Instance Segmentation for Direct Measurements of Satellites in Metal Powders and Automated Microstructural Characterization from Image Data

Abstract

We propose instance segmentation as a useful tool for image analysis in materials science. Instance segmentation is an advanced technique in computer vision which generates individual segmentation masks for every object of interest that is recognized in an image. Using an out-of-the-box implementation of Mask R-CNN, instance segmentation is applied to images of metal powder particles produced through gas atomization. Leveraging transfer learning allows for the analysis to be conducted with a very small training set of labeled images. As well as providing another method for measuring the particle size distribution, we demonstrate the first direct measurements of the satellite content in powder samples. After analyzing the results for the labeled data dataset, the trained model was used to generate measurements for a much larger set of unlabeled images. The resulting particle size measurements showed reasonable agreement with laser scattering measurements. The satellite measurements were self-consistent and showed good agreement with the expected trends for different samples. Finally, we provide a small case study showing how instance segmentation can be used to measure spheroidite content in the UltraHigh Carbon Steel Database, demonstrating the flexibility of the technique.

Recent advances and applications of deep learning methods in materials science

“…In this case, DL models designed for the detection or instance segmentation can be used to resolve overlapping instances. In one such study, Cohn and Holm applied DL for instance-level segmentation of individual particles and satellites in dense powder images 235 . Segmenting each particle allows for computer vision to generate detailed size and morphology information which can be used to supplement experimental powder characterization for additive manufacturing.…”

AtomVision: A Machine Vision Library for Atomistic Images

“…For the machine learning models, we primarily use the STEM data set developed with the convolution approximation. We use several machine/deep learning approaches, such as clustering, classification with convolution and graph convolution neural network, fully convolutional neural network using U-Net, and generative adversarial network. − We provide a brief description of these methods, and more details can be found elsewhere …”

“…Because of rapid growth in computer-vision techniques, , its application to atomic scale image data is natural. These data can be obtained from experimental, as well as computational, methods, and recently, their usage has become widespread. − Nevertheless, an integrated library to capture, curate, generate data sets, and apply data-analytics methods is still needed.…”

Recent Advances and Applications of Deep Learning Methods in Materials Science

“…In this case, DL models designed for detection or instance segmentation can be used to resolve overlapping instances. In one such study, Cohn and Holm applied DL for instance level segmentation of individual particles and satellites in dense powder images [254]. Segmenting each particle allows for computer vision to generate detailed size and morphology information which can be used to supplement experimental powder characterization for additive manufacturing.…”