Crack Detection in Concrete Using Transfer Learning

Sharma, Nabin; Dhir, Ravindra K.; Rani, Radha

doi:10.37418/amsj.9.6.69

Cited by 7 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference [11] discusses the classical-classical transfer learning approach for crack classification on pre-trained networks such as AlexNet, GoogleNet and ResNet18, it compares the test accuracy of the above-mentioned pretrained models. Reference [12] presents a deep network to detect cracks employing a pixel-wise semantic segmentation and a fusion algorithm.…”

Section: Classification Using Classical Computingmentioning

confidence: 99%

Classical–Quantum Transfer Learning for Image Classification

et al. 2021

View full text Add to dashboard Cite

Classical-quantum transfer learning is a recent development in the field of quantum computing, which involves the modification of a pre-trained classical network and compounding it with a variational quantum circuit. This paper puts forward a quantum transfer learning-based approach for three different image classification tasks-classifying organic and recyclable from Trash, TB detection from chest X-ray images and detecting the presence of cracks from concrete crack images. The model used in this paper is a concatenation of pre-trained classical feature extractor with a quantum circuit as classifier. This paper compares the classification results obtained using various pre-trained networks such as VGG19, DenseNet169 and AlexNet, as feature extractors. From the obtained results, it is inferred that, DenseNet, Alexnet and VGG19 performs better in trash, TB and crack datasets, respectively. No model is the best for all the classification tasks, it is purely based on parameters such as dataset size, test-train split and learning rate.

show abstract

Section: Classification Using Classical Computingmentioning

confidence: 99%

Classical–Quantum Transfer Learning for Image Classification

et al. 2021

View full text Add to dashboard Cite

show abstract

Monitoring and Analysis of Surface Cracks in Concrete Using Convolutional Neural Network

Kapadia

Soneji²,

Rotti³

et al. 2022

Lecture Notes in Civil Engineering

View full text Add to dashboard Cite

Multi-layers deep learning model with feature selection for automated detection and classification of highway pavement cracks

Elghaish,

Matarneh,

Abdellatef

et al. 2024

SASBE

View full text Add to dashboard Cite

PurposeCracks are prevalent signs of pavement distress found on highways globally. The use of artificial intelligence (AI) and deep learning (DL) for crack detection is increasingly considered as an optimal solution. Consequently, this paper introduces a novel, fully connected, optimised convolutional neural network (CNN) model using feature selection algorithms for the purpose of detecting cracks in highway pavements.Design/methodology/approachTo enhance the accuracy of the CNN model for crack detection, the authors employed a fully connected deep learning layers CNN model along with several optimisation techniques. Specifically, three optimisation algorithms, namely adaptive moment estimation (ADAM), stochastic gradient descent with momentum (SGDM), and RMSProp, were utilised to fine-tune the CNN model and enhance its overall performance. Subsequently, the authors implemented eight feature selection algorithms to further improve the accuracy of the optimised CNN model. These feature selection techniques were thoughtfully selected and systematically applied to identify the most relevant features contributing to crack detection in the given dataset. Finally, the authors subjected the proposed model to testing against seven pre-trained models.FindingsThe study's results show that the accuracy of the three optimisers (ADAM, SGDM, and RMSProp) with the five deep learning layers model is 97.4%, 98.2%, and 96.09%, respectively. Following this, eight feature selection algorithms were applied to the five deep learning layers to enhance accuracy, with particle swarm optimisation (PSO) achieving the highest F-score at 98.72. The model was then compared with other pre-trained models and exhibited the highest performance.Practical implicationsWith an achieved precision of 98.19% and F-score of 98.72% using PSO, the developed model is highly accurate and effective in detecting and evaluating the condition of cracks in pavements. As a result, the model has the potential to significantly reduce the effort required for crack detection and evaluation.Originality/valueThe proposed method for enhancing CNN model accuracy in crack detection stands out for its unique combination of optimisation algorithms (ADAM, SGDM, and RMSProp) with systematic application of multiple feature selection techniques to identify relevant crack detection features and comparing results with existing pre-trained models.

show abstract

Crack Detection in Concrete Using Transfer Learning

Cited by 7 publications

References 0 publications

Classical–Quantum Transfer Learning for Image Classification

Classical–Quantum Transfer Learning for Image Classification

Monitoring and Analysis of Surface Cracks in Concrete Using Convolutional Neural Network

Multi-layers deep learning model with feature selection for automated detection and classification of highway pavement cracks

Contact Info

Product

Resources

About