English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose instance segmentation as a useful tool for image analysis inmaterials science. Instance segmentation is an advanced technique in computervision which generates individual segmentation masks for every object ofinterest that is recognized in an image. Using an out-of-the-box implementationof Mask R-CNN, instance segmentation is applied to images of metal powderparticles produced through gas atomization. Leveraging transfer learning allowsfor the analysis to be conducted with a very small training set of labeledimages. As well as providing another method for measuring the particle sizedistribution, we demonstrate the first direct measurements of the satellitecontent in powder samples. After analyzing the results for the labeled datadataset, the trained model was used to generate measurements for a much largerset of unlabeled images. The resulting particle size measurements showedreasonable agreement with laser scattering measurements. The satellitemeasurements were self-consistent and showed good agreement with the expectedtrends for different samples. Finally, we provide a small case study showinghow instance segmentation can be used to measure spheroidite content in theUltraHigh Carbon Steel Database, demonstrating the flexibility of thetechnique.

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