Cell sizes of a foam from an SEM image

An SEM image shows the cells of a foam, and measuring them by hand is slow. This case study takes one SEM image of a foam and gets the sizes of the cells that lie fully inside it. The work was done in GeoDict.

SEM image of a foam with polyhedral cells, scale bar 200 µm.
The SEM image.
The same SEM image with the evaluated cells marked in orange and the cells at the image edge or below the minimum size in blue.
The cells found in it. Orange cells are evaluated, blue ones are left out.

Finding the cells

The cells are marked by a 2D U-Net, a neural network for image segmentation, which GeoDict’s AI segmentation applies to the image. cvt engineering trained it on eleven SEM images, this one among them. It marks the cells together with their floors and leaves the walls.

A threshold on the same image

A grey value threshold after Otsu takes the dark openings and the darker cell floors and leaves out the brightly lit cells. The picture shows the threshold and the model on the same detail.

The same detail of the SEM image twice. On the left a threshold marks only the dark cells, on the right the model marks the cells with their floors.
The same detail, segmented by a threshold and by the model.

Cell sizes

Each connected marked area counts as one cell and gets the diameter of the circle with the same area. Cells cut by the image edge are left out, and so are areas below a minimum size, which the analyst chooses.

Histogram of the equivalent cell diameter of the evaluated cells, with D10, D50 and D90 marked.
Distribution of the equivalent cell diameter.

Cell sizes across the image

Coloured by diameter, the image shows large and small cells mixed across the field of view.

The SEM image with each evaluated cell coloured by its equivalent diameter, from blue for small to orange for large cells.
The evaluated cells, coloured by their equivalent diameter.

Limits

The model saw this image during its training, so this is not a test on an unknown sample. The diameters describe the cells as they appear in the image plane and say nothing about their volume.

The analysis with the GeoDict Copilot. The clock in the video shows real time.

Made with the GeoDict Copilot

The GeoDict Copilot, the AI agent that cvt engineering develops for GeoDict, ran this analysis. An engineer gave it the image, its pixel size and the model file. The Copilot wrote and ran the GeoDict macros and built the report.