Where you are: Home pageYear 2019Issue (133) → Article:

Fabric Defect Detection and Classifier via Multi-Scale Dictionary Learning and an Adaptive Differential Evolution Optimized Regularization Extreme Learning Machine

Research and development


  • Zhou Zhiyu
    School of Information Science and Technology, Zhejiang Sci-Tech University (ZSTU), Hangzhou, P. R. China
  • Wang Chao (j/w)
  • Gao Xu (j/w)
  • Zhu Zefei
    College of Mechanical Engineering and Automation, Zhejiang Sci-Tech University (ZSTU), Hangzhou, P. R. China
  • Hu Xudong
    The Research Centre of Modern Textile Machinery Technology, Ministry of Education, Zhejiang Sci-Tech University (ZSTU), Hangzhou, P. R. China
  • Zheng Xiao
    School of Computer Science, Anhui University of Technology, Maanshan, P. R. China
  • Jiang Likai
    School of Information Science and Technology, Zhejiang Sci-Tech University (ZSTU), Hangzhou, P. R. China

Nr DOI: 10.5604/01.3001.0012.7510

Download... PDF
Full text
Download... PDF


To develop an automatic detection and classifier model for fabric defects, a novel detection and classifier technique based on multi-scale dictionary learning and the adaptive differential evolution algorithm optimised regularisation extreme learning machine (ADE-RELM) is proposed. Firstly in order to speed up dictionary updating under the condition of guaranteeing dictionary sparseness, k-means singular value decomposition (KSVD) dictionary learning is used. Then multi-scale KSVD dictionary learning is presented to extract texture features of textile images more accurately. Finally a unique ADE-RELM is designed to build a defect classifier model. In the training ADE-RELM classifier stage, a self-adaptive mutation operator is used to solve the parameter setting problem of the original differential evolution algorithm, then the adaptive differential evolution algorithm is utilised to calculate the optimal input weights and hidden bias of RELM. The method proposed is committed to detecting common defects like broken warp, broken weft, oil, and the declining warp of grey-level and pure colour fabrics. Experimental results show that compared with the traditional Gabor filter method, morphological operation and local binary pattern, the method proposed in this paper can locate defects precisely and achieve high detection efficiency.


defect detection, multi-scale dictionary learning, regularisation extreme learning machine, adaptive differential evolution.


Zhou Z, Wang C, Gao X, Zhu Z, Hu X, Zheng X, Jiang L. Fabric Defect Detection and Classifier via Multi-Scale Dictionary Learning and an Adaptive Differential Evolution Optimized Regularization Extreme Learning Machine. FIBRES & TEXTILES in Eastern Europe 2019; 27, 1(133): 67-77. DOI: 10.5604/01.3001.0012.7510

Published in issue no 1 (133) / 2019, pages 67–77.


in Eastern Europe
ul. Skłodowskiej-Curie 19/27,
90-570 Łódź, Poland
tel. (48-42) 638-03-14
tel. (48-42) 638-03-63
e-mail: infor@ibwch.lodz.pl

ul. Skłodowskiej-Curie 1927, 90-570 Łódź, Poland • tel.  (48-42) 638-03-14 • e-mail: infor@ibwch.lodz.plhttp://www.fibtex.lodz.pl

Editor-in-Chief Emilia Jaszczurska-Niedźwiedzka, V-ce Editor-in-Chief Marta Cyrczak, Text Editor Geoffrey Large, Assistant Editor Anna Wahl, Typesetting and Printed at Media-Press • Production IBWCh