Ehsun Saeed
Automated microstructure classification has the potential to improve the consistency and scalability of metallurgical characterisation; however, industrial datasets frequently exhibit severe class imbalance, where safety-critical microstructures are substantially underrepresented. This study presents a baseline evaluation of rare-phase detection in ultra-high carbon steel (UHCS) microstructures using deep learning. The dataset comprised 961 scanning electron microscopy (SEM) micrographs spanning seven microstructural classes, with Martensite represented by only 36 images (3.75% of the dataset). A frozen ResNet50 transfer-learning framework was evaluated using a stratified train–test split, online data augmentation, and imbalance-aware learning strategies. The baseline model achieved 52.8% accuracy, with Martensite precision of 0.600, recall of 0.429, and F1-score of 0.500. Class-weighted loss increased Martensite recall to 0.857 but reduced overall accuracy to 29.0%, indicating a substantial increase in false-positive predictions. Focal loss achieved the strongest overall performance, with 56.0% accuracy.
@article{30dfa140-999d-4e2e-b1b7-dc0eed625c9f,
title={2026 Saeed Rare Phase Detection UHCS},
author={Ehsun Saeed},
year={2026},
language={en}
}TY - JOUR TI - 2026 Saeed Rare Phase Detection UHCS AU - Ehsun Saeed PY - 2026 LA - en ER -
Robert A. Francis
This document serves as a comprehensive introduction to the metallurgy of steel and its alloys, focusing on various aspects of iron and steel manufact
This paper addresses the challenge of assessing the feasibility of wind power plant projects at sites with insufficient or no local historic wind data
Important advances in electrochemical engineering technology over the last three decades have fostered the development of a lternative methods to alle
Increasing volumes of waste printed circuit boards from obsolete electronic equipment posed escalating environmental risks and resource losses due to