Anomaly surface inspection · MSc thesis, rebuilt as a demo
Everything runs in your browser. The surface is a real thesis microscope scan; the wider industrial dataset stays confidential. · The model learns this surface's normal texture live, with no defect labels.

Find the defects nobody labelled

A model that learned this real scan's normal texture inspects it: wherever it can't reproduce what it sees, it flags a defect. Click any patch to interrogate it.

scanning… click anywhere on the surface to inspect that patch

Where do you draw the line?

Reconstruction error of clean patches vs. patches with a seeded defect, the two histograms the threshold has to separate. The suggested cut maximises true positives against a tight false-positive budget; that's how the thesis picked its operating point from the ROC curve.

clean patches patches with a seeded defect
Threshold
the numbers behind these charts

Patch under the microscope

What the model saw, what it reconstructed, and where the two disagree: the same input · reconstruction · difference triptych the thesis used to debug the network.

input patch
reconstruction
difference ×8
reconstruction error (MSE)