The Northeastern University Steel Surface Defects Database includes micrographs of six different defects observed on hot-rolled steel . We use the VGG16 convolutional neural network pre-trained on the ImageNet dataset of natural images to extract feature representations for each micrograph . After applying principal component analysis to extract signal from the feature descriptors, we use k-means clustering to classify the images without needing labeled training data . The approach achieves $99.4\% \pm 0.16\%$ accuracy, and the resulting model can be used to classify new images without retraining . This approach demonstrates an improvement in both performance and utility compared to a previous study . The results provide insight toward applying . applying unsupervised machine learning techniques to problems of interest in materials science to problems in material science. The results are available at the University of Northheastern University of Northeastern. University of N.E.