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

TL;DR

This paper presents an automated, foundation model-based pipeline for accurate grain size estimation from microscopy images, integrating ASTM standards and demonstrating high few-shot accuracy.

Contribution

It introduces a novel pipeline adapting Cellpose-SAM for microstructures, achieving superior accuracy and robustness in automated grain size estimation.

Findings

Achieves as low as 1.50% MAPE with only two training samples.

Outperforms classical U-Net, MatSAM, and Qwen2.5-VL-7B in benchmarks.

Maintains topological separation and robustness across varying grain counts.

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.