A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Classification of Surface Defects on Steel Sheet Images Using DenseNet121 Architecture
Classifying surface defects is vital for steel sheet manufacturers. The conventional approaches have obtained moderate accuracies in terms of classifiers, while these methods have developed by depending on experts or different projects. DenseNet121 model, a machine-vision-based classification approach was proposed to overcome the drawbacks of traditional approaches. The goal of this paper is to apply pre-trained DenseNet121 network for classifying the steel defects categorized as rolled-in scales, patches, crazing, pitted surface, inclusion, and scratches. Fine-tuning transfer learning and k-fold cross-validation were implemented to train and evaluate the performance of the model. Additionally, this study uses Adaptive Moment Estimation (Adam) and Stochastic Gradient Descent (SGD) algorithms to optimize the model parameters. The testing result showed that all 5 folds were over 98.5% accuracy for both Adam and SGD optimizers. It also found that a gradient-weighted class activation mapping (Grad-CAM) was a good technique to visualize the surface failure locations of steel sheets. The findings indicated the ability of the proposed method to automatically classify the steel surface defect statuses.
Classification of Surface Defects on Steel Sheet Images Using DenseNet121 Architecture
Classifying surface defects is vital for steel sheet manufacturers. The conventional approaches have obtained moderate accuracies in terms of classifiers, while these methods have developed by depending on experts or different projects. DenseNet121 model, a machine-vision-based classification approach was proposed to overcome the drawbacks of traditional approaches. The goal of this paper is to apply pre-trained DenseNet121 network for classifying the steel defects categorized as rolled-in scales, patches, crazing, pitted surface, inclusion, and scratches. Fine-tuning transfer learning and k-fold cross-validation were implemented to train and evaluate the performance of the model. Additionally, this study uses Adaptive Moment Estimation (Adam) and Stochastic Gradient Descent (SGD) algorithms to optimize the model parameters. The testing result showed that all 5 folds were over 98.5% accuracy for both Adam and SGD optimizers. It also found that a gradient-weighted class activation mapping (Grad-CAM) was a good technique to visualize the surface failure locations of steel sheets. The findings indicated the ability of the proposed method to automatically classify the steel surface defect statuses.
Classification of Surface Defects on Steel Sheet Images Using DenseNet121 Architecture
Lecture Notes in Civil Engineering
Reddy, J. N. (editor) / Wang, Chien Ming (editor) / Luong, Van Hai (editor) / Le, Anh Tuan (editor) / Do, Tung-Lam (author) / Nguyen, Truong-Giang (author) / Nguyen, Khac-Quan (author) / Nguyen, Tan-No (author) / Nguyen, Nhut-Nhut (author)
The International Conference on Sustainable Civil Engineering and Architecture ; 2023 ; Da Nang City, Vietnam
2023-12-12
7 pages
Article/Chapter (Book)
Electronic Resource
English
Gradient Propagation Based DenseNet121 with ResNet50 Feature Extraction for Lymphoma Classification
| Springer Verlag | 2024
Classification of Defects in Underground Pipe Images Using Fuzzy Neural Networks
| British Library Conference Proceedings | 2001
Effect of Surface Defects on Quality of Phosphating Film on Electrogalvanized Steel Sheet
| British Library Online Contents | 2018
Cause and Preventive Measures of Hot Galvanized Steel Sheet Passivation Defects
| British Library Online Contents | 2013
The Classification of Weld Defects from Ultrasonic Images: A Neural Network Approach
| British Library Online Contents | 1993