Automatic Detection of Welding Defects Using Faster R-CNN
In the shipbuilding industry, the non-destructive testing for welding quality inspection is mainly used for the permanent storage of the testing results and the radio-graphic testing which can visually inspect the interior of the welded part. Experts are required to properly detect the test results...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/23/8629 |
| _version_ | 1797545910329147392 |
|---|---|
| author | Sang-jin Oh Min-jae Jung Chaeog Lim Sung-chul Shin |
| author_facet | Sang-jin Oh Min-jae Jung Chaeog Lim Sung-chul Shin |
| author_sort | Sang-jin Oh |
| collection | DOAJ |
| description | In the shipbuilding industry, the non-destructive testing for welding quality inspection is mainly used for the permanent storage of the testing results and the radio-graphic testing which can visually inspect the interior of the welded part. Experts are required to properly detect the test results and it takes a lot of time and cost to manually Interpret the radio-graphic testing image of the structure over 500 blocks. The algorithms that automatically interpret the existing radio-graphic testing images to extract features through image pre-processing and classify the defects using neural networks, and only partial automation is performed. In order to implement the feature extraction and classification in one algorithm and to implement the overall automation, this paper proposes a method of automatically detecting welding defect using Faster R-CNN which is a deep learning basis. We analyzed the data to learn algorithms and compared the performance improvements using data augmentation method to artificially increase the limited data. In order to appropriately extract the features of the radio-graphic testing image, two internal feature extractors of Faster R-CNN were selected, compared, and performance evaluation was performed. |
| first_indexed | 2024-03-10T14:22:37Z |
| format | Article |
| id | doaj.art-b9ecca1b93d1473797b7ebf7591fb485 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T14:22:37Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b9ecca1b93d1473797b7ebf7591fb4852023-11-20T23:16:52ZengMDPI AGApplied Sciences2076-34172020-12-011023862910.3390/app10238629Automatic Detection of Welding Defects Using Faster R-CNNSang-jin Oh0Min-jae Jung1Chaeog Lim2Sung-chul Shin3Department of Naval Architecture and Ocean Engineering, Pusan National University, Busan 46241, KoreaDepartment of Naval Vessel Service, Korean Register, Busan 46241, KoreaDepartment of Naval Architecture and Ocean Engineering, Pusan National University, Busan 46241, KoreaDepartment of Naval Architecture and Ocean Engineering, Pusan National University, Busan 46241, KoreaIn the shipbuilding industry, the non-destructive testing for welding quality inspection is mainly used for the permanent storage of the testing results and the radio-graphic testing which can visually inspect the interior of the welded part. Experts are required to properly detect the test results and it takes a lot of time and cost to manually Interpret the radio-graphic testing image of the structure over 500 blocks. The algorithms that automatically interpret the existing radio-graphic testing images to extract features through image pre-processing and classify the defects using neural networks, and only partial automation is performed. In order to implement the feature extraction and classification in one algorithm and to implement the overall automation, this paper proposes a method of automatically detecting welding defect using Faster R-CNN which is a deep learning basis. We analyzed the data to learn algorithms and compared the performance improvements using data augmentation method to artificially increase the limited data. In order to appropriately extract the features of the radio-graphic testing image, two internal feature extractors of Faster R-CNN were selected, compared, and performance evaluation was performed.https://www.mdpi.com/2076-3417/10/23/8629welding defectFaster R-CNNradiographic testingautomatic detectionobject detection |
| spellingShingle | Sang-jin Oh Min-jae Jung Chaeog Lim Sung-chul Shin Automatic Detection of Welding Defects Using Faster R-CNN Applied Sciences welding defect Faster R-CNN radiographic testing automatic detection object detection |
| title | Automatic Detection of Welding Defects Using Faster R-CNN |
| title_full | Automatic Detection of Welding Defects Using Faster R-CNN |
| title_fullStr | Automatic Detection of Welding Defects Using Faster R-CNN |
| title_full_unstemmed | Automatic Detection of Welding Defects Using Faster R-CNN |
| title_short | Automatic Detection of Welding Defects Using Faster R-CNN |
| title_sort | automatic detection of welding defects using faster r cnn |
| topic | welding defect Faster R-CNN radiographic testing automatic detection object detection |
| url | https://www.mdpi.com/2076-3417/10/23/8629 |
| work_keys_str_mv | AT sangjinoh automaticdetectionofweldingdefectsusingfasterrcnn AT minjaejung automaticdetectionofweldingdefectsusingfasterrcnn AT chaeoglim automaticdetectionofweldingdefectsusingfasterrcnn AT sungchulshin automaticdetectionofweldingdefectsusingfasterrcnn |