A Review of Image‐Based Fabric Color Measurement: Methods, Challenges, and Future Prospects

ABSTRACT Color is a crucial factor in the textile industry, directly affecting product quality and customer satisfaction. Traditionally, fabric color measurement has primarily relied on spectroscopic methods and colorimeters, which require direct contact with the fabric samples and often involve high costs. With the innovations of image processing technology, image‐based color measurement (IBCM) methods have provided new possibilities thanks to their flexibility and automation potential. This paper provides an overview of IBCM approaches, including multispectral imaging systems, hyperspectral imaging, digital cameras, and scanners. Recent studies have shown that the application of artificial intelligence (AI) and computer vision in color measurement can enhance measurement accuracy and stability. However, this method still faces many challenges, such as the influence of ambient lighting, camera angles, fabric materials, and discrepancies among measuring devices. In addition, the work discusses color correction techniques aimed at improving the IBCM's accuracy, including spectral reflectance reconstruction, color balancing, and machine learning algorithms. Furthermore, the paper analyzes the applicability of IBCM technology in industrial textile quality control, and proposes future research directions, such as developing advanced AI algorithms, integrating Internet of Things (IoT) technology, and establishing standards for IBCM. The findings suggest that, despite remaining challenges, IBCM is emerging as a promising solution to replace or complement traditional color measurement methods in the textile industry.