Abstract: Complex deformable webs like lace fabrics are amongst the most complicated materials to be inspected without any human intervention. The ability of such webs to deform easily, along with their complex patterns, presents a challenging problem for any machine vision system.

Their pattern complexity makes it very difficult to use any global image processing or rule based techniques for inspection, leaving direct comparison with a perfect prototype as the only choice available. Due to the elastic nature of the lace fabric, small distortions are characteristic of the product and are unavoidable. This renders sensitive direct comparison methods, such as those employed for the automatic inspection of printed circuit boards, prone to unacceptable false alarms. In the present work, the authors have exploited a mechatronic methodology, coupled with image processing techniques, to develop a high-speed inspection station for complex patterned lace webs.

Abstract: The ever-increasing cost of labour in the textile industries coupled with rapid advances in technology has resulted in the automation of most sections in the present textile manufacturing industry. The recent addition to the automation drive, mostly in the last decade, has been substantial research in applying machine vision tools to replace humans for tasks such as inspection, textile characterisation and apparel manufacturing.

This paper investigates a novel approach for automatic inspection of deformable textile webs, particularly lace fabrics, in real time. The authors have worked on an incremental approach using a multi Digital Signal Processor (DSP) system to achieve the required task at a reasonably high speed with minimum false alarms. A direct comparison of
the live image with a perfect prototype in real time is found to be the most adaptable solution to the problem.