Home / Food industry / TOMRA Food LUCAi
TOMRA Systems ASA (Asker, NO)TOMRA Food LUCAi
Deep-learning model on TOMRA optical sorting machines that sorts and grades fresh fruit by defects.
Shared spot3of 16 professional tools with a GDPR profileOur summary of what the provider itself publishes about your data: whether the data is stored in the EU (2 points), whether there is a certification or GDPR guarantee (1) and whether the provider is based in the Netherlands or the EU (1). 3 or 4 points is Strong, 2 Good, 1 Limited, 0 Unknown. How we measure in food industry
GDPR: Good
- Provider based in the EU
- Publishes certification/GDPR safeguards
Priceon request
Free trialNone foundNot found on the provider's site when checked on 2 November 2026
Based inAsker, NOEU
ModelNot publicown image recognition model (according to the provider); deep learning model trained on its own fruit images from 20+ seasons, runs on the sorting machine (according to the provider); GDPR and standard contractual clauses outside the EU (according to the provider); data processing agreements with service providers (according to the provider); hosting and ISO certification sought, not published
Last checked: 2 November 2026 · How we check
Is this your tool? Fill in missing detailsWhat it does
Defect class, certainty and severity (0-100)
Set severity limits per sorting class
Assesses the whole fruit in context
Learns from seasonal and regional defects
For apple, berry, cherry, citrus and kiwi
Also for stone fruit
Pre-trained, operator makes corrections
On Spectrim, InVision² and KAT0260
Comparable in the food industry
Delicious DataFree
OneThirdon request
FoodDocs$99-$299 per location/month (annually…
Nutriticson request
Qcifyon request
Robovision Indurionon requestTOMRA Food LUCAi compared
Underlying model
GDPR check for the food industry own image recognition model (according to the provider); deep learning model trained on its own fruit images from 20+ seasons, runs on the sorting machine (according to the provider); GDPR and standard contractual clauses outside the EU (according to the provider); data processing agreements with service providers (according to the provider); hosting and ISO certification sought, not published. Many tools build on a large model from, for example, OpenAI or Anthropic. If in doubt, ask for the data processing agreement: it states where your data goes.
Questions about TOMRA Food LUCAi
- Which AI model does TOMRA Food LUCAi use?
- The maker of TOMRA Food LUCAi does not publish which AI model is underneath. Own image recognition model (according to the provider); deep learning model trained on its own fruit images from 20+ seasons, runs on the sorting machine (according to the provider); GDPR and standard contractual clauses outside the EU (according to the provider); data processing agreements with service providers (according to the provider); hosting and ISO certification sought, not published.
- How much does TOMRA Food LUCAi cost?
- on request. Check the current price on the provider's website; rates change often.
- Who is TOMRA Food LUCAi for?
- TOMRA Food LUCAi is aimed at the food industry. It fits work such as optically inspecting and sorting products by defects, ripeness and internal quality, forecasting shelf life and demand to reduce food waste and shrinkage, and developing and reformulating recipes, including nutritional value, allergens and labelling.
- What should I watch out for with AI in the food industry?
- In this sector the data is mostly business data (recipes, suppliers, production figures) and rarely personal data, but recipes and specifications are trade secrets. Ask every provider whether your data is used to train models: Trace One excludes training of public models, while OneThird, according to its terms, receives a perpetual licence to anonymised, aggregated data. Pay attention to hosting location: OneThird and Delicious Data host in the EU, SGS FoodNexus is Swiss, and with Qcify the American parent is the controller. Hardly any provider states which AI model sits behind it (Trace One names Gemini). An AI inspection or HACCP proposal does not replace release by a competent employee: legal responsibility for food safety (Regulation (EC) No 178/2002) and labelling (Regulation (EU) No 1169/2011) remains with you. Cameras on the shop floor can also capture employees; arrange that with the works council and a DPIA.
Every Friday: what changed in AI for the food industry
New models, prices, oversight and tools, with sources and what it means for you. One email a week, unsubscribe with one click.