Deep Learning-Based Semantic Segmentation for Morphological Fractography

Abstract

Fractographic analysis poses a significant challenge for field researchers without specialized training in fractography. To address this issue, the paper proposes an integrated approach comprising four steps of dataset establishment, data augmentation, deep learning SegFormer model and semantic segmentation. An extensive collection of fractography images is formulated and augmented to train the SegFormer model, enabling precise semantic segmentation of morphological fracture regions including cleavage, ductile, dimple, fatigue striations and others. To accommodate the demanding SEM imaging conditions which frequently include distortions, noise, and aberrations, we developed a two-stage method with diverse data augmentation strategies. This method resulted in a robust model demonstrating exceptional performance, as evidenced by high mean Intersection over Union (mIOU) scores and other metrics. The findings validate the potential of deep learning techniques, particularly the SegFormer model's efficacy in morphological fractography image segmentation for the first time. Our work offers a cost-effective, and efficient alternative deep learning approach to traditional experimental fracture analysis, thereby expanding opportunities for a broader range of professionals in the engineering domain.

Keywords: morphological fractography, deep learning, semantic segmentation, data augmentation, SegFormer