A multi-task and multi-scale convolutional neural network for automatic recognition of woven fabric pattern

• Published in: Journal of intelligent manufacturing Vol. 32; no. 4; pp. 1147 - 1161
• Main Authors: Meng, Shuo, Pan, Ruru, Gao, Weidong, Zhou, Jian, Wang, Jingan, He, Wentao
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.04.2021; Springer Nature B.V
• Subjects: Artificial neural networks; Business and Management; Control; Datasets; Fabric structures; Fabrics; Floats; Image processing; Machines; Manufacturing; Mechatronics; Neural networks; Pattern recognition; Portable equipment; Processes; Production; Quality control; Robotics; Textile industry; Woven fabrics; Yarns; Computer vision; Texture analysis; Weave pattern recognition; Multi-task learning; Convolutional neural network
• ISSN: 0956-5515; 1572-8145
• DOI: 10.1007/s10845-020-01607-9

The recognition of woven fabric pattern is a crucial task for mass manufacturing and quality control in the textile industry. Traditional methods based on image processing have some limitations on accuracy and stability. In this paper, an automatic method is proposed to jointly realize yarn location and weave pattern recognition. First, a new big fabric dataset is established by a portable wireless device. The dataset contains wide kinds of fabrics and detailed fabric structure parameters. Then, a novel multi-task and multi-scale convolutional neural network (MTMSnet) is proposed to predict the location maps of yarns and floats. By adopting the multi-task structure, the MTMSnet can better learn the related features between yarns and floats. Finally, the weave pattern and basic weave repeat are recognized by combining the yarn and float location maps. Extensive experimental results on various kinds of fabrics indicate that the proposed method achieves high accuracy and quality in weave pattern recognition.