Detect missed scans and theft at self-checkouts

Retailers detect theft and missed scans at self-checkouts

Needs setupAI Act: no extra obligationsInspecting by cameraRetail & e-commerce

Fits: Sales · Legal & compliance

The camera above the checkout notices when an item has been put down but not scanned, and asks on screen for it to be scanned again. Fewer items go through unpaid, and the checkout supervisor helps where needed instead of watching every purchase.

Is this for you?

  • You have several self-checkouts and noticeable stocktaking differences for goods sold there.
  • You want to correct mistakes by customers, who are mostly honest, in a friendly way, without facial recognition and without suspect lists.
  • Your checkout provider offers camera-based recognition, or you can test it with them in one store.
First step today

Today, put six to eight items on the bagging area of a checkout, photograph them from above with no people in the picture and write down the list of scanned items, leaving one out on purpose. Use the template below to have the AI compare the two and see whether it finds the missing item. This shows on a small scale how the recognition works and where it fails.

How to go about it

  1. Define the checkout situations to be detected
  2. Set up cameras above the scanner and bagging area
  3. Record and label test purchases
  4. Test the recognition and set the intervention threshold
  5. Build in the on-screen prompt and help from staff
  6. Review false alarms and missed cases monthly

Templates to copy

Try it now
in the training
Analyse
in the training
Plan the rollout
in the training
Included in the training

The complete guide

  • 6 steps explaining exactly what to do
  • 3 proven templates to copy into your own AI
  • Safe use: data, checking, deciding, informing
  • Pitfalls, effort and how to recognise success

With the training you get all 430 guides for as long as your access runs.

See the trainingOne-off per person, no subscription

Same approach, other use cases

24 more use cases follow the pattern “Inspecting by camera”.

Have AI estimate nutritional values from food photosIdentify plant diseases and pests from photosAnalyse match situations and movements on videoDetect damage to parcels and pallets by cameraDetect forest damage by satellite and droneDetect missing protective equipment and hazards with camerasDocument construction defects and progress with photosFind heat losses in the district heating network by thermal imagingHave AI check fibre and mast installations by photoHave AI correct exercise technique via cameraIdentify animal species in camera trap and audio recordingsInspect products on the line by camera
‹ PreviousSee all use casesNext ›

EH-08 · Legal status 08.10.2026