MATLAB Algorithms for Diameter Measurements of Textile Yarns and Fibers through Image Processing Techniques

Abstract

Textile yarns are the fundamental building blocks in the fabric industry. The measurement of the diameter of the yarn textile and fibers is crucial in textile engineering as the diameter size and distribution can affect the yarn’s properties, and image processing can provide automatic techniques for faster and more accurate determination of the diameters. In this paper, facile and new methods to measure the yarn’s diameter and its individual fibers diameter based on image processing algorithms that can be applied to microscopic digital images. Image preprocessing such as binarization and morphological operations on the yarn image were used to measure the diameter automatically and accurately compared to the manual measuring using ImageJ software. Additionally, the image preprocessing, the circular Hough transform was used to count the individual fibers in a yarn’s cross-section and count the number of fibers. The algorithms were built and deployed in a MATLAB (R2020b, The MathWorks, Inc., Natick, Massachusetts, United States) environment. The proposed methods showed a reliable, fast, and accurate measurement compared to other different image measuring softwares, such as ImageJ.

Intelligent Computer Vision System for Analysis and Characterization of Yarn Quality

“…In recent years, research work has been carried out to obtain more precise parameters of yarn quality, using image processing [4][5][6][7][8]. Thus, there is the need to implement these technological advances in a physical prototype to fill the existing gap in the industry.…”