Skip to the card

Card 842 of 9832026-09-30 issue

Observed arrival · 2026-09-30

Tensor Material measures pores in material images

tensormaterial.tech Visit website
Editorial interest 76/100 Selection signal · not a rating of the site

A research software project for segmenting pores in material images, measuring their geometry, and assembling analysis reports.

Landing page captured for the 2026-09-30 issue.
For
Materials researchers analyzing porous microstructures
Worth noticing
One control image reports 82.18% IoU and 90.22% Dice; the page says other samples require separate validation.

Field notes

The described process runs from operator-edited pore boundaries to trained segmentation models, then to measurements and statistical reports. It distinguishes physical dimensions, calculated using an image scale, from porosity, defined as the pore-area share of a two-dimensional section; the reported comparison metrics apply to one control image only.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

○OpenPublic substance visible
✦PrettyNotable craft visible
◎NicheUnusually specific use

One card from the complete issue

Ask the Descendants

390,826 arrived 1,000 judged 983 catalogued Enter the complete issue
tensormaterial.tech

Landing page observed 2026-09-30. The live site may have changed.