Bridging Foundation Models and ASTM Metallurgical Standards for Automated Grain Size Estimation from Microscopy Images

2026-04-20

AI Summary

This study addresses the challenges of automatically extracting ASTM E112-compliant grain size measurements from metallographic micrographs, which are hindered by complex grain morphologies and scarce annotated data. The authors propose a novel approach that integrates foundation vision models with metallographic standards by adapting Cellpose-SAM to metallographic images. This framework leverages Cellpose-SAM’s topology-aware segmentation capability alongside a Jeffries area method module to achieve high-precision grain instance segmentation and size estimation. Remarkably, using only two training samples, the method achieves a mean absolute percentage error of just 1.50% in predicting the ASTM grain size number (G), substantially outperforming baseline models such as U-Net, MatSAM, and Qwen2.5-VL-7B. Furthermore, it provides the first empirical validation of the statistical robustness of the ASTM-recommended minimum of 50 grains for sampling, demonstrating exceptional few-shot generalization performance.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Other Foundations of Computer Vision
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Security and Privacy: Large-scale security measurements

Abstract

Extracting standardized metallurgical metrics from microscopy images remains challenging due to complex grain morphology and the data demands of supervised segmentation. To bridge foundational computer vision with practical metallurgical evaluation, we propose an automated pipeline for dense instance segmentation and grain size estimation that adapts Cellpose-SAM to microstructures and integrates its topology-aware gradient tracking with an ASTM E112 Jeffries planimetric module. We systematically benchmark this pipeline against a classical convolutional network (U-Net), an adaptive-prompting vision foundation model (MatSAM) and a contemporary vision-language model (Qwen2.5-VL-7B). Our evaluations reveal that while the out-of-the-box vision-language model struggles with the localized spatial reasoning required for dense microscopic counting and MatSAM suffers from over-segmentation despite its domain-specific prompt generation, our adapted pipeline successfully maintains topological separation. Furthermore, experiments across progressively reduced training splits demonstrate exceptional few-shot scalability; utilizing only two training samples, the proposed system predicts the ASTM grain size number (G) with a mean absolute percentage error (MAPE) as low as 1.50%, while robustness testing across varying target grain counts empirically validates the ASTM 50-grain sampling minimum. These results highlight the efficacy of application-level foundation model integration for highly accurate, automated materials characterization. Our project repository is available at https://github.com/mueez-overflow/ASTM-Grain-Size-Estimator.

Problem

• grain size estimation
• microscopy images
• ASTM standards
• metallurgical characterization
• instance segmentation

Innovation

• foundation models
• ASTM E112
• grain size estimation
• few-shot learning
• topology-aware segmentation