Where you are: Home pageYear 2014Issue (108) → Article:
AAA     ENG | POL

Integrated Computer Vision and Soft Computing System for Classifying the Pilling Resistance of Knitted Fabrics

Research and development

Authors:

  • Eldessouki Mohamed
    Department of Textile Engineering, Faculty of Engineering, Mansoura University, Mansoura, Egypt
  • Eldessouki Mohamed
    Department of Materials Engineering, Technical University of Liberec, Liberec, Czech Republic
  • Bukhari Hanan A.
    Department of Fashion Design, Faculty of Art & Design, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
  • Hassan Mounir
    Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
  • Hassan Mounir
    Department of Textile Engineering, Faculty of Engineering, Mansoura University, Mansoura, Egypt
  • Qashqary Khadijah
    Department of Fashion Design, Faculty of Art & Design, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia

Download... PDF
Full text

Abstract:

Fabric pilling is one of the important properties that affect fabric appearance. The testing of fabric pilling using the standard methods available, however, depends on subjective sample evaluation. Objective fabric pilling evaluation using image processing techniques comprises four main stages that include binarisation, segmentation, quantisation, and classification. Literature on the topic focuses only on one or more of these stages while there is a growing need for an integrated system that combines the most effective techniques of each stage and introduces them in a way that does not depend on the subjective evaluation of human operators. This work tries to tackle this problem and creates an integrated system for classifying the pilling resistance of knitted fabrics. The system introduced a new method for generating an image library based on photographs of the EMPA Standards to allow the training and testing of a soft-computing classifier. The method suggested was tested using knitted samples of different structures and colours and the results show their high robustness performance. The quantitative pilling classification produced from the system suggested shows high agreement with the subjective operators’ evaluation with a Spearman’s correlation coefficient of +0.85.

Tags:

pilling of knitted fabric, pill segmentation, pill quantisation, soft-computing classifier, artificial neural networks.

Citation:

Eldessouki M, Hassan M, Bukhari HA, Qashqari K. Integrated Computer Vision and Soft Computing System for Classifying the Pilling Resistance of Knitted Fabrics. FIBRES & TEXTILES in Eastern Europe 2014; 22, 6(108): 106-112.

Published in issue no 6 (108) / 2014, pages 106–112.

CONTACT:

FIBRES & TEXTILES
in Eastern Europe
ul. Skłodowskiej-Curie 19/27,
90-570 Łódź, Poland
e-mail: infor@lit.lukasiewicz.gov.pl
ftee@lit.lukasiewicz.gov.pl
Events:

EDITORIAL OFFICE
FIBRES & TEXTILES in Eastern Europe 19/27 M. Skłodowskiej-Curie Str., 90-570 Łódź, Poland e-mail: infor@lit.lukasiewicz.gov.pl; ftee@lit.lukasiewicz.gov.pl

EDITORIAL DEPARTMENT
Editor-in-Chief Dariusz Wawro, Head of Editorial Office Janusz Kazimierczak, Text Editor Geoffrey Large, Assistant Editor Anna WahlProduction Łukasiewicz-ŁIT

facebook