Detection on chemical fiber silk detects by deep learning

Abstract

There are many surface defects which are difficult to detect manually in the process of chemical fiber silk production. In order to realize the intelligent detection on these defects and improve detection accuracy, an improved Faster RCNN algorithm was proposed. Firstly, the deformable convolution model was added to the backbone feature extraction network to improve the adaptability of the network to different defect features. Secondly, the Feature Pyramid Network was replaced by Recursive Feature Pyramid structure to extract features twice. Finally, the Loss function was improved, and RS Loss function was used to replace the original classification loss function to solve the problem caused by imbalanced sample categories. Experiment result shows that the mAP value calculated by the improved model is 84.7%, which is 4.3% higher than original Faster RCNN model. The improved model can meet the requirements of intelligent detection on chemical fiber silk defects in practical production and processing.