Frequently Asked Questions about Automatic Defect Removal and AI Vision Technology

Yes. Defect removal keeps improving over time. With deep learning, PIP improves the model based on what it sees in real production and rolls out controlled, tested updates. Every producer benefits from those improvements.

Among automatic defect removal systems, the main difference is the technology. PIP is the only supplier using deep learning, which lets S-Blade keep improving over time. Conventional defect removal systems rely on fixed rules and do not adapt in the same way.

S-Blade is not a replacement for optical sorting. It is a different technology, based on defect removal instead of removing the fries that have defects. The two work together: optical sorting and S-Blade combine to lift overall yield.

S-Blade uses deep learning and self-learning vision algorithms, trained on real production data.

Cost of ownership is low, estimated at no more than €45K per year, with predictable maintenance.

S-Blade removes only the defective part of each fry, instead of rejecting the whole piece. The result is higher usable output per ton of incoming potato.

S-Blade removes surface blemishes, scab marks and other skin defects. Thanks to deep learning, it tells the difference between healthy skin and a defect, so it removes the defect while keeping the healthy skin intact. This makes it possible to upgrade skin-on fries without cutting away good skin.

S-Blade detects black spots by colour and shape using deep learning. The affected section is cut out while the rest of the fry continues down the line.

Optical sorting rejects the whole fry when a defect is detected. Defect removal cuts out only the defect and keeps the good product. The result is higher yield from the same input.

Automatic defect removal is the process of detecting and removing defects from french fries directly on the production line, without manual sorting. S-Blade uses deep learning to identify each defect and cut it out, while keeping the rest of the fry intact.