Yarn features extraction using image processing and computer vision - A study with cotton and polyester yarns

The aim of this paper is the development of a new technological solution, for the automatic characterization of the yarn mass parameters (linear mass, diameter, and hairiness) based on image processing and computer vision techniques. A preliminary study for the detection and distinction between loop and protruding fibers is also presented. A custom-made application developed in LabVIEW from National Instruments with the IMAQ Vision Toolkit was used to acquire, analyze and process the yarn images. Some experimental results using cotton and polyester yarns were performed and compared with a commercial solution for validation. The presented approach allows a correct yarn parameterization improving products' quality in the textile industry.