Department of Mechatoronics Engineering, National Changhua University of Education, Changhua City 50007, Taiwan.
Department of Telecommunication Engineering, National Kaohsiung University of Science and Technology, Kaohsiung City 80778, Taiwan.
Sensors (Basel). 2020 Sep 29;20(19):5593. doi: 10.3390/s20195593.
Metallography is the study of the structure of metals and alloys. Metallographic analysis can be regarded as a detection tool to assist in identifying a metal or alloy, to evaluate whether an alloy is processed correctly, to inspect multiple phases within a material, to locate and characterize imperfections such as voids or impurities, or to find the damaged areas of metallographic images. However, the defect detection of metallography is evaluated by human experts, and its automatic identification is still a challenge in almost every real solution. Deep learning has been applied to different problems in computer vision since the proposal of AlexNet in 2012. In this study, we propose a novel convolutional neural network architecture for metallographic analysis based on a modified residual neural network (ResNet). Multi-scale ResNet (M-ResNet), the modified method, improves efficiency by utilizing multi-scale operations for the accurate detection of objects of various sizes, especially small objects. The experimental results show that the proposed method yields an accuracy of 85.7% (mAP) in recognition performance, which is higher than existing methods. As a consequence, we propose a novel system for automatic defect detection as an application for metallographic analysis.
金相学是研究金属和合金结构的学科。金相分析可以被视为一种检测工具，用于辅助识别金属或合金，评估合金是否经过正确加工，检查材料中的多个相，定位和描述缺陷，如空隙或杂质，或查找金相图像的损坏区域。然而，金相学的缺陷检测是由人类专家进行评估的，其自动识别在几乎每个实际解决方案中仍然是一个挑战。自 2012 年 AlexNet 提出以来，深度学习已经应用于计算机视觉的不同问题。在这项研究中，我们提出了一种基于改进的残差神经网络（ResNet）的金相分析新型卷积神经网络架构。多尺度 ResNet（M-ResNet），改进方法，通过利用多尺度操作来提高效率，从而准确检测各种大小的物体，特别是小物体。实验结果表明，所提出的方法在识别性能方面的准确率达到 85.7%（mAP），高于现有方法。因此，我们提出了一种新的自动缺陷检测系统，作为金相分析的应用。
