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

Journal Title: Fibres and Textiles in Eastern Europe - Year 2019, Vol 27, Issue 1

Abstract

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.<br/><br/>

Authors and Affiliations

Zhiyu Zhou, Chao Wang, Xu Gao, Zefei Zhu, Xudong Hu, Xiao Zheng, Likai Jiang

Keywords

Related Articles

Functional Nanocomposite Poly(phenylene sulphide) Fibres - Preliminary Studies&nbsp;

Composite poly(phenylene sulphide) (PPS) fibres and nonwovens were obtained by the melt blowing method. A specially designed twin screw extruder was used which allowed to perform several mixing cycles prior to final extr...

Statistical Analysis of the Pilling Behaviour of Polyester/Cotton and Polyester/Viscose Blended Woven Fabrics

In this work, the pilling behaviour of polyester blended fabrics was studied and analysed statistically. Two different groups of blends were selected, namely polyester/cotton (P/C) and polyester/viscose blends (P/V). All...

Influence of the Yarn Formation Process on the Characteristics of Viscose Fabric Made of Vortex Coloured Spun Yarns

In this study, based on the Box-Behnken design, regression statistical analysis is introduced to evaluate the influence of yarn formation process variables (nozzle pressure, yarn delivery speed and yarn count) on the pro...

Właściwości kompozytów aramidowych i z polietylenu o super wysokim ciężarze cząsteczkowym poddanych udarom o małej prędkości

Powszechną metodą produkcji kompozytów dla zastosowań balistycznych jest użycie jako wzmocnienia włókien aramidowych oraz włókien polietylenowych o super wysokim ciężarze cząsteczkowym i różnych materiałach matrycy. Mate...

Social Media in the Process of Marketing Evolution in Polish Textile-Clothing Industry

The extile-clothing industry is still perceived as one of the most important sectors of the world economy, and it is also the case in Poland, where it determines the directions of development of regions related to it. Th...

Download PDF file
  • EP ID EP413796
  • DOI 10.5604/01.3001.0012.7510
  • Views 90
  • Downloads 0

How To Cite

Zhiyu Zhou, Chao Wang, Xu Gao, Zefei Zhu, Xudong Hu, Xiao Zheng, Likai Jiang (2019). Fabric Defect Detection and Classifier via Multi-Scale Dictionary Learning and an Adaptive Differential Evolution Optimized Regularization Extreme Learning Machine. Fibres and Textiles in Eastern Europe, 27(1), 67-77. https://europub.co.uk/articles/-A-413796