Classification of colored spun fabric structure based on wavelet decomposition and hierarchical hybrid classifier

• Published in: Journal of the Textile Institute Vol. 113; no. 9; pp. 1832 - 1837
• Main Authors: Gong, Xue, Yuan, Li, Yang, Yali, Liu, Junping, Liu, Muli
• Format: Journal Article
• Language: English
• Published: Manchester Taylor & Francis 02.09.2022; Taylor & Francis Ltd
• Subjects: Algorithms; Classification; Classifiers; color; Colored spun fabric; Decomposition; fabric structure classification; Fabric structures; fabrics; Feature extraction; hierarchical hybrid classifier; hybrids; Parameters; texture; wavelet; wavelet decomposition
• ISSN: 0040-5000; 1754-2340; 1754-2340
• DOI: 10.1080/00405000.2021.1950452

In view of the difficulty in extracting the feature parameters of colored spun fabric structure, this article proposes an automatic classification algorithm based on wavelet decomposition and hierarchical hybrid classifier. Based on HSV color space, the algorithm uses the wavelet function to perform multi-resolution decomposition and parameter feature extraction of colored spun fabric image. At the same time, it uses BP network and naive Bayes to build hierarchical hybrid classifier, and realizes the classification of the structure feature parameters. The experimental results show that the extracted fabric weave features not only have the ability of multi-resolution texture information representation, but also the constructed hybrid classifier has the characteristics of cascade enhancement. The average classification accuracy of 176 colored spun fabric structure with different dyeing fiber blending coefficient and twist coefficient is 96.67%, which proves the effectiveness and robustness of the method. The research in this article has important guiding significance to construct stable and effective colored spun fabric design and production system.