Multilinear principal component analysis-based tensor decomposition for fabric weave pattern recognition from high-dimensional streaming data

Modern textile industry integrates video sensors with automated fabric reeling systems for real-time fabric weave pattern inspection. This automation system lessens the human-vision-based cognitive load and improves fabric weave pattern inspection work. However, this automation system poses a unique challenge, particularly when dealing with high-dimensional streaming data from highly precision digital microscope cameras. The complexity arises from the continuous acquisition and management of such high-dimensional streaming video data. Considering the challenges posed by dimensionality reduction in high-dimensional data, this study employs multilinear principal component analysis (MPCA)-based tensor decomposition, a statistical technique designed to effectively reduce high-dimensional datasets into low-dimensional features. This paper proposes an innovative method for fabric weave pattern recognition (FWPR) by leveraging MPCA-based tensor decomposition to extract low-dimensional features from the high-dimensional fabric’s surface texture descriptor tensor (STDT). This proposed method replicates fabric pattern monitoring in automated fabric reeling systems by integrating a digital microscope camera to capture high-dimensional streaming video data from fabric surface texture features. Subsequently high-dimensional video data is converted into sequential image frames representing different fabric weave patterns. These image frames are processed with local binary pattern (LBP) and gray-level co-occurrence matrix (GLCM) methods to aggregate fabric’s surface pattern features and construct the high-dimensional STDT. This STDT is subsequently decomposed into low-dimensional features by leveraging MPCA, resulting in an impressive 99.99% reduction in dimension. A supervised machine learning method utilizes the extracted low-dimensional features to enable FWPR, demonstrating superiority of the proposed method over the benchmark methods in evaluation.