Posted in | News

Automatically Detecting Surface Defects in Ceramic Tiles

Surface defects in ceramic tiles, invisible to the naked eye, could be automatically detected by a new system being developed at the University of the West of England. The system would detect imperfections such as pinholes, crazing, rough or dull glazes, even on tiles with a texture or relief pattern, saving the industry time and money and reducing wastage.

A demonstration model is being developed at UWE's Machine Vision Laboratories, in collaboration with the University of Bath and Fima Surface Inspection Ltd. It is based on photometric stereo technology, an area where UWE is internationally recognised for its expertise.

The research is being supported by the SWRDA's Great Western Research fund, with matching funding from the academic and industry partners.

Professor Melvyn Smith, director of the Machine Vision Lab, said, “This three-year project will lead to significant advances in automating inspection of ceramic tiles. It could also have applications in other industries, where the quality of the surface is paramount, such as metals or shiny plastic components. It builds on our existing expertise in photometric stereo, and will be able to capture surface topography detail at extremely high resolution, at pixel level.”

Arwyn Roberts, chief technical officer from Fima SI Ltd said, “No commercial device exists so far for online detection and analysis of defects in material that is rapidly moving along a production line. This project with UWE and the University of Bath will allow us to become more competitive, as well as reducing the amount of waste materials.”

The new technology could also open up new markets in North America, the EU, China and India, and improve the export revenues of the South West region.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.