Stacked wooden boards with one board outlined in purple and labeled Defect Detected: Frayed Edges

Use cases

How do sawmills detect surface defects on boards at line speed?

A camera over the board line checks every board as it passes, and Video-to-Action AI flags frayed and torn edges, cracks, chips and other surface flaws in real time. Each board is graded against your rules, so only on-spec stock moves to the next station, and every defect is saved as an image.

Wood

Quality Assurance

What it catches

On a board or panel line, Video-to-Action AI checks each piece for:

Frayed or torn edges
Cracks and chips
Spots and discoloration
Dents and scratches
Defects down to about 0.8 mm, with the right camera

Why manual grading struggles

Boards move fast, every piece looks slightly different, and graders make hundreds of decisions an hour. Grading drifts between people and over a shift, so good stock gets downgraded and defective boards slip through to the customer. Rule-based vision systems help, but struggle with natural variation in wood.

How it acts

VITA, Maneva's quality and downtime agent, decides on every board in real time and grades it against your rules. The result can drive a manual pull, a reject system or a robot, and each defect is saved as an image, so grading can be audited and tuned.

Because the model is trained on images of your own boards, it handles the natural variation in wood that fixed rules miss.

Where it sits on the line

The camera, often a line scan or 3D camera, sits above the board line after sawing or planing, ahead of sorting. Some lines can start with cameras they already have; many need at least one off-the-shelf camera placed for the task. Maneva helps choose the camera and where it goes.

Result

Every board is checked and graded the same way. Maneva customers have seen up to 16x longer mean time between stoppages; on one board line, stops went from every 1.5 minutes to every 25 minutes on good material.

See it on a line like yours →

More for wood and panel plants: AI for wood processing →

Frequently Asked Questions

Didn't find what you need? Our team will walk you through Video-to-Action AI and show how it fits your production environment.

Can it grade boards as well as find defects?

Yes. Each board is graded against your rules as it passes, so only on-spec stock moves to the next station.

Which wood defects can it detect?

Visible surface defects such as frayed or torn edges, cracks, chips, spots and discoloration, down to about 0.8 mm with the right camera. Defects inside the wood need other imaging, such as X-ray.

Do we need new cameras?

It depends on your site and the problem you want to solve. Some customers can start with the cameras they already have. Many need at least one new off-the-shelf camera placed and set up for the task, so the AI sees exactly what it needs to see.

Maneva helps you scope this from the start. We look at your line, the result you want, and what the camera needs to capture, then recommend the right camera and where to put it.

Maneva is hardware agnostic and connects to a wide range of camera types, including:

Standard RGB and security cameras for many quality, downtime, safety and efficiency use cases
3D and depth cameras for measuring volume, position and dimensions
Thermal and infrared cameras for heat signatures and low-light areas
Short-wavelength infrared (SWIR) cameras, which see through plastic to check seal integrity
High-resolution precision cameras for defects under a millimeter across large surfaces

If you can see it in the video, our AI can understand it and act on it. Start with one line, and we'll help you choose the setup that gets you there.