# Vision quality control for fruit and vegetables

TOS Robotics builds vision quality control that checks every product on the line with cameras and an AI model. One image is analysed in 0.02 seconds. The model judges colour, shape, damage and decay, so the check no longer needs a person at the belt. It is ready for deployment, in our flowpacking cell or built into a machine on your line.

Source: https://tosrobotics.com/products/quality-control/
Last updated: 2026-11-20

- Status: Ready for deployment
- Per image: 0.02 seconds
- Checks: Every product, not a sample
- Cameras: Four, all sides
- How you buy it: In our cell or built into your line

Nobody keeps the same standard for eight hours. **A camera with an AI model judges the last product of the shift like the first.**

## One pepper, four cameras

Real frames from the quality cameras of TOS Robotics. Pick another pepper to see its four views.

## What the model adds to the picture

On the left what the camera sees. On the right what the AI model makes of it. It outlines each bell pepper and marks the spot that makes one of them not fresh.

## Performance

- To analyse one image with one or more products: 0.02 s

## Where it is used

- [Bell pepper flowpacking with a singulator and AI robots](https://tosrobotics.com/cases/bell-pepper-flowpacking-singulator/): Robots fill the flowpacker, where people used to stand.
- [Mango packing in trays and crates with robots](https://tosrobotics.com/cases/mango-flowpacking/): Ready for deployment. Mangos into carton trays of 2, or into small and normal crates.
- [Avocado packing in trays and crates with robots](https://tosrobotics.com/cases/avocado-flowpacking/): Ready for deployment. Avocados into carton trays of 2 or 4, or into crates.
- [Assembling meal packages with robots](https://tosrobotics.com/cases/meal-packages/): Ready for deployment. A modular cell that fills meal boxes per recipe, without hands at the line.

## Keep reading

- [How vision quality control on fruit and vegetables works](https://tosrobotics.com/knowledge/how-vision-quality-control-on-fruit-works/): Cameras and an AI model judge colour, shape and visible defects, in the TOS Robotics system in 0.02 seconds per image.
- [Flowpacking cell: robots that fill the flowpacker](https://tosrobotics.com/products/flowpacking-cell/): A complete cell that fills the flowpacker. €150,000 per cell. In production.

## Questions and answers

### What can vision quality control detect on fruit and vegetables?

The system of TOS Robotics detects differences in colour, shape and size and visible defects such as damage and decay. Which defects count, and how strict the limit is, is set from examples that quality experts have judged.

### How fast is it?

One image is analysed in 0.02 seconds. That is fast enough to check every single product at line speed and not only a sample.

### What happens with a rejected product?

It is not packed. On the bell pepper line the check sits at the singulator, so a rejected pepper leaves through a separate chute before it reaches the robot.

### Is it a separate machine?

No. On the bell pepper line the four cameras are built into the singulator, in front of the robots. That saves floor space and a separate sorting step. The AI model is being trained on the peppers of that line and does not sort in production yet.

### How do I buy quality control?

It comes with the [flowpacking cell](https://tosrobotics.com/products/flowpacking-cell/) with the TOS Robot, where a camera checks every product before the pick. It can also be built into a machine on your line, as at the singulator of the bell pepper line. Ask us for an offer.

### Can it check the side that lies on the belt?

A camera only sees what faces it. That is why four cameras photograph each pepper from different sides while it falls, so no side stays hidden.
