Exploring the Detection Accuracy of Concrete Cracks Using Various CNN Models
Automatic crack detection with the least amount of workforce has become a crucial task in the inspection and evaluation of the performances of concrete structure in civil engineering. Recently, although many concrete crack detection models based on convolutional neural networks (CNNs) have been deve...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Advances in Materials Science and Engineering |
| Online Access: | http://dx.doi.org/10.1155/2021/9923704 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850167067956740096 |
|---|---|
| author | Mohammed Ameen Mohammed Zheng Han Yange Li |
| author_facet | Mohammed Ameen Mohammed Zheng Han Yange Li |
| author_sort | Mohammed Ameen Mohammed |
| collection | DOAJ |
| description | Automatic crack detection with the least amount of workforce has become a crucial task in the inspection and evaluation of the performances of concrete structure in civil engineering. Recently, although many concrete crack detection models based on convolutional neural networks (CNNs) have been developed, the accuracy of the proposed models varies. Up-to-date, the issue regarding the convolutional neural network architecture with best performance for detecting concrete cracks is still debated in many previous studies. In this paper, we choose three established open-source CNN models (Model1, Model2, and Model3) which have been well-illustrated and verified in previous studies and test them for the purpose of crack detection of concrete structures. The chosen three models are trained using a concrete crack dataset containing 40,000 images those with 227 × 227-pixel in size. The performance of three different convolutional neural network (CNN) models was then evaluated. The comprehensive comparison result indicates that Model2 which used batch normalization is capable of the best performance amongst the three models as selected for concrete cracks detection, with recording the highest classification accuracy and low loss. In a conclusion, we recommend Model2 for a concrete crack detection task. |
| format | Article |
| id | doaj-art-db6a62e9d4444e37a46d404cce1505f1 |
| institution | OA Journals |
| issn | 1687-8434 1687-8442 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Materials Science and Engineering |
| spelling | doaj-art-db6a62e9d4444e37a46d404cce1505f12025-08-20T02:21:17ZengWileyAdvances in Materials Science and Engineering1687-84341687-84422021-01-01202110.1155/2021/99237049923704Exploring the Detection Accuracy of Concrete Cracks Using Various CNN ModelsMohammed Ameen Mohammed0Zheng Han1Yange Li2School of Civil Engineering, Central South University, Changsha 410075, ChinaSchool of Civil Engineering, Central South University, Changsha 410075, ChinaSchool of Civil Engineering, Central South University, Changsha 410075, ChinaAutomatic crack detection with the least amount of workforce has become a crucial task in the inspection and evaluation of the performances of concrete structure in civil engineering. Recently, although many concrete crack detection models based on convolutional neural networks (CNNs) have been developed, the accuracy of the proposed models varies. Up-to-date, the issue regarding the convolutional neural network architecture with best performance for detecting concrete cracks is still debated in many previous studies. In this paper, we choose three established open-source CNN models (Model1, Model2, and Model3) which have been well-illustrated and verified in previous studies and test them for the purpose of crack detection of concrete structures. The chosen three models are trained using a concrete crack dataset containing 40,000 images those with 227 × 227-pixel in size. The performance of three different convolutional neural network (CNN) models was then evaluated. The comprehensive comparison result indicates that Model2 which used batch normalization is capable of the best performance amongst the three models as selected for concrete cracks detection, with recording the highest classification accuracy and low loss. In a conclusion, we recommend Model2 for a concrete crack detection task.http://dx.doi.org/10.1155/2021/9923704 |
| spellingShingle | Mohammed Ameen Mohammed Zheng Han Yange Li Exploring the Detection Accuracy of Concrete Cracks Using Various CNN Models Advances in Materials Science and Engineering |
| title | Exploring the Detection Accuracy of Concrete Cracks Using Various CNN Models |
| title_full | Exploring the Detection Accuracy of Concrete Cracks Using Various CNN Models |
| title_fullStr | Exploring the Detection Accuracy of Concrete Cracks Using Various CNN Models |
| title_full_unstemmed | Exploring the Detection Accuracy of Concrete Cracks Using Various CNN Models |
| title_short | Exploring the Detection Accuracy of Concrete Cracks Using Various CNN Models |
| title_sort | exploring the detection accuracy of concrete cracks using various cnn models |
| url | http://dx.doi.org/10.1155/2021/9923704 |
| work_keys_str_mv | AT mohammedameenmohammed exploringthedetectionaccuracyofconcretecracksusingvariouscnnmodels AT zhenghan exploringthedetectionaccuracyofconcretecracksusingvariouscnnmodels AT yangeli exploringthedetectionaccuracyofconcretecracksusingvariouscnnmodels |