发表机构
Institute of Physics, Bahauddin Zakariya University（巴哈丁·扎卡里亚大学物理研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对SEM图像分类中的信息泄漏问题，提出区域留出协议（LORO），在316L不锈钢氢脆检测中，LBP+SVM以0.79平衡准确率优于深度学习模型，并经置换检验验证，证明纹理特征可有效识别充氢特征。
AI 中文摘要
扫描电子显微镜（SEM）通常用于表征结构钢中氢脆（HE）引起的微观结构变化。机器学习可以自动化这种表征，但模型往往使用图像级划分进行评估。当多张图像来自同一试样区域时，此类划分会在训练集和测试集之间泄漏信息。在此，我们提出一种区域留出协议，用于对316L不锈钢的原始（AR）和充氢（H2）SEM显微图像进行分类，该协议基于对14个空间区域（8个AR，6个H2；共31张图像）的留一区域交叉验证（LORO）。我们比较了基于局部二值模式（LBP）、灰度共生矩阵（GLCM）、在143张未标记SEM图像上预训练的自监督卷积嵌入以及卷积神经网络（CNN）的六种特征-分类器组合。最简单的纹理方法，即LBP结合支持向量机（LBP+SVM），表现最佳，实现了0.79的平衡准确率、0.69的H2召回率和0.82的H2精确率，优于所有深度学习及组合特征模型。组级置换检验（从3,003种可能的区域到标签分配中抽样500次置换）得到p=0.008，表明该结果不能由区域结构的偶然对齐来解释。在完整数据集上训练的CNN生成的Grad-CAM图倾向于集中在局部表面和晶界特征上，这些是已知发生氢致形态变化的区域。在防泄漏、统计验证的协议下，纹理描述符即使在样本较少的情况下也能从SEM显微图像中恢复充氢特征，且该协议可扩展到其他合金体系中更大规模的氢脆检测研究。
英文摘要
Scanning electron microscopy (SEM) is routinely used to characterize the microstructural changes caused by hydrogen embrittlement (HE) in structural steels. Machine learning can automate this characterization, but models are often evaluated using image-level splits. When several images come from the same specimen region, such splits leak information between the training and test sets. Here, we propose a region-held-out protocol for classifying as-received (AR) and hydrogen-charged (H2) SEM micrographs of 316L stainless steel, based on Leave-One-Region-Out (LORO) cross-validation over 14 spatial regions (8 AR, 6 H2; 31 images). We compared six feature-classifier combinations built on local binary patterns (LBP), grey-level co-occurrence matrices (GLCM), self-supervised convolutional embeddings pretrained on 143 unlabeled SEM images, and a convolutional neural network (CNN). The simplest texture approach, LBP with a support vector machine (LBP+SVM), performed best, achieving a balanced accuracy of 0.79, H2 recall of 0.69, and H2 precision of 0.82, outperforming every deep-learning and combined-feature model. A group-level permutation test (500 permutations sampled from the 3,003 possible region-to-label assignments) yielded p = 0.008, indicating that the result cannot be explained by a chance alignment of the region structure. Grad-CAM maps from a CNN trained on the full dataset tended to concentrate on localized surface and grain-boundary features, where hydrogen-induced morphological changes are known to occur. Under a leakage-safe, statistically validated protocol, texture descriptors recover a hydrogen-charging signature from SEM micrographs even with few samples, and the same protocol can be extended to larger HE detection studies in other alloy systems.
