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

2026-03-14

AI Summary

This study addresses the high heterogeneity in material microstructure images caused by variations in processing and testing conditions, which severely limits the generalization of conventional methods and necessitates extensive manual annotation. To overcome these challenges, this work proposes a semi-automatic segmentation framework based on active learning, integrating a U-Net architecture, an interactive correction interface, and a novel image selection strategy termed SMILE—leveraging maximin Latin hypercube sampling in the embedding space. The SMILE strategy significantly outperforms both manual selection and uncertainty-based sampling, enhancing model performance while substantially reducing annotation costs. Experimental results demonstrate that the macro F1-score improves from 0.74 to 0.93, with approximately 65% reduction in manual labeling time, and successfully establish meaningful correlations between defect characteristics and additive manufacturing process parameters, offering an efficient, scalable, and robust solution for microstructure analysis.

Technology Category

• Machine Learning: Active Learning
• Computer Vision: Segmentation
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation 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.

Problem

• image segmentation
• microstructure analysis
• additive manufacturing
• heterogeneous materials
• manual annotation

Innovation

• active learning
• U-Net
• SMILE
• semi-automated segmentation
• additive manufacturing