From the Sector

Over the past three years, a dedicated AI development team at BTMA member Shelton Vision has been developing tailored machine learning solutions for the textiles industry.

The aim has been to elevate the detection process and the accuracy of naming and grading subtle defects in textiles, in real time within production environments.

“Big Data ‘off-the-shelf’ systems such as those behind technolgies like facial recognition and Google Maps involve reading many thousands of single images each second and simply take too long to accumulate sufficient data for what’s required in this specific case,” says Shelton Vision CEO and Managing Director Mark Shelton. “A feature of the textile industry is that in many sectors, the product range changes several times within a year and it is not uncommon to have to inspect hundreds, if not thousands of different styles in a year based on precise settings.”

In terms of defect types, he adds, there may typically be over 100 that need to be accurately detected, classified (named) and graded in real time.

“Added to this is the need to ‘filter out’ the random occurrence of ‘non defects’, such as loose threads, lint and dust on the surface – the number of which can be higher than actual defects – and it is clear that a bespoke system is required.”
The development team has consequently established metadata for identifying defect properties, enabling the successful identification of faults from a much smaller number of images.

“The system employs a unique combination of machine learning for automated style training and novel algorithms for defect detection, to provide high quality images for the AI real time defect classification and grading software,” Shelton explains. “Due to the inherent variation in fabric features – raw materials, construction, texture, colour and finishes, as well as the differing product quality standards in value chains and the regional variations in what defects are called – our AI engine uses models built for each individual company or group of companies, or product value chain.”

The AI models are constructed so that the user operatives can populate them with their own data produced by the vision system or by obtaining defect images from another imaging source (eg a mobile phone camera).  

The occurrence of defects is sporadic and many defect types occur infrequently, although when they do, they can have severe consequences. These scenarios re-enforce the need for the AI engine to be quickly set up and able to operate accurately with limited data sets of typically between 30 and 50 good quality images per defect type.

A further feature is a tool enabling the user to periodically ‘clean up’ the AI data during the set up phase. This is used to resolve conflicting data and to correct mis-named images.

Generally, the highest cost component of fabric production is the raw material and in addition to finished product inspection, a cost effective use for vision systems is in process operation.

Generally, the highest cost component of fabric production is the raw material and in addition to finished product inspection, a cost effective use for vision systems is in process operation.

“There is a need for the real time detection of defects that are being created in separate processes, such as printing or coating and for real time automated systems that can accurately determine the defects and their severity and provide a reliable signal for an operative to rectify the issue, This can result in considerable savings.

Prior to Shelton introducing powerful customised machine vision and real time defect classification, the only systems available were those that required manual sifting through vast numbers of images, which included both real defects and ‘non defect’ images. The task was very often overwhelming and did not provide much benefit beyond manual fabric inspection.

A new fabric inspection technique for accurately detecting the most subtle of defects on patterned fabrics during high speed production has been developed by BTMA member Shelton Vision, of Leicester, UK.

The patent-pending system has been integrated into the company’s WebSpector platform and validated through factory trials on a purpose-built full scale in-house demonstration system with sophisticated fabric transport capabilities. As a result, a first system has already been ordered by a manufacturer of both plain and patterned fabrics, including camouflage, in Colombia. This follows the successful conclusion of a 21-month Innovate UK project in which techniques for the resolution of complex pattern deformations were developed by machine vision and computer scientists in the company, backed up by the machine vision and robotics department at Loughborough University.

Restrictions
Traditional methods for defect detection rely on human inspection which is ineffective, with detection rates under 65%, while the Shelton WebSpector machine vision system offers a sophisticated platform for automated defect detection of over 97%, but until now has been restricted to plain textiles.

While pattern matching and neural network approaches have previously been tried for patterned textiles, they have failed to provide a practical solution due to the extreme complexity associated with pattern matching on deformable substrates like textiles, as well as the time required to train a neural network for each pattern type.

Challenges
The challenge is that fabrics are not rigid and can be creased or stretched and are also subject to local distortion,” says Shelton Vision Managing Director and CEO Mark Shelton. “As a result, inspection without the technique we have developed, would lead to thousands of false positives. Our sophisticated pattern inspection software techniques ensure a clean image, allowing the detection of faults on fabrics running at speeds of up to a hundred metres a minute.”

The full system consists of:

• A camera and lighting system for optimum image capture at high speed and associated image processing hardware.
• Self-training software utilising statistical analysis to automate the system configuration for new textile products.
• An advanced suite of defect detection algorithms for the detection of all textile defect types.
• An AI-driven defect classification system which learns and automates defect naming in real time, as well as a real time defect grading capability based on client decision rules.
• A system for recording and retrieving complete roll map images for subsequent review and quality control.

The generation of textile roll maps with complete defect data allows for an optimised textile cut plan, improved downstream processing and quality assurance.

Baldwin Technology Company Inc. will showcase its latest high-performance color management, surface treatment, LED-UV curing, inspection, defect detection and Industry 4.0-based analytics solutions at Print4All, which is taking place May 3 to 6 at Fiera Milano in Italy.

One of its latest advances — which will be on display at Print4All — is the XP Quatro Series™ LED-UV curing module with one head and two frequencies for broader applications. It is designed to economically and efficiently cure LED-formulated printing inks and coatings on sheetfed and web offset printing presses, as well as on larger-format flexo presses and digital print engines. The XP Quatro Series LED-UV enhances print quality, while operating at top speeds, driving increased productivity and profitability.

Italy’s ACM Flexible Packaging selected Baldwin as its LED-UV partner and became one of the first flexible film converters to offer all LED-UV curing in a narrow to mid-web format. This partnership established LED-UV printing as a growing production standard in flexible packaging and labels. Today, ACM is a 100% LED-UV, non-mercury facility.

Baldwin’s Print4All booth also will showcase Industry 4.0 and industrial Internet of Things-enabled technologies that work together to achieve greater uptime, productivity and automation. Featured solutions pair sensor-gathered data with operational data from Baldwin equipment to gain live, actionable insights to improve production monitoring, so printers and converters can achieve new levels of color consistency with fewer defects and greater assurance of curing.

Other highlights in Baldwin’s booth include the Corona Slim treatment system, which ensures the exact dyne levels needed for perfect uniformity in application, and the Guardian PQV 100% Print Inspection, which provides complete print quality verification from prepress through production, reporting and archiving.

Electronics For Imaging, Inc. has received two European Digital Press (EDP) Awards from the European graphics arts trade press, a prestigious technical awards programme that recognises innovative advancements in digital print production. The EFI™ VUTEk® Q5r roll-to-roll UV LED printer beat competition in the large/wide- format printing systems category for printers above 350-centimetres wide. EDP judges honoured EFI Fiery® software integration with finishers as the top solution in the awards programme’s category for software automation tools.

Automation, quality and value with award-winning roll-to-roll technology
The EFI VUTEk Q5r printer is a roll-to-roll display graphics printer, capable of running at speeds of up to 672 square metres per hour. The 5.2-metre-wide printer delivers a full system solution from file submission to a finished print with options such as in-line quality inspection, in-line slitting and cutting, roll and tape collection, auto-calibration, automated backlit printing, automated blockout printing and much more.
 
EFI VUTEk Q series printers, which include both the Q5r and a 3.5-metre wide VUTEk Q3r model, are available with up to nine colours including white and clear, and feature EFI UltraDrop™ Technology with native 7-picolitre printheads and multi-drop addressability for high-definition quality. Benefits include smoothness in shadows, gradients, and transitions, as well as precise and sharp 3-point size text with a true resolution of up to 1,200 dots per inch.

Fast, flawless finishing
EFI Fiery software integration with finishers, the winner in the EDP Awards category for best software automation tool, offers advanced integration with in-line or offline slitter/cutter/creasers. Operators can define cut, crease, and perforation locations on the job content in the Fiery software solution, which then communicates the configuration to finishing equipment, eliminating operator touchpoints and errors from incompatible layouts.

EFI Fiery software integration with finishers is offered in two different EFI Fiery software products: Fiery Impose and Fiery Finishing Designer.

A broad coalition of industry and labor groups has sent a letter to House and Senate leadership urging support for the Import Security and Fairness Act (included in the broader House America COMPETES Act), which aims to stop China from exploiting the de minimis threshold that allows imports valued under $800 to come into the United States without paying duties and taxes, bypassing U.S. Customs inspections and providing a backdoor to Chinese goods produced with forced labor.

The coalition sent the letter to Senate Majority Leader Charles Schumer (D-NY), Senate Minority Leader Mitch McConnell (R-KY), Speaker of the House Nancy Pelosi (D-CA) and House Minority Leader Kevin McCarthy (R-CA), urging the leaders to strongly support and prioritize the provision in the underlying China bill.

The letter was signed by the following organizations:

• AFL-CIO
• Alliance for American Manufacturing
• Coalition for a Prosperous America
• International Brotherhood of Teamsters
• Narrow Fabrics Institute
• National Council of Textile Organizations
• Service Employees International Union
• U.S. Footwear Manufacturers Association
• U.S. Industrial Fabrics Institute
• United Steelworkers
• Workers United/SEIU

See the full letter here.

Paper Converting Machine Company (PCMC), part of Barry-Wehmiller, is pleased to announce the opening of a new Packaging Innovation Center, located at its headquarters in Green Bay. The multi-purpose space is more than 4,700 square feet and will serve as a hub for demonstrations, training, education, industry trials, and research and development.

The Packaging Innovation Center will be the home of a Fusion C flexographic press, Hudson-Sharp’s Ares 400-SUP stand-up pouch machine, a Meridian Elite laser anilox cleaner, an ELS-MAX inline press and the ION digital printing platform. These machines will be available for demonstrations, as well as for hands-on learning and training opportunities. The state-of-the-art center also features industry-leading tools and supplies for anilox sleeves, plate-mounting, color-proofing, plate and print inspection, sleeve-cleaning, and plate sleeves and tapes.

“We’re excited to be able to welcome printing and converting customers into our facility to experience our innovations firsthand,” said Rodney Pennings, PCMC’s Director of Sales–Printing, Coating and Laminating. “Our new Packaging Innovation Center is a vision that we’ve had for several years, and it’s rewarding to see it finally be completed.”