Machine vision grading uses colour, near-infrared and hyperspectral cameras to inspect food and agricultural products at high speed, removing stalks, stones, foreign matter and defective pieces with air jets, and grading the rest by colour and size. It brings consistent quality to products that vary by nature.
Food and agricultural grading separates product by quality: removing what should not be there, and sorting the rest into grades by colour, size and appearance. By hand it is slow and inconsistent, and pickers cannot keep up with modern processing lines.
Optical sorters image a fast-moving stream of product and fire short bursts of compressed air to eject each rejected piece. For inspection of whole items such as fruit, cameras grade each piece on a conveyor and direct it to the right lane.
A vibratory feeder or belt spreads the product into a thin, even stream so every piece can be seen.
Colour, NIR or hyperspectral cameras image every piece in flight or on the belt, often from both sides.
Software compares colour, shape, size and spectral signature with the accept recipe for this product and grade.
Fast air-jet valves blow rejected pieces out of the stream; whole items are diverted into grade lanes.
Throughput, reject rates and grade yields are logged for each batch.
Colour cameras remove discoloured, burnt, mouldy or immature pieces and grade by colour, as used widely for tea, rice, spices and nuts.
Near-infrared and hyperspectral cameras see chemical differences, so they can detect plastic, wood, stones or shell that look the same colour as the product.
Measures length, width and shape of each piece to remove broken pieces or to grade by size.
Stainless steel, washdown-rated enclosures (for example IP65 or IP69K) and easy-clean surfaces suit food processing environments.
Two example project scopes showing how the station, the checks and the outputs are defined. Every plant is different, so the final configuration is confirmed after a feasibility study on your own parts.
The situation: A tea factory removes stalk and fibre by hand after rolling and grading, and struggles to staff the line.
The situation: A spice exporter needs stronger foreign body control to meet a new buyer’s audit.
Industrial cameras, lenses, line-scan cameras and code readers are available through our machine vision catalog, quoted with delivery to Sri Lanka. We select the hardware for your application during the feasibility study.
Browse the hardware catalogEvery product, surface and line behaves differently under a camera, so every project starts with evidence from your own material.
A site visit to understand your product, line speed, quality criteria and where the check should sit.
We image your good and defective samples and show what the system can reliably detect. This is the go or no-go.
One station on one line, running beside your inspectors until results match and your team trusts them.
More lines, integration with your PLC and systems, and local support from our Sri Lankan engineering team.
Vision inspection for labels, caps, fill levels, seals and cartons. Check the right label is present, straight and legible, caps are fitted, containers are filled and packs are sealed, on every unit at line speed.
Give robots eyes: 2D and 3D vision locates parts on conveyors, in trays and in bins so robots can pick, place, pack, palletise and tend machines without precise fixtures. Hand-eye calibration and conveyor tracking included.
Sort fabric rolls, cut panels and washed garments into buyer shade bands with CIELAB measurement and 555 codes.
Every machine vision application we design and build, in one place.
Yes. Colour sorters are widely used in tea processing to remove stalk, fibre and discoloured particles, and to make grades more consistent. The sorter is set up for each grade and tea type.
With near-infrared or hyperspectral imaging. These cameras see differences in chemical composition that are invisible in colour images, so plastic, wood and stones can be separated from the product.
An optical sorter inspects a stream of small pieces and ejects rejects with air jets. A grader inspects larger individual items, such as fruit, on a conveyor and sends each one to a lane for its grade. Both use cameras and the same software ideas.
Food-grade sorters are built from stainless steel with washdown-rated enclosures and easy-clean surfaces. The right rating depends on how the area is cleaned.
Yes. Cameras on a conveyor measure the colour, size and surface defects of each fruit or vegetable and direct it to the lane for its grade.
Tell us what you need to check and share some good and faulty samples. We will show you what a camera can reliably see before you commit to anything.
Photographs show representative plants and equipment, not Cerox installations or client sites. Diagrams by Cerox Engineering. Photo credits, via Wikimedia Commons: Tea factory, Nuwara Eliya by Yercaud-elango, CC BY-SA 4.0; Tea processing conveyors by Bdx, CC BY-SA 4.0; Optical sorting machine by MB-one, CC BY-SA 4.0.