New software solution to ensure textile quality. The textile manufacturing process has several sources of defects, but more than 80% of those originate from the knitting stage. Detecting these defects early in the production chain is difficult. The EU-funded Smartex project has developed a solution to help reduce defective production levels from 5% to near zero. Its online software as a service (SaaS) is based on computer vision, machine learning, and artificial intelligence and aims to become the main solution for the automation of inspection processes in the textile industry. This technology has already performed successfully in real short-term environmental tests.
Smartex is a company committed to reducing the textile industry's defective production (from 5%) to 0%. Our dedicated and highly skilled team has made this possible by developing unique devices, which combine hardware and software built in-house to achieve such a goal. Smartex is able to detect defects during the production stage, offering an online software as a service (SaaS) based on computer vision, machine learning, and artificial intelligence with the clear mission of becoming the main solution for automation of the inspection processes in the knitting textile industry. At the beginning of the project, Smartex devices were in a prototype stage (TRL 6). Since then, real short-time environment tests have been successfully performed. The market fit was also validated by multiple letters of intent, and prices agreed with potential clients, including Decathlon Group, PVH (Calvin Klein, Tommy Hilfiger, etc.), and Kering (Gucci, YSL), in different countries.
Smartex’s disruptive hardware and software technology has been recognized with several grants and awards and has recently participated in the biggest hardware startup acceleration program, HAX (Shenzhen, China), backed by Smartex’s first investor SOSV (Sean O’Sullivan Ventures).
Call for proposal H2020-EIC-SMEInst-2018-2020 | Sub call - H2020-EIC-SMEInst-2018-2020-3
Start Date: 1 February 2020 | End Date: 30 September 2021
Total Investment: 1,464,375.00 € | EU Contribution: 1,025,062.50 €
This project has received funding from the European Union’s Horizon 2020 Research & Innovation Program under grant agreement No 946915.