{"title":"Local Characterisation and Detection of Woven Fabric Texture Based on a Sparse Dictionary","authors":"Ying Wu, Ren Wang, Lin Lou, Lali Wang, J. Wang","doi":"10.2478/ftee-2022-0020","DOIUrl":null,"url":null,"abstract":"Abstract To achieve enhanced accuracy of fabric representation and defect detection, an innovative approach using a sparse dictionary with small patches was used for fabric texture characterisation. The effectiveness of the algorithm proposed was tested through comprehensive characterisation by studying eight weave patterns: plain, twill, weft satin, warp satin, basket, honeycomb, compound twill, and diamond twill and detecting fabric defects. Firstly, the main parameters such as dictionary size, patch size, and cardinality T were optimised, and then 40 defect-free fabric samples were characterised by the algorithm proposed. Subsequently, the impact of the weave pattern was investigated based on the representation result and texture structure. Finally, defective fabrics were detected. The algorithm proposed is an alternative simple and scalable method to characterise fabric texture and detect textile defects in a single step without extracting features or prior information.","PeriodicalId":12309,"journal":{"name":"Fibres & Textiles in Eastern Europe","volume":"30 1","pages":"33 - 40"},"PeriodicalIF":0.7000,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fibres & Textiles in Eastern Europe","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.2478/ftee-2022-0020","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATERIALS SCIENCE, TEXTILES","Score":null,"Total":0}
引用次数: 0
Abstract
Abstract To achieve enhanced accuracy of fabric representation and defect detection, an innovative approach using a sparse dictionary with small patches was used for fabric texture characterisation. The effectiveness of the algorithm proposed was tested through comprehensive characterisation by studying eight weave patterns: plain, twill, weft satin, warp satin, basket, honeycomb, compound twill, and diamond twill and detecting fabric defects. Firstly, the main parameters such as dictionary size, patch size, and cardinality T were optimised, and then 40 defect-free fabric samples were characterised by the algorithm proposed. Subsequently, the impact of the weave pattern was investigated based on the representation result and texture structure. Finally, defective fabrics were detected. The algorithm proposed is an alternative simple and scalable method to characterise fabric texture and detect textile defects in a single step without extracting features or prior information.
期刊介绍:
FIBRES & TEXTILES in Eastern Europe is a peer reviewed bimonthly scientific journal devoted to current problems of fibre, textile and fibrous products’ science as well as general economic problems of textile industry worldwide. The content of the journal is available online as free open access.
FIBRES & TEXTILES in Eastern Europe constitutes a forum for the exchange of information and the establishment of mutual contact for cooperation between scientific centres, as well as between science and industry.