efficient Semi-Automated Material Microstructure Analysis Using Deep Learning: A Case Study in Additive Manufacturing

TL;DR

This paper introduces a semi-automated deep learning pipeline for microstructure segmentation in additive manufacturing, significantly reducing manual effort and improving accuracy through active learning and core-set sampling strategies.

Contribution

It presents a novel active learning framework combining U-Net segmentation with core-set sampling (SMILE) for efficient, scalable microstructure analysis in heterogeneous materials.

Findings

SMILE outperforms other sampling strategies in segmentation accuracy.

Manual annotation time reduced by approximately 65%.

Framework applicable to diverse materials systems.

Abstract

Image segmentation is fundamental to microstructural analysis for defect identification and structure-property correlation, yet remains challenging due to pronounced heterogeneity in materials images arising from varied processing and testing conditions. Conventional image processing techniques often fail to capture such complex features rendering them ineffective for large-scale analysis. Even deep learning approaches struggle to generalize across heterogeneous datasets due to scarcity of high-quality labeled data. Consequently, segmentation workflows often rely on manual expert-driven annotations which are labor intensive and difficult to scale. Using an additive manufacturing (AM) dataset as a case study, we present a semi-automated active learning based segmentation pipeline that integrates a U-Net based convolutional neural network with an interactive user annotation and correction interface and a representative core-set image selection strategy. The active learning workflow iteratively updates the model by incorporating user corrected segmentations into the training pool while the core-set strategy identifies representative images for annotation. Three subset selection strategies, manual selection, uncertainty driven sampling and proposed maximin Latin hypercube sampling from embeddings (SMILE) method were evaluated over six refinement rounds. The SMILE strategy consistently outperformed other approaches, improving the macro F1 score from 0.74 to 0.93 while reducing manual annotation time by about 65 percent. The segmented defect regions were further analyzed using a coupled classification model to categorize defects based on microstructural characteristics and map them to corresponding AM process parameters. The proposed framework reduces labeling effort while maintaining scalability and robustness and is broadly applicable to image based analysis across diverse materials systems.