Real-time Segmentation of Yarn Images Based on an FCM Algorithm and Intensity Gradient Analysis

Journal Title: Fibres and Textiles in Eastern Europe - Year 2016, Vol 24, Issue 4

Abstract

This paper presents a new method for real-time segmentation of yarn images which are captured by a real-time image acquisition device. The first frame of the images is clustered by the local average intensity and entropy of the image based on the FCM (Fuzzy C-means) algorithm to obtain a segmentation threshold value. The pixels with an intensity below the threshold value in each column of the image are convolved with a convolve template to construct an intensity gradient curve. The points of maximum value and minimum value in the curve are considered as the upper and lower edge points of yarn. A robust real-time segmentation algorithm of yarn images is obtained for evaluating yarn diameter more precisely. Finally two indices of SE (Segmentation Error) in % and ADE (Average Diameter Error) in % are proposed to evaluate the segmentation method, which is then compared with the manual method.

Authors and Affiliations

Zhongjian Li, Ruru Pan, Jing’an Wang, Ziyu Wang, Bianbian Li, Weidong Gao

Keywords

Related Articles

Investigation of the Properties of Natural Fibre Woven Fabrics as a Reinforcement Materials for Green Composites

The mechanical properties of flax and jute woven fabrics were investigated and compared with each other. Mechanical properties of the yarns and fabrics were characterised and compared for each scale. The fabric structur...

Geo-textiles for Side Slope Protection: Preparation and Characteristics

The vegetation blanket is the most common choice for soil and water preservation. This is a feasible method that protects the land and environment according to basic agriculture and engineering theories. This study manuf...

Dziany ubiór wielofunkcjyjny jako część inkubatora tekstylnego dla dzieci przedwcześnie urodzonych

Przedstawiono innowacyjną koncepcje budowy tekstylnego inkubatora. Przeprowadzono studium literaturowe w aspekcie sposobów opieki nad wcześniakami na oddziałach intensywnej terapii neonatologii. W oparciu o wymagania fiz...

Ornamentacja litewskich etnograficznych tkanin ludowych

W analizowanej literaturze nie stwierdzono interdyscyplinarnych badań, które łączyłyby aspekty etnograficzne i technologiczne dotyczące litewskich tekstyliów ludowych. Celem badań była kompleksowa analiza tych zagadnień....

Water Vapor Permeability through PAN Nanofiber Mat with Varying Membrane-Like Areas

Electrospinning can be used to create nanofiber mats from diverse polymers which can be used as filters etc. Depending on the spinning parameters, also nano-membranes, i.e. non-fibrous mats, can be produced as well as mi...

Download PDF file
  • EP ID EP90624
  • DOI 10.5604/12303666.1201130
  • Views 121
  • Downloads 0

How To Cite

Zhongjian Li, Ruru Pan, Jing’an Wang, Ziyu Wang, Bianbian Li, Weidong Gao (2016). Real-time Segmentation of Yarn Images Based on an FCM Algorithm and Intensity Gradient Analysis. Fibres and Textiles in Eastern Europe, 24(4), 45-50. https://www.europub.co.uk/articles/-A-90624