Unsupervised machine learning via transfer learning and k-means clustering to classify materials image data

TL;DR

This paper presents an unsupervised image classification system for microstructural steel defect images using transfer learning with VGG16, PCA, and k-means clustering, achieving high accuracy without labeled data.

Contribution

It introduces a high-performance unsupervised classification method combining transfer learning, PCA, and k-means for materials image data, improving accuracy and utility over prior methods.

Findings

Achieved 99.4% classification accuracy

Demonstrated effective use of transfer learning with VGG16

Provided insights into the influence of each processing step

Abstract

Unsupervised machine learning offers significant opportunities for extracting knowledge from unlabeled data sets and for achieving maximum machine learning performance. This paper demonstrates how to construct, use, and evaluate a high performance unsupervised machine learning system for classifying images in a popular microstructural dataset. The Northeastern University Steel Surface Defects Database includes micrographs of six different defects observed on hot-rolled steel in a format that is convenient for training and evaluating models for image classification. 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. A sensitivity analysis is conducted to better understand the influence of each step on the classification performance. The results provide insight toward applying unsupervised machine learning techniques to problems of interest in materials science.