Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN
To meet the practical needs of detecting various defects on the pointer surface and solve the difficulty of detecting some defects on the pointer surface, this paper proposes a transfer learning and improved Cascade-RCNN deep neural network (TICNET) algorithm for detecting pointer defects. Firstly,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/17/4939 |
| _version_ | 1797555017696149504 |
|---|---|
| author | Weidong Zhao Hancheng Huang Dan Li Feng Chen Wei Cheng |
| author_facet | Weidong Zhao Hancheng Huang Dan Li Feng Chen Wei Cheng |
| author_sort | Weidong Zhao |
| collection | DOAJ |
| description | To meet the practical needs of detecting various defects on the pointer surface and solve the difficulty of detecting some defects on the pointer surface, this paper proposes a transfer learning and improved Cascade-RCNN deep neural network (TICNET) algorithm for detecting pointer defects. Firstly, the convolutional layers of ResNet-50 are reconstructed by deformable convolution, which enhances the learning of pointer surface defects by feature extraction network. Furthermore, the problems of missing detection caused by internal differences and weak features are effectively solved. Secondly, the idea of online hard example mining (OHEM) is used to improve the Cascade-RCNN detection network, which achieve accurate classification of defects. Finally, based on the fact that common pointer defect dataset and pointer defect dataset established in this paper have the same low-level visual characteristics. The network is pre-trained on the common defect dataset, and weights are transferred to the defect dataset established in this paper, which reduces the training difficulty caused by too few data. The experimental results show that the proposed method achieves a 0.933 detection rate and a 0.873 mean average precision when the threshold of intersection over union is 0.5, and it realizes high precision detection of pointer surface defects. |
| first_indexed | 2024-03-10T16:40:14Z |
| format | Article |
| id | doaj.art-eb001cf3dd6c4729b671b1a55389ea93 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T16:40:14Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-eb001cf3dd6c4729b671b1a55389ea932023-11-20T12:06:19ZengMDPI AGSensors1424-82202020-09-012017493910.3390/s20174939Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNNWeidong Zhao0Hancheng Huang1Dan Li2Feng Chen3Wei Cheng4School of Electrical Information and Engineering, Anhui University of Technology, Ma’anshan 243032, ChinaSchool of Electrical Information and Engineering, Anhui University of Technology, Ma’anshan 243032, ChinaSchool of Electrical Information and Engineering, Anhui University of Technology, Ma’anshan 243032, ChinaSchool of Electrical Information and Engineering, Anhui University of Technology, Ma’anshan 243032, ChinaSchool of Electrical Information and Engineering, Anhui University of Technology, Ma’anshan 243032, ChinaTo meet the practical needs of detecting various defects on the pointer surface and solve the difficulty of detecting some defects on the pointer surface, this paper proposes a transfer learning and improved Cascade-RCNN deep neural network (TICNET) algorithm for detecting pointer defects. Firstly, the convolutional layers of ResNet-50 are reconstructed by deformable convolution, which enhances the learning of pointer surface defects by feature extraction network. Furthermore, the problems of missing detection caused by internal differences and weak features are effectively solved. Secondly, the idea of online hard example mining (OHEM) is used to improve the Cascade-RCNN detection network, which achieve accurate classification of defects. Finally, based on the fact that common pointer defect dataset and pointer defect dataset established in this paper have the same low-level visual characteristics. The network is pre-trained on the common defect dataset, and weights are transferred to the defect dataset established in this paper, which reduces the training difficulty caused by too few data. The experimental results show that the proposed method achieves a 0.933 detection rate and a 0.873 mean average precision when the threshold of intersection over union is 0.5, and it realizes high precision detection of pointer surface defects.https://www.mdpi.com/1424-8220/20/17/4939pointerdefect detectiontransfer learningdeformable convolutiononline hard example mining |
| spellingShingle | Weidong Zhao Hancheng Huang Dan Li Feng Chen Wei Cheng Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN Sensors pointer defect detection transfer learning deformable convolution online hard example mining |
| title | Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN |
| title_full | Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN |
| title_fullStr | Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN |
| title_full_unstemmed | Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN |
| title_short | Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN |
| title_sort | pointer defect detection based on transfer learning and improved cascade rcnn |
| topic | pointer defect detection transfer learning deformable convolution online hard example mining |
| url | https://www.mdpi.com/1424-8220/20/17/4939 |
| work_keys_str_mv | AT weidongzhao pointerdefectdetectionbasedontransferlearningandimprovedcascadercnn AT hanchenghuang pointerdefectdetectionbasedontransferlearningandimprovedcascadercnn AT danli pointerdefectdetectionbasedontransferlearningandimprovedcascadercnn AT fengchen pointerdefectdetectionbasedontransferlearningandimprovedcascadercnn AT weicheng pointerdefectdetectionbasedontransferlearningandimprovedcascadercnn |