This paper addresses the problem of creating a large quantity of high‐quality training segmentation masks from scanning electron microscopy (SEM) images. The images are acquired from concrete samples that exhibit progressive amounts of degradation resulting from alkali–silica reaction (ASR), a leading cause of deterioration, cracking and loss of capacity in much of the nation's infrastructure. The target damage classes in concrete SEM images are defined as paste damage, aggregate damage, air voids and no damage. We approached the SEM segmentation problem by applying convolutional neural network (CNN)‐based methods to predict the damage classes due to ASR for each image pixel. The challenges in using the CNN‐based methods lie in preparing large numbers of high‐quality training labelled images while having limited human resources. To address these challenges, we designed damage‐ and context‐assisted approaches to lower the requirements on human resources. We then evaluated the accuracy of CNN‐based segmentation methods using the datasets prepared with these two approaches.

中文翻译：

---

混凝土损伤多类语义图像分割训练方法

本文解决了从扫描电子显微镜 (SEM) 图像创建大量高质量训练分割掩模的问题。这些图像是从混凝土样品中获取的，这些样品显示出由碱 - 二氧化硅反应 (ASR) 导致的逐渐降解量，这是导致该国大部分基础设施退化、开裂和容量损失的主要原因。混凝土 SEM 图像中的目标损伤等级定义为糊状损伤、骨料损伤、气孔和无损伤。我们通过应用基于卷积神经网络 (CNN) 的方法来预测每个图像像素的 ASR 损伤类别，从而解决 SEM 分割问题。使用基于 CNN 的方法的挑战在于在人力资源有限的情况下准备大量高质量的训练标记图像。为了应对这些挑战，我们设计了损害和情境辅助方法来降低对人力资源的要求。然后，我们使用这两种方法准备的数据集评估了基于 CNN 的分割方法的准确性。