Comparison of Classification Models for Detection of Cracks in Building Surfaces After Earthquake

Year 2022, Volume: 37 Issue: 4, 899 - 910, 30.12.2022

Abdullah Şener , Burhan Ergen

https://doi.org/10.21605/cukurovaumfd.1230792

Abstract

An earthquake is a natural disaster that causes loss of life and property. It is of great importance to make preparations to minimize the damage and loss of life after an earthquake. In the study, the detection of small or large cracks on the wall surfaces was performed using image classification methods, which are one of the most popular working topics in the computer field in recent years. A dataset of 40000 wall images with and without cracks was used for the study. DenseNet-201, VGG-19 and Xception models were used separately for the classification. Feature maps of the images were extracted using the models. In the next step, the classification processes were performed with DenseNet-201 with 99% accuracy, with VGG-19 with 94% accuracy, and with the Xception model with 99% accuracy. Considering the success in the classification processes, an alternative method that can be used in damage assessment is presented.

Keywords

Image classification, Artificial neural networks, Deep learning, DenseNet-201, VGG-19, Xception

Deprem Sonrası Bina Yüzeylerinde Meydana Gelen Çatlakların Tespitinde Sınıflandırma Modellerinin Karşılaştırılması

Abstract

Deprem, can ve mal kaybına neden olan bir doğal afettir. Deprem sonrası hasarların ve can kayıplarının en aza indirilebilmesi için ön hazırlıkların yapılması büyük önem taşımaktadır. Yapılan çalışmada duvar yüzeylerinde meydana gelen küçük veya büyük çaplı çatlakların tespit edilmesi işlemleri, son yıllarda bilgisayar alanında popüler çalışma konularından biri olan görüntü sınıflandırma yöntemleriyle gerçekleştirilmiştir. Çalışmada içerisinde çatlakların bulunduğu ve bulunmadığı 40000 duvar görüntülerinden oluşan veri seti kullanılmıştır. Sınıflandırma işlemlerinde DenseNet-201, VGG-19 ve Xception modelleri ayrı ayrı kullanılmıştır. Modeller kullanılarak görüntüler özellik haritaları çıkartılmıştır. Bir sonraki aşamada ise DenseNet-201 ile %99, VGG-19 ile %94 ve Xception modeli ile
%99 doğruluk oranı ile sınıflandırma işlemleri gerçekleştirilmiştir. Gerçekleştirilen sınıflandırma işlemlerindeki başarılar göz önüne alındığında hasar tespiti işlemlerinde kullanılabilecek alternatif bir yöntem sunulmaktadır.

Keywords

Görüntü sınıflandırma, Yapay sinir ağları, Derin öğrenme, DenseNet-201, Xception, VGG-19

References

• ⦁ İşçi, C., 2008. Deprem Nedir ve Nasıl Korunuruz. Yaşar Üniversitesi E-Dergisi, 3(9), 959.
• ⦁ Liu, X., Deng, Z., Yang, Y., 2019. Recent Progress in Semantic Image Segmentation. Artificial Intelligence Review, 52(2), 1089-1106.
• ⦁ Campbell, J.B., Wynne, R.H., 2011. Introduction to Remote Sensing. Guilford Press, 670.
• ⦁ Gao, J., 2009. Digital Analysis of Remotely Sensed Imagery. McGraw-Hill Education, 674.
• ⦁ Rateke, T., Von Wangenheim, A., 2021. Road Surface Detection and Differentiation Considering Surface Damages. Autonomous Robots, 45(2), 299-312.
• ⦁ Silva, W.R.L.D., Lucena, D.S.D., 2018. Concrete Cracks Detection Based on Deep Learning Image Classification. In Proceedings, MDPI AG, 2(8) 489.
• ⦁ Duarte, D., Nex, F., Kerle, N., Vosselman, G., 2018. Multi-Resolution Feature Fusion for Image Classification of Building Damages with Convolutional Neural Networks Remote Sens, 10(1636), 10-3390.
• ⦁ Maeda, H., Sekimoto, Y., Seto, T., Kashiyama, T., Omata, H., 2018. Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone. arXiv preprint arXiv:1801.09454.
• ⦁ Wang, N., Zhao, Q., Li, S., Zhao, X., Zhao, P., 2018. Damage Classification for Masonry Historic Structures Using Convolutional Neural Networks Based on Still Images. Computer-Aided Civil and Infrastructure Engineering, 33(12), 1073-1089.
• ⦁ Reddy, A., Indragandhi, V., Ravi, L., Subramaniyaswamy, V., 2019. Detection of Cracks and Damage in Wind Turbine Blades Using Artificial Intelligence-Based Image Analytics. Measurement, 147, 106823.
• ⦁ Shihavuddin, A.S.M., Rashid, M.R.A., Maruf, M.H., Hasan, M.A., ul Haq, M.A., Ashique, R. H., Al Mansur, A., 2021. Image Based Surface Damage Detection of Renewable Energy Installations Using a Unified Deep Learning Approach. Energy Reports, 7, 4566-4576.
• ⦁ Choi, K.Y., Kim, S.S., 2005. Morphological Analysis and Classification of Types of Surface Corrosion Damage by Digital Image Processing. Corrosion Science, 47(1), 1-15.
• ⦁ Surface Crack Detection Using DL Models, Veri seti: https://www.kaggle.com/ hamzamanssor/surface-crack-detection-using-dl-models/data, Erişim tarihi: 28.12.2021.
• ⦁ Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Chen, T., 2018. Recent Advances in Convolutional Neural Networks. Pattern Recognition, 77, 354-377.
• ⦁ Min, S., Lee, B., Yoon, S., 2017. Deep Learning in Bioinformatics. Briefings in Bioinformatics, 18(5), 851-869.
• ⦁ Hanbay, K., 2020. Hyperspectral Image Classification Using Convolutional Neural Network and Two-Dimensional Complex Gabor Transform. Journal of the Faculty of Engineering and Architecture of Gazi University, 35(1), 443-456.
• ⦁ Niepert, M., Ahmed, M., Kutzkov, K., 2014. Learning Convolutional Neural Networks for Graphs. In International Conference on Machine Learning, Germany: 2016. 2014-2023.
• ⦁ Kumar, R., 2020. Adding Binary Search Connections to Improve Densenet Performance. In 5th International Conference on Next Generation Computing Technologies (NGCT-2019).
• ⦁ Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q., 2017. Densely Connected Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4700-4708.
• ⦁ Li, X., Shen, X., Zhou, Y., Wang, X., Li, T.Q., 2020. Classification of Breast Cancer Histopathological Images Using Interleaved DenseNet with SENet (IDSNet). PloS one, 15(5), e0232127.
• ⦁ Toğaçar, M., Ergen, B., Özyurt, F., 2020. Evrişimsel Sinir Ağı Modellerinde Özellik Seçim Yöntemlerini Kullanarak Çiçek Görüntülerinin Sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 32(1), 47-56.
• ⦁ Mateen, M., Wen, J., Song, S., Huang, Z., 2018. Fundus Image Classification Using VGG-19 Architecture with PCA and SVD. Symmetry, 11(1), 1.
• ⦁ Lin, M., Chen, Q., Yan, S., 2014. Network in Network, 2nd Int. Conf. Learn. Represent. ICLR 2014 - Conf. Track Proc.
• ⦁ Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z., 2016. Rethinking the Inception Architecture for Computer Vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818-2826.
• ⦁ Chollet, F., 2017. Xception: Deep Learning with Depthwise Separable Convolutions. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1251-1258.
• ⦁ Söylemez, Ö.F., Ergen, B., 2020. Farklı Evrişimsel Sinir Ağı Mimarilerinin Yüz İfade Analizi Alanındaki Başarımlarının İncelenmesi. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 11(1), 123-133.
• ⦁ Fan, Z., Wu, Y., Lu, J., Li, W., 2018. Automatic Pavement Crack Detection Based on Structured Prediction with the Convolutional Neural Network. arXiv preprint arXiv:1802.02208.