Clean flax fiber, sorted at line speed
SORTIX builds in-line machinery that sees contaminants in moving flax fiber and removes them automatically, in real time, at full line speed, delivering first-grade fiber up to 98% pure.
Four capabilities, one clean stream
Everything happens in-line, on the moving belt, without changing the rest of your production line.
- 01
AI + UV optical sorting
An industrial camera and a neural network recognise more than 15 contaminant types; the AI + UV model adds ultraviolet inspection for clear film, white synthetic string and bleached fabric.
- 02
Built for flax fiber
Background removal designed for irregular natural fiber, and automatic real-time removal that never grips or cuts the fiber.
- 03
Edge processing
Inference runs on an edge AI computer inside the machine in 5 to 7 ms per image; no cloud or internet needed.
- 04
Automatic training on the factory floor
The machine keeps learning from your own production. New fiber and new contaminants are added to its training on site, so accuracy improves the longer it runs.
From raw fiber to clean fiber, in one pass
Five stages, all of them happening while the belt keeps moving.
Raw flax
Fiber enters on the conveyor exactly as it leaves the preceding stage; no change to your line is required upstream.
Imaging
An industrial camera captures the moving fiber under controlled lighting, frame by frame.
Analysis
Background removal isolates the fiber, then the neural network classifies what it sees.
Identification
The contaminant is located on the belt and its position is tracked from the conveyor speed.
Removal
The system removes it from the stream automatically, in real time, and clean fiber continues to the next stage.
With you for the life of the machine
From testing and feasibility to installation, maintenance and training.
What the system achieves
- Fiber purity
- up to98%
- Classification accuracy
- 96.4%
- Processing capacity
- up to3t/h
- Inference latency
- 7ms
first-grade flax fiber
tonnes per hour
milliseconds per image
Sort everything