Intelligent Quality Control of Surface Defects in Fabrics: A Comprehensive Research Progress

Abstract

Fabric defect detection is a crucial step of quality control in textile enterprises. The use of computer vision inspection technology in the textile industry is key to achieving intelligent manufacturing. This study sought to determine the progress made and future research directions in intelligent fabric surface defect detection by comprehensively reviewing published literature in terms of algorithms, datasets, and detection systems. Initially, the detection methods are classified as traditional and learning-based methods. The traditional methods are subdivided into model, spectral, statistical, and structural approaches. Learningbased methods are categorized into classical machine learning methods and deep learning methods. The principles, model performance, detection rate, real-time performance, and applicability of deep learning methods are highlighted and compared. In addition, the strengths and weaknesses of all the approaches are elaborated. The use of fabric defect datasets and deep learning frameworks is analyzed. Public datasets and commonly used frameworks are collated and organized. The application of existing fabric inspection systems on the market is outlined. Fabric defect types are systematically named and analyzed. Finally, future research directions are discussed to provide guidance for researchers in related fields.