Introduction
When we tell people our system uses AI to identify food waste, the first question is usually: "How accurate is it?" It's a fair question. But it's also the wrong starting point for understanding what AI food recognition actually does and why it matters.
The real question isn't "Is it perfect?" The real question is: "Does it give me data I can act on?" And the answer to that is unequivocally yes—even when the AI makes mistakes.
This guide explains how our AI food recognition works, why we've designed it the way we have, what its limitations are, and how you can get the most value from the data it produces. We're going to be completely transparent about what the technology can and can't do—because understanding the system helps you use it better.
Key Points
- Our AI recognises 2,400+ different food items
- We achieve approximately 80% accuracy across all deployments
- When the AI isn't confident, items go to "Mixed Waste"
- You can flag corrections and add custom foods to improve accuracy
How AI Food Recognition Works
Every time someone throws food waste into a monitored bin, a sequence of events happens in milliseconds. Understanding this process helps explain both the capabilities and limitations of the system.
The Recognition Process
Image Capture
The camera detects motion and captures an image the moment food enters the bin. The scale simultaneously records the weight change. This pairing of image + weight is fundamental to the system.
Neural Network Analysis
The image is processed by a convolutional neural network trained on millions of food images. The model compares what it sees against its database of 2,400+ food categories, looking for visual patterns it recognises.
Confidence Scoring
For each potential match, the model calculates a confidence score—essentially, how sure it is about the identification. This happens for every category in the database, resulting in a ranked list of possibilities.
Classification Decision
If the top match exceeds our confidence threshold, the item is classified as that food. If no match is confident enough, the item goes to "Mixed Waste." This threshold is calibrated to balance accuracy against data completeness.
The 2,400+ Food Database
Our recognition model is trained on a comprehensive database of over 2,400 food items commonly found in commercial kitchens. This includes:
- •Raw ingredients: Vegetables, fruits, proteins, grains, dairy
- •Prepared foods: Common dishes, sauces, sides, desserts
- •Bakery items: Breads, pastries, cakes
- •Beverages: Coffee grounds, tea, liquid waste
- •Trimmings: Peels, stems, bones, fat
This is a global model—the same AI serves all our deployments. It's trained on data from kitchens worldwide, which makes it robust across different cuisines and kitchen types.
The Mixed Waste Category
"Mixed Waste" is what the system assigns when it's not confident enough to classify an item. Some people see high Mixed Waste and think the AI is failing. Actually, it's doing exactly what it should: being honest about uncertainty.
The Alternative Would Be Worse
We could tune the system to always make a guess, even when it's uncertain. The result? More "confident" classifications that are actually wrong. We'd rather show you honest uncertainty than false precision.
What Triggers Mixed Waste
- •Low confidence scores: The AI's top guess doesn't meet the confidence threshold
- •Multiple items at once: Several different foods thrown together in one disposal
- •Unusual items: Foods not well-represented in the training data
- •Poor visibility: Bad lighting, obstructed camera, or blurry images
Using Mixed Waste as a Diagnostic
Your Mixed Waste percentage is actually useful information:
Low Mixed Waste (under 15%)
Great conditions. The AI is confidently classifying most items. Your data is highly granular.
Moderate Mixed Waste (15-30%)
Normal range for most kitchens. You're getting good category-level data with some uncertainty.
High Mixed Waste (over 30%)
Worth investigating. Could indicate lighting issues, camera positioning, lots of unusual menu items, or staff throwing multiple items at once. Contact support for optimisation.
Common Mislabeling Scenarios
No AI system is perfect. Understanding where the model commonly struggles helps you interpret your data correctly and flag items that need correction.
Visually Similar Foods
The AI sees what the camera sees—it can't taste or smell. Foods that look alike often get confused:
Prepared vs Raw
The same ingredient looks very different raw, cooked, or mixed into a dish:
- •Raw chicken breast vs grilled chicken vs chicken in a curry
- •Fresh vegetables vs roasted vs stir-fried
- •Individual ingredients vs combined in a plated dish
Environmental Factors
Lighting
Poor lighting changes how colours appear, making identification harder. Harsh shadows or very bright spots can also confuse the model.
Camera Cleanliness
Grease, steam residue, or debris on the camera lens degrades image quality. A quick wipe with a clean cloth can significantly improve accuracy.
Partial Visibility
If food lands in a corner of the bin or is partially obscured, the AI has less visual information to work with.
New or Uncommon Items
The model knows what it's been trained on. Novel menu items, regional specialties, or unusual ingredients may not be well-represented in the database. This is where custom foods become valuable (more on that later).
Flagging & Corrections
When you spot a mislabeled item in your dashboard, you can flag it. This isn't just correcting your own data—it helps improve the model for everyone using the system.
Your Corrections Matter
Every flag you submit becomes training data for the next model update. You're directly contributing to improved accuracy—not just for your site, but for all sites.
How to Flag an Item
Find the Item
In your dashboard, navigate to the waste log or detailed view where individual items are listed with their images.
Click the Flag Icon
Select the flag or "report" option on the item. This opens the correction interface.
Select the Correct Category
Choose the correct food item from the list, or search for it. If it's not in the database, you can add it as a custom food.
Submit
Your correction updates your data immediately and is logged for model training.
When to Flag
You don't need to flag every single error. Focus on:
- •High-volume items: Corrections on frequently wasted foods have the biggest impact
- •High-value items: Expensive proteins or specialty items worth tracking accurately
- •Recurring errors: If the same item keeps getting misclassified, flag it
Adding Custom Foods
Our database covers 2,400+ common foods, but every kitchen has its specialties. Custom foods let you extend the system with items specific to your menu.
When to Add a Custom Food
- •A signature dish specific to your restaurant
- •Regional or ethnic specialties not in the global database
- •Items that keep getting misclassified as something else
- •Specific preparations you want to track separately (e.g., "Caesar Salad" vs generic "Salad")
Best Practices for Custom Foods
Use Clear, Specific Names
"House Marinara Sauce" is better than "Sauce." "Pulled Pork Sandwich" is better than "Sandwich." Specific names make your reports more useful.
Choose the Right Category
Assign custom foods to appropriate parent categories. This ensures they're grouped correctly in reports and waste analysis.
Don't Over-Customise
Adding too many hyper-specific items can make reporting harder to interpret. Find the balance between granularity and usability.
How Custom Foods Work
Custom foods you add become available for manual classification and flagging at your site. They're stored alongside the global database. When you flag items as your custom food, it helps train the model to recognise similar items in the future.
Why 80% Accuracy Is Actually Good
When people hear "80% accurate," some wonder if that's good enough. Let's put it in context.
The Alternative: Manual Logging
Before AI-powered systems, food waste tracking meant manual logging. Staff were supposed to weigh and record every item thrown away. In practice:
The choice isn't between 80% AI accuracy and 100% manual accuracy. It's between 80% AI accuracy and effectively 0% usable data.
Trends Matter More Than Items
Individual item accuracy matters less than you might think. What matters is:
- Consistent measurement over time. Even with some errors, week-over-week trends are reliable.
- Category-level accuracy. Even if "chicken" is sometimes "turkey," you know your protein waste total.
- Total waste volume. The scale never lies—you always know exactly how much went in the bin.
Statistical Significance
At 80% accuracy across thousands of data points, the errors tend to average out. If the AI occasionally calls rice "couscous," it also occasionally calls couscous "rice." Over time, your category totals converge on reality.
The Real Benchmark
Don't compare AI accuracy to theoretical perfection. Compare it to the alternative: no automated data at all. 80% accurate data that exists beats 100% accurate data that doesn't.
Best Practices for Better Accuracy
While AI does the heavy lifting, there are things you can do to maximise accuracy.
Optimise Lighting
The AI needs good light to see clearly. Ensure the bin area is well-lit without harsh shadows or glare. Consistent lighting throughout the day helps too.
Keep the Camera Clean
Kitchen environments produce steam and grease. Wipe the camera lens periodically with a soft, clean cloth. A quick wipe during daily cleaning makes a difference.
One Item at a Time (When Possible)
The AI identifies best when it sees one type of food at a time. Dumping mixed plate scrapings in one go makes identification harder. This isn't always practical, but when it is, it helps.
Add Custom Foods for Your Menu
If you have signature items or regional specialties, add them as custom foods. This gives you more accurate tracking for items that matter to your operation.
Flag Recurring Errors
If you notice the same item repeatedly getting misclassified, flag it. This helps retrain the model and improves future accuracy.
Reading Reports with AI in Mind
Understanding how the AI works helps you interpret your waste reports correctly.
Trust Aggregates Over Individual Items
Your weekly summary of "Protein: 45kg" is more reliable than any individual "2.3kg chicken" entry. The more data points in a total, the more accurate it becomes as errors average out.
Focus on Trends
The most valuable insights come from week-over-week or month-over-month comparisons:
- •Is total waste going up or down?
- •Are certain categories consistently high?
- •Did an intervention (menu change, portion adjustment) have an effect?
- •Are there patterns by day of week or time of day?
Use Mixed Waste as a Signal
If your Mixed Waste percentage suddenly increases:
- •Check the camera lens—may need cleaning
- •Check lighting—bulb may have changed or failed
- •Check for new menu items that might need to be added as custom foods
Don't Over-Interpret Outliers
If you see a single unusual entry—like 5kg of "chocolate cake" in a kitchen that doesn't serve dessert—check the image before drawing conclusions. It might be a mislabel worth flagging, or it might be a one-off event.
Summary: How to Read AI-Generated Reports
- Category totals are more reliable than individual items
- Trends over time are more reliable than single data points
- Weight is always accurate—even when identification isn't
- High Mixed Waste is a diagnostic signal, not a failure
Sources & References
arXiv - Cornell University
McKinsey & Company
Trends in Food Science & Technology
Stanford HAI