TOMRA artificial intelligence

Artificial Intelligence

Discover how TOMRA Food develops technologies from across the spectrum of artificial intelligence to enhance sorting precision, improve food safety, and maximize yield. Our intelligent systems learn, adapt, and make smarter decisions —  empowering food producers to deliver consistent quality with greater efficiency.  

Optical sorting machines engineered for artificial intelligence

The power of any artificial intelligence model comes from the data used to train it.

TOMRA's high-spec hardware combined with our global footprint across commodities and geographies means your business benefits from models trained on high quality data. 

We’re not only training our algorithms with the best possible data, but we’re generating clear data for your algorithms to read. And with stellar data comes new levels of performance for your operations.


A visual description of why our data, hardware, and expertise work together to produce good AI models

Types of artificial intelligence used in TOMRA food sorting and grading machines

Machine learning

What is machine learning?

Machine learning in post-harvest food sorting and grading is the use of AI algorithms to automatically analyze and classify fruits, vegetables, and other food products based on factors like size, color, ripeness, structure, defects, and contamination. 

How does it work?

Machine learning aims to learn patterns without being explicitly programmed. It’s a statistical modeling technique that uses algorithms to automatically learn from the data that’s generated by your crops running through machine.

Depending on your machine and your application, your algorithm will work one of three ways:

Unsupervised learning: Your machine learns a pattern to split characteristics into groups.

Reinforcement learning: Your machine learns through trial and error to maximize a reward.

Supervised learning: Your machine features the most sophisticated type of machine learning and uses labeled data to learn a pattern and assign to given labels​.


TOMRA 5A usability

Explore TOMRA Food's machine learning-powered bulk sorters and optical grading systems

  • TOMRA 3A sorting machine

    TOMRA 3A

    Capable of unrivaled foreign material removal, this highly efficient machine is powerful and robust, easy to use and maintain, reduces storage needs, is easily movable, and saves on labor.

    Applications: Field Potatoes, Fresh Pack Potatoes, Onions, Beets

    discover the TOMRA 3A
  • TOMRA 5A

    The TOMRA 5A is a premium bulk sorting and size grader. This heavy-duty, high capacity, high-performance sorter improves yields every minute it is running. 

    Applications: Fresh Pack Potatoes, Beets, Brussel Sprouts, Peppers, Gherkins, Radishes, Peaches

    discover the tomra 5A
  • TOMRA 5B Compact AI Background

    TOMRA 5B

    Coupling the latest sensor technology with advanced algorithms, the TOMRA 5B belt sorter enables you to reach the most challenging quality targets and yields.

    Applications: Berries, Cherries, Mangoes, Pineapple, Stonefruit, Dried Fruit, Almonds, Cashews, Hazelnuts, Peanuts, Raisins, Walnuts, French fries, Potato Crisps, Beans, Bell Peppers, Broccoli Carrots, Cauliflower, Corn, Garlic, Green Beans, Leafy Greens, Mushrooms, Onions, Peas, Gherkins, Radishes, Spinach

    discover the TOMRA 5B
  • TOMRA 5C

    TOMRA 5C

    Capable of unrivaled foreign material removal, this highly efficient machine is powerful and robust, easy to use and maintain, reduces storage needs, is easily movable, and saves on labor. 

    Applications: Berries, Dried Fruit, Almonds, Cashews, Hazelnuts, Macadamia Nuts, Peanuts, Pecans, Pistachios, Raisins, Walnuts, Leafy Greens; IQF fruit and vegetables

    discover the tomra 5C
LUCAi rgb

Deep learning

What is deep learning?
Deep learning models are deep, complex, global models that begin to correctly classify hard-to-read defects from the moment you switch them on
 in your packhouse.

Our primary deep learning product is LUCAi, and its superpower is looking at the whole piece of fruit to predict the most correct classification.

Where machine learning can accurately classify a product by assessing a few pixelsLUCAi™ considers the entire piece of fruit. It can not only assess the following but assign the correct grade based on your tolerance level:

Quality: We can classify produce based on quality references, such as Premium, Standard, or Reject.

Ripeness & maturity: We can determine ripeness stage by color, texture, or infrared analysis for Brix values.  LUCAi™  can see whether an organ is underripe, rip, or overripe.​

Defect & disease: LUCAi™ easily spots and assesses bruising and mechanical damage, pests, scarring, and mold and fungal infections.

Size & shape: LUCAi™ can identify roundness, size, and deformities to classify each piece of fruit.

Dive deeper into LUCAi™

Explore TOMRA's deep learning-powered optical grading machines

  • Invision2 line running

    InVision² with LUCAi™

    Meet demand and improve productivity with increased yields, optimized pack-out results, and minimal fruit loss. Adaptable to varying crop conditions to maintain consistent high performance with every batch.

    Applications: Cherries

    Discover InVision² with LUCAi™
  • Kato Hero

    KATO260 with LUCAi™

    The advanced industry-leading precision grading system powered by artificial intelligence.

    Applications: Blueberries

    discover KATO260 with LUCAi™
  • Spectrim cabinet with oranges on the line

    Spectrim with LUCAi™

    The Spectrim with LUCAi™ grading platform utilizes deep learning technology to boost profitability and minimize operational instability. Packing operations can meet demand and improve productivity with increased yields, optimized pack-out results, and minimal fruit loss.

    Applications: Apples, Avocados, Citrus, Kiwifruits, Stonefruits

    Discover Spectrim with LUCAi™
  • A render of the TOMRA Neon blueberry pre-grading machine

    TOMRA Neon

    The ultimate in pre-grading technology  for machine-harvested fresh blueberries. The TOMRA Neon removes over 95% of clusters and over 90% of green and red berries, ensuring maximized optical grader efficiency.

    Applications: Blueberries

    Discover the TOMRA Neon

Right product, right pack, season after season: AI at TOMRA

Setting the right grading tolerance takes discussion, time, effort, and labor – and the one thing that remains the same is that the next season will be different. 

TOMRA Food’s AI capabilities extend across our entire active product line. From deep learning to simple machine learning applications, our AI features and capabilities support your strategic decision-making and lift the burden from your operators. 

The result: right product, right pack, season after season – no matter where the year takes your business.

Where will we go next? 

TOMRA Food aims to extend its deep learning algorithms across the commodities we serve – and go further.

We’re constantly working towards offering more precision to our customers with improved usability, so operators can raise the bar on best performance.
 
One thing we can predict is constant change in the global food industry, and TOMRA will be here every step of the way to support our customers, existing and new, through this journey.



A visual timelime of TOMRA's key achievements in AI
A photo of a person operating the LUCAi user interface on a computer monitor featuring many images of oranges with a severity rating
Your details and enquiry