<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>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 <italic>T</italic> 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.</p>
</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.

Local Characterisation and Detection of Woven Fabric Texture Based on a Sparse Dictionary


Zhejiang Province Engineering Laboratory of Clothing Digital Technology

School of Economics and Management Zhejiang Sci-Tech University

Key Laboratory of Advanced Textile Materials and Manufacturing Technology

Zhejiang Provincial Key Laboratory of Fiber Materials and Manufacturing Technology

Key Laboratory of Textile Science & Technology

Fibres & Textiles in Eastern Europe

This work is licensed under the Creative Commons Attribution 3.0 Public License.