Tile grading sorts every tile by shade, size and surface quality before it is boxed. Machine vision measures colour in CIELAB to group tiles into shades, measures calibre and squareness, and finds cracks, chips, pinholes and glaze faults, so each box holds matching first-grade tiles.
Tile grading is the end-of-line process that decides which shade, calibre and quality grade each tile belongs to. Tiles from one production run vary slightly in colour and size, and customers expect every tile in a box, and every box in an order, to match.
Machine vision does this objectively. A colour camera under fixed, calibrated lighting measures each tile in CIELAB and groups tiles whose colour difference falls within a set ΔE tolerance into the same shade. Dimensional measurement assigns the calibre. Surface inspection finds defects and grades the tile.
The method follows the same principles as our shade segregation work for textiles: controlled light, colour measured as numbers instead of by eye, and shade bands set to the tolerance your customers accept. Surface quality and dimensional checks are defined for ceramic tiles in ISO 10545-2.
Tiles pass on the grading line after the kiln, one at a time and flat, at production speed.
A colour camera under controlled light measures shade in CIELAB; dimensional measurement checks calibre, squareness and edges.
Lighting at several angles reveals cracks, chips, pinholes, glaze and decoration faults, and deep learning handles patterned surfaces.
Each tile is assigned a shade group, a calibre and a quality grade against your limits.
The line diverts tiles to the right stacker or box, and each batch record keeps the shade and grade distribution.
Colour is measured as L*, a* and b* under fixed illumination, so shade groups are defined by numbers rather than opinion. Differences are expressed as ΔE, using CIE76, CMC or CIEDE2000 as agreed.
Tiles are grouped into shades by their colour difference from shade references, with tolerances tuned to what is visible on the laid floor or wall.
Calibrated cameras measure length, width, squareness and edge straightness to assign the calibre and reject out-of-tolerance tiles.
Low-angle and diffuse lighting together reveal cracks, chips, pinholes, glaze drips and crawling on glossy and matt glazes.
Printed and patterned tiles vary by design, so a model trained on good tiles separates real defects from the pattern.
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 tile manufacturer grades wall tiles by eye after the kiln and receives complaints about mixed shades within one order.
The situation: A porcelain tile plant needs to catch fine cracks and pinholes on polished surfaces that reflect light strongly.
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 glossy and injection moulded parts: scratches, sink marks, short shots, flash and gloss faults, found with deflectometry and dome lighting.
Automated surface inspection for scratches, dents, cracks, porosity, stains and coating faults on metal, plastic, rubber and glass. Specialised lighting and deep learning find cosmetic and functional defects on every part.
Non-contact measurement of lengths, diameters, hole positions, gaps and profiles with telecentric optics and 3D laser profiling. Measure every part in-line, pass or fail it against tolerance, and log data for SPC.
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.
It measures the colour of each tile in CIELAB under fixed, calibrated light and groups tiles whose colour difference is within a set ΔE tolerance. Because it measures rather than judges, the same tile always lands in the same shade group.
Yes. For shade, colour is measured over the whole surface or chosen regions. For defects, deep learning trained on good tiles of each design separates real faults from the pattern.
ISO 10545-2 describes how ceramic tile dimensions and surface quality are determined, and ISO 13006 covers classification. Many manufacturers also use their own customer-specific shade and grade rules, which the system can follow.
Yes, but the lighting has to be designed for reflective surfaces. Dome lighting gives an even view for colour and spots, while low-angle light makes cracks and pinholes visible. See our page on glossy part inspection for the principles.
The principles are the same: controlled light, CIELAB measurement and shade bands set by tolerance. We apply the method we use for fabric and garment shade segregation, adapted to tiles and kiln variation.
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: Ceramic tiles by Houss 2020, CC0.