LUCAi™ for Citrus
Deep learning for precision citrus sorting and grading
Specifications
Standard Configuration
- Machine Type
- sort-grade
- Category
- Fruits and berries
- Applications
- Citrus
- Product ID
- fd-sort-grade-tomra-lucai-for-citrus
- Product Family
- Sorting and grading
Downloads
Download the brochure
Experience what LUCAi™ for Citrus can offer your business.
| Title | Size |
|---|---|
| LUCAi for Citrus brochure - English | 14.54 Mb |
"LUCAi™ now handles all our Juice from Pre-grader and made it super clean. We sometimes had to mix some Juice into pack more. It's a waste not to have LUCAi™ on our packing line."
Benefits
Superior defect detection
Correctly classify difficult to detect defects like rot, clipper cut, long stem, and sunburn.
How LUCAi™ achieves 99%+ detection accuracy for citrus defects
Traditional machine learning approaches to fruit grading work by analyzing small sections of the fruit, a few pixels at a time and making local predictions. It can't fully assess how those pixels relate to each other across the whole fruit.
LUCAi™ sees the whole fruit. It uses a deep learning classification model, designed to mimic the human brain's visual cortex, which is the part of the brain that processes what we "see" with our eyes. This allows LUCAi™ not just to recognize individual defects from the images produced by Spectrim but also make a decision based on the overall appearance and context of the entire piece of citrus fruit.
This advanced model allows LUCAi™ to correctly identify and categorize previously hard-to-detect citrus defects such as rot, sunburn, clipper cuts, pre-rot, long stems, doubles, and more than 20 other common defects.
When analyzing each fruit, LUCAi™ will assign:
- Defect Class/Category: Identifies the specific type of defect (e.g., rot, sunburn, clipper cut, etc.).
- Confidence Score: Indicates how certain LUCAi™ is that a defect has been correctly classified.
- Severity Rating: Provides a 0-100 measurement of how severe the defect is, based on its size, color contrast, and spread. This gives operators clear control over how tightly or loosely they wish to sort the fruit based on quality thresholds.
Associated technologies
Page list
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™LUCAi™
Our customers say they achieve unparalleled precision in grading because "LUCAi™ knows the difference" between even the hard-to-detect defects. But how does LUCAi™ know? Learn more about how this form of artificial intelligence works for apples, blueberries, cherries, and now, citrus fruits.
Learn more about deep learning
Dive even deeper into the Severity Score
LUCAi™ Severity Score: the little number that gives your operator full control of your sort
LUCAi™ Severity Score empowers packhouse operators with unprecedented control over fruit sorting. By combining deep learning with decades of expert-labelled data, LUCAi distinguishes not just the type of defect, but how severe it is — down to a fine-grain severity score from 0–100. This advanced scoring system helps operators make smarter decisions, maximize packout, and protect profit margins by ensuring the right fruit ends up in the right grade.
Read the ArticleTalk to a TOMRA Spectrim with LUCAi™ expert today
Operating expenses are on the rise, and every efficiency and cost-cutting advancement has a significant impact. Let the Spectrim with LUCAi™ enhance your operations. Connect with us by using the form below to discover how you can make Every Resource Count.™