Lei Guo
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.
- M Yao, K Lai, R J Sun. Review and Prospect of Textile Detection Technology and Test Instruments[J]. Cotton Textile Technology, 2003, 31(2): 16-19Google Scholar
- Z J Duan, S B Li, J J Hu, Review of deep learning based object detection methods and their mainstream frameworks[J]. Laser & Optoelectronics Progress, 2020, 57(12): 59-74.Google Scholar
- M M Fu, M L Deng, D X Zhang. Survey on deep neural network image target detection algorithms[J]. Computer Systems & Applications, 2022, 31(07): 35-45.Google Scholar
- J F Dai, H Z Qi, Y W Xiong, Deformable Convolutional Networks[C]//Proceedings of 2017 IEEE International Conference on Computer Vision, October 22-29, 2017, Venice, Italy. New York: IEEE, 2017: 764-773.Google Scholar
- S Y Qiao, L C Chen, Y Alan. DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 19-25, 2021. New York: IEEE, 2021: 10208-10219.Google Scholar
- K Oksuz, B C Cam, E Akbas, Rank & Sort Loss for Object Detection and Instance Segmentation[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV), June 19-25, 2021. New York: IEEE, 2021: 2989-2998.Google ScholarCross Ref
- K He, X Zhang, S Ren, . Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 26-July 1, 2016, Las Vegas, USA. New York: IEEE, 2016: 770-778.Google Scholar
- T Y Lin, P Dollar, R Girshick, Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, USA. New York: IEEE, 2017: 936-944.Google Scholar
Recommendations
Hybrid dilated faster RCNN for object detection
Object detection is a very important part of computer vision, and the most common method of object detection is the Faster region convolutional neural network (RCNN), which uses CNN to extract image features. However, the parameters to be learned in CNN ...
A Comparison of Deep Learning Methods for Vision-based Fire Detection in Surveillance System
ICFNDS 2021: The 5th International Conference on Future Networks & Distributed SystemsFire detection by analyzing video and images from surveillance cameras is increasingly being used as an early warning system. Fire detection using video surveillance as input is much more efficient than fire sensors because of the broader coverage area ...
RETRACTED ARTICLE: Capacitance pin defect detection based on deep learning
AbstractMask R-CNN network based on deep learning algorithm is specifically optimized for the small visual defects of gears. After comparison, the ResNet-101 residual neural network is used as the image sharing feature for network extraction. Subsequently,...
Comments