Research Progress on the Application of Deep Learning Algorithms in Fiber Identification

Fiber identification is a key technology for determining the types and characteristics of fibers in fabrics. As the fundamental unit of yarns and textiles, fibers have diverse sources, with common materials including wool, polyester, and acrylic, among others. Therefore, accurately and efficiently identifying fiber types is of great significance in the field of textile inspection. In recent years, with the rapid advancement of artificial intelligence, deep learning algorithms have been increasingly applied to fiber identification tasks, significantly improving both accuracy and efficiency. This paper aims to provide a comprehensive review of the development of fiber identification technologies over the past decade, with a particular focus on the application of deep learning algorithms in this field. Specifically, we summarize deep learning-based fiber identification methods, analyze and compare them in terms of experimental accuracy and characteristics, and systematically review commonly used datasets and evaluation metrics. Finally, we discuss the limitations and challenges of current deep learning approaches and offer insights into future research directions in this field.