Complex-Phase Steel Microstructure Segmentation Using UNet: Analysis across Different Magnifications and Steel Types

Abstract

The quantification of the phase fraction is critical in materials science, bridging the gap between material composition, processing techniques, microstructure, and resultant properties. Traditional methods involving manual annotation are precise but labor-intensive and prone to human inaccuracies. We propose an automated segmentation technique for high-tensile strength alloy steel, where the complexity of microstructures presents considerable challenges. Our method leverages the UNet architecture, originally developed for biomedical image segmentation, and optimizes its performance via careful hyper-parameter selection and data augmentation. We employ Electron Backscatter Diffraction (EBSD) imagery for complex-phase segmentation and utilize a combined loss function to capture both textural and structural characteristics of the microstructures. Additionally, this work is the first to examine the scalability of the model across varying magnifications and types of steel and achieves high accuracy in terms of dice scores demonstrating the adaptability and robustness of the model.

A Deep Learning Approach to Semantic Segmentation of Steel Microstructures

“…U-Net is commonly used in the context of semantic image segmentation, and its effectiveness in capturing both global context and fine details makes it particularly wellsuited for tasks such as medical image segmentation and satellite image analysis, and it is also employed for the segmentation of materials microstructures [28,29]. U-Net is characterized by a U-shaped architecture with an encoder-decoder structure and skip connections.…”