Microstructure Cluster Analysis with Transfer Learning and Unsupervised Learning
Microstructure Cluster Analysis with Transfer Learning and Unsupervised Learning
复制标题
DOI：
10.1007/s40192-018-0116-9
复制
发表时间：
2018-09-01
影响因子：
3.3
通讯作者：
Holm, Elizabeth A.
中科院分区：
文献类型：
--
作者：
Kitahara, Andrew R.;Holm, Elizabeth A.
我们应用计算机视觉和机器学习的方法分析了两个显微结构图像的数据集。转移学习流水线利用预先训练的卷积神经网络的完全连接层作为图像表示。无监督学习方法使用图像表示来发现两个数据集中视觉上不同的图像簇。最小监督聚类方法将显微图像分类为视觉上相似的组。这种方法成功地对钢铁表面缺陷数据集中的图像进行了分类，其中图像类别在视觉上是不同的，也是在人类难以分类的断口表面数据集中。我们发现，无监督的迁移学习方法给出的结果与完全监督的定制方法相当。
We apply computer vision and machine learning methods to analyze two datasets of microstructural images. A transfer learning pipeline utilizes the fully connected layer of a pre-trained convolutional neural network as the image representation. An unsupervised learning method uses the image representations to discover visually distinct clusters of images within two datasets. A minimally supervised clustering approach classifies micrographs into visually similar groups. This approach successfully classifies images both in a dataset of surface defects in steel, where the image classes are visually distinct and in a dataset of fracture surfaces that humans have difficulty classifying. We find that the unsupervised, transfer learning method gives results comparable to fully supervised, custom-built approaches.