Automatic Damage Detection on Traditional Wooden Structures with Deep Learning-Based Image Classification Method
Wood has a long history of being used as a valuable resource when it comes to building materials. Due to various external factors, in particular the weather, wood is liable to progressive damage over time, which negatively impacts the endurance of wooden structures. Damage assessment is key in under...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Zagreb, Faculty of Forestry and Wood Technology
2022-01-01
|
| Series: | Drvna Industrija |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/403148 |
| _version_ | 1811249485148323840 |
|---|---|
| author | Kemal Haciefendioglu Hasan Basri Başaga Murat Emre Kartal Mehmet Ceyhun Bulut |
| author_facet | Kemal Haciefendioglu Hasan Basri Başaga Murat Emre Kartal Mehmet Ceyhun Bulut |
| author_sort | Kemal Haciefendioglu |
| collection | DOAJ |
| description | Wood has a long history of being used as a valuable resource when it comes to building materials. Due to various external factors, in particular the weather, wood is liable to progressive damage over time, which negatively impacts the endurance of wooden structures. Damage assessment is key in understanding, as well as in effectively mitigating, problems that wooden structures are likely to face. The use of a classification system, via deep learning, can potentially reduce the probability of damage in engineering projects reliant on wood. The present study employed a transfer learning technique, to achieve greater accuracy, and instead of training a model from scratch, to determine the likelihood of risks to wooden structures prior to project commencement. Pretrained MobileNet_V2, Inception_V3, and ResNet_V2_50 models were used to customize and initialize weights. A separate set of images, not shown to the trained model, was used to examine the robustness of the models. The three models were compared in their abilities to assess the possibilities and types of damage. Results revealed that all three models achieve performance rates of similar reliability. However, when considering the loss ratios in regard to efficiency, it became apparent that the multi-layered MobileNet_V2 classifier stood out as the most effective of the pre-trained deep convolutional neural network (CNN) models. |
| first_indexed | 2024-04-12T15:48:26Z |
| format | Article |
| id | doaj.art-32c2233a2db744c49380edf3d6ad10ae |
| institution | Directory Open Access Journal |
| issn | 0012-6772 1847-1153 |
| language | English |
| last_indexed | 2024-04-12T15:48:26Z |
| publishDate | 2022-01-01 |
| publisher | University of Zagreb, Faculty of Forestry and Wood Technology |
| record_format | Article |
| series | Drvna Industrija |
| spelling | doaj.art-32c2233a2db744c49380edf3d6ad10ae2022-12-22T03:26:36ZengUniversity of Zagreb, Faculty of Forestry and Wood TechnologyDrvna Industrija0012-67721847-11532022-01-0173216317610.5552/drvind.2022.210815Automatic Damage Detection on Traditional Wooden Structures with Deep Learning-Based Image Classification MethodKemal Haciefendioglu0Hasan Basri Başaga1Murat Emre Kartal2Mehmet Ceyhun Bulut3Karadeniz Technical University, Department of Civil Engineering, Trabzon, TurkeyKaradeniz Technical University, Department of Civil Engineering, Trabzon, Turkeyİzmir Democracy University, Department of Civil Engineering, İzmir, TurkeyKaradeniz Technical University, Department of Civil Engineering, Trabzon, TurkeyWood has a long history of being used as a valuable resource when it comes to building materials. Due to various external factors, in particular the weather, wood is liable to progressive damage over time, which negatively impacts the endurance of wooden structures. Damage assessment is key in understanding, as well as in effectively mitigating, problems that wooden structures are likely to face. The use of a classification system, via deep learning, can potentially reduce the probability of damage in engineering projects reliant on wood. The present study employed a transfer learning technique, to achieve greater accuracy, and instead of training a model from scratch, to determine the likelihood of risks to wooden structures prior to project commencement. Pretrained MobileNet_V2, Inception_V3, and ResNet_V2_50 models were used to customize and initialize weights. A separate set of images, not shown to the trained model, was used to examine the robustness of the models. The three models were compared in their abilities to assess the possibilities and types of damage. Results revealed that all three models achieve performance rates of similar reliability. However, when considering the loss ratios in regard to efficiency, it became apparent that the multi-layered MobileNet_V2 classifier stood out as the most effective of the pre-trained deep convolutional neural network (CNN) models.https://hrcak.srce.hr/file/403148deep learning methodconvolutional neural networksmobilenet_v2inception_v3resnet_ v2_50wooden structures |
| spellingShingle | Kemal Haciefendioglu Hasan Basri Başaga Murat Emre Kartal Mehmet Ceyhun Bulut Automatic Damage Detection on Traditional Wooden Structures with Deep Learning-Based Image Classification Method Drvna Industrija deep learning method convolutional neural networks mobilenet_v2 inception_v3 resnet_ v2_50 wooden structures |
| title | Automatic Damage Detection on Traditional Wooden Structures with Deep Learning-Based Image Classification Method |
| title_full | Automatic Damage Detection on Traditional Wooden Structures with Deep Learning-Based Image Classification Method |
| title_fullStr | Automatic Damage Detection on Traditional Wooden Structures with Deep Learning-Based Image Classification Method |
| title_full_unstemmed | Automatic Damage Detection on Traditional Wooden Structures with Deep Learning-Based Image Classification Method |
| title_short | Automatic Damage Detection on Traditional Wooden Structures with Deep Learning-Based Image Classification Method |
| title_sort | automatic damage detection on traditional wooden structures with deep learning based image classification method |
| topic | deep learning method convolutional neural networks mobilenet_v2 inception_v3 resnet_ v2_50 wooden structures |
| url | https://hrcak.srce.hr/file/403148 |
| work_keys_str_mv | AT kemalhaciefendioglu automaticdamagedetectionontraditionalwoodenstructureswithdeeplearningbasedimageclassificationmethod AT hasanbasribasaga automaticdamagedetectionontraditionalwoodenstructureswithdeeplearningbasedimageclassificationmethod AT muratemrekartal automaticdamagedetectionontraditionalwoodenstructureswithdeeplearningbasedimageclassificationmethod AT mehmetceyhunbulut automaticdamagedetectionontraditionalwoodenstructureswithdeeplearningbasedimageclassificationmethod |