|
| Image recognition method of zinc cathode plate residue based on improved yolov3 |
|
Received:June 23, 2020
Revised:July 08, 2020
Accepted:July 09, 2020
Published Online:February 08, 2021
|
| View Full Text View/Add Comment Download reader |
| DOI： |
| KeyWord:Deep learning; Residue identification; cathode plate; YOLOv3 |
| Author | Institution |
| LU Hengrun |
BGRIMM Machinery and Automation Technology Co.,Ltd. |
| LI Qiang |
BGRIMM Machinery and Automation Technology Co.,Ltd. |
| YANG Wenwang |
BGRIMM Machinery and Automation Technology Co.,Ltd. |
|
| Hits: 2428 |
| Download times: 1218 |
| Abstract: |
| In order to identify the residue of zinc cathode plate of zinc stripping machine, this paper studies an image recognition method based on deep learning. Based on the yolov3 single-stage image detection model, the original network structure darknet53 is replaced by the Xception network structure with deep separable convolution to improve the feature extraction ability of the detection model, and by improving the candidate box generation strategy to reduce the imbalance between positive and negative samples. The experiment compares the recognition effect of the improved structure and the original structure from the loss curve of training process and the recognition accuracy. The results show that the method based on improved yolov3 improves the generalization ability of the detection model, the recognition accuracy of cathode plate residue is up to 95%, 3% higher than the original yolov3 model. |
| Close |
|
|
|