Defects detection of floor tiles of ancient buildings based on Faster R-CNN
Defect detection is of great significance for the protection and repair of ancient buildings. The traditional floor tile defect detection has been subject to visual inspection, which has limitations due to human influence and time-consuming. Based on the good application prospects of deep learning,...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
National Computer System Engineering Research Institute of China
2021-01-01
|
| Series: | Dianzi Jishu Yingyong |
| Subjects: | |
| Online Access: | http://www.chinaaet.com/article/3000127916 |
| _version_ | 1819068521987964928 |
|---|---|
| author | Chen Li Liu Yanyan |
| author_facet | Chen Li Liu Yanyan |
| author_sort | Chen Li |
| collection | DOAJ |
| description | Defect detection is of great significance for the protection and repair of ancient buildings. The traditional floor tile defect detection has been subject to visual inspection, which has limitations due to human influence and time-consuming. Based on the good application prospects of deep learning, this paper builds a data set of imperfections in the Forbidden City, and proposes an improved Faster R-CNN. Firstly, the deformable convolution was constructed, and the defect features in the floor tile were learned and extracted through the network. Then，the feature graph was input into region proposal network to generate the candidate region box, and the generated feature graph and candidate region box was pooled. Finally, the defect detection results were output. Under the test of the image data set of floor tiles of the Forbidden City, the mean accuracy of the improved model reached 92.49%, which was 2.99% higher than the Faster R-CNN model and more suitable for the floor tile defect detection. |
| first_indexed | 2024-12-21T16:35:29Z |
| format | Article |
| id | doaj.art-565820e30e0b4a94abf70571f0551319 |
| institution | Directory Open Access Journal |
| issn | 0258-7998 |
| language | zho |
| last_indexed | 2024-12-21T16:35:29Z |
| publishDate | 2021-01-01 |
| publisher | National Computer System Engineering Research Institute of China |
| record_format | Article |
| series | Dianzi Jishu Yingyong |
| spelling | doaj.art-565820e30e0b4a94abf70571f05513192022-12-21T18:57:14ZzhoNational Computer System Engineering Research Institute of ChinaDianzi Jishu Yingyong0258-79982021-01-01471313510.16157/j.issn.0258-7998.2005553000127916Defects detection of floor tiles of ancient buildings based on Faster R-CNNChen Li0Liu Yanyan1Key Laboratory for Photoelectronic Thin Film Devices and Technology of Tianjin，Nankai University，Tianjin 300350，ChinaKey Laboratory for Photoelectronic Thin Film Devices and Technology of Tianjin，Nankai University，Tianjin 300350，ChinaDefect detection is of great significance for the protection and repair of ancient buildings. The traditional floor tile defect detection has been subject to visual inspection, which has limitations due to human influence and time-consuming. Based on the good application prospects of deep learning, this paper builds a data set of imperfections in the Forbidden City, and proposes an improved Faster R-CNN. Firstly, the deformable convolution was constructed, and the defect features in the floor tile were learned and extracted through the network. Then，the feature graph was input into region proposal network to generate the candidate region box, and the generated feature graph and candidate region box was pooled. Finally, the defect detection results were output. Under the test of the image data set of floor tiles of the Forbidden City, the mean accuracy of the improved model reached 92.49%, which was 2.99% higher than the Faster R-CNN model and more suitable for the floor tile defect detection.http://www.chinaaet.com/article/3000127916defect detectionfaster r-cnndeformable convolution |
| spellingShingle | Chen Li Liu Yanyan Defects detection of floor tiles of ancient buildings based on Faster R-CNN Dianzi Jishu Yingyong defect detection faster r-cnn deformable convolution |
| title | Defects detection of floor tiles of ancient buildings based on Faster R-CNN |
| title_full | Defects detection of floor tiles of ancient buildings based on Faster R-CNN |
| title_fullStr | Defects detection of floor tiles of ancient buildings based on Faster R-CNN |
| title_full_unstemmed | Defects detection of floor tiles of ancient buildings based on Faster R-CNN |
| title_short | Defects detection of floor tiles of ancient buildings based on Faster R-CNN |
| title_sort | defects detection of floor tiles of ancient buildings based on faster r cnn |
| topic | defect detection faster r-cnn deformable convolution |
| url | http://www.chinaaet.com/article/3000127916 |
| work_keys_str_mv | AT chenli defectsdetectionoffloortilesofancientbuildingsbasedonfasterrcnn AT liuyanyan defectsdetectionoffloortilesofancientbuildingsbasedonfasterrcnn |