Visual Anomaly Detection via CNN-BiLSTM Network with Knit Feature Sequence for Floating-Yarn Stacking during the High-Speed Sweater Knitting Process

• Published in: Electronics (Basel) Vol. 13; no. 19; p. 3968
• Main Authors: Li, Jing, Wang, Yixiao, Liang, Weisheng, Xiong, Chao, Cai, Wenbo, Li, Lijun, Liu, Yi
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.10.2024
• Subjects: Accuracy; Algorithms; Anomalies; Computer vision; Defects; Head movement; High speed; Knitting; Methods; Needles; Needlework; Visual fields; Yarn; Yarns; China

In order to meet the current expanding market demand for knitwear, high-speed automatic knitting machines with “one-line knit to shape” capability are widely used. However, the frequent emergence of floating-yarn stacking anomalies during the high-speed knitting process will seriously hinder the nor...