A Detection Method for the Interlacing Degree of Filament Yarn Based on Semantic Information Enhancement
The interlacing degree serves as an important indicator for evaluating the performance of filament yarns and fabrics,typically detected manually in production workshop.To address the issues of high false detection rates in manual inspection,a parallel detection method for filament yarn interlacing degree based on semantic informa-tion enhancement is proposed.Firstly,to improve the recognition accuracy of interlacing nodes in a filament yarn,an improved backbone architecture based on MobileNetV2 is used for semantic information extraction to improve the computational speed of model.Building upon the proposed backbone architecture,semantic information en-hancement module and multilevel feature dilated module are designed to process the feature information of the backbone architecture.Meanwhile,a pixel-level attention mask is designed to weight and fuse the feature,in order to improve the accuracy of interlacing degree detection.Then,based on the proposed enhancement algorithm for se-mantic information,a parallel detection method of interlacing degree is designed to achieve batch calculation for in-terlacing degree of multiple filament yarns.The algorithm is used to detect interlacing node,while connected do-main analysis and mask extraction are used for parallel detection to extract independent regions of each filament yarn within the field.The parallel detection results are then fused to accurately obtain the interlacing degree detec-tion results for each filament yarn.To validate the effectiveness of the proposed method,a synthetic filament yarn dataset is established using a self-developed interlacing degree detection device,and experimental verification is con-ducted.The results demonstrate that the proposed method can effectively improve the accuracy of detection.
万方数据
维普
