Automatic recognition of woven fabric structural parameters: a review

This paper provides a comprehensive review of automatic recognition of woven fabric structural parameters in recent years. Fabric structural parameters mainly include fabric density, weave pattern, color pattern, etc., which need to be pre-set before production and carefully checked during quality control. The analysis of these parameters is considered the most crucial step in the textile industry. The commonly used manual operations based on human eyes and experiences are time-consuming and labor-intensive. In contrast, computer-vision-based methods or other automatic methods hold the advantages of quick response, objective evaluation, and high stability. In this paper, the background and definition of the analysis of fabric structural parameters are first introduced. Secondly, it offers some automated recognition systems and their configurations. Then, it describes an up-to-date survey across the existing methods and performs a comparative study of their characteristics, strengths, and weaknesses. Besides, some evaluation matrixes are provided to evaluate the performance of automatic recognition methods. Finally, the report makes conclusions and discusses future research directions. This review can benefit researchers in understanding and utilizing automated methods to recognize fabric structural parameters. Promisingly, it can also provide some novel ideas for other recognition problems in the textile industry like fabric defect detection, fabric appearance analysis, and fabric inverse modelling.

Automated summary

This paper provides a comprehensive review of recent research on automatic recognition of woven fabric structural parameters, highlighting the drawbacks of manual operations based on human eyes and experiences and the advantages of computer-vision-based automatic methods. It offers insights for researchers in the textile industry to understand and utilize automated methods effectively.