CNN Training with Twenty Samples for Crack Detection via Data Augmentation

Wang, Zirui; Yang, Jingjing; Jiang, Haonan; Fan, Xueling

doi:10.3390/s20174849

Cited by 26 publications

(16 citation statements)

References 26 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Image-based method implemented with artificial intelligence algorithms [17][18][19] was also widely performed for crack detection in industry non-destructive testing for the purpose of automation. Unfortunately, the accuracy of such methods may strongly depend on the amount of the training data, which was impractical for the clinical crack tooth diagnosis.…”

Section: Introductionmentioning

confidence: 99%

A method of crack detection based on digital image correlation for simulated cracked tooth

Zhang

Guo

et al. 2021

BMC Oral Health

View full text Add to dashboard Cite

Background Early clinical cracked tooth can be a perplexing disorder to diagnose and manage. One of the key problems for the diagnosis of the cracked tooth is the detection of the location of the surface crack. Methods This paper proposes an image-based method for the detection of the micro-crack in the simulated cracked tooth. A homemade three-axis motion platform mounted with a telecentric lens was built as an image acquisition system to observe the surface of the simulated cracked tooth, which was under compression with a magnitude of the masticatory force. By using digital image correlation (DIC), the deformation map for the crown surface of the cracked tooth was calculated. Through image analysis, the micro-crack was quantitatively visualized and characterized. Results The skeleton of the crack path was successfully extracted from the image of the principal strain field, which was further verified by the image from micro-CT. Based on crack kinematics, the crack opening displacement was quantitatively calculated to be 2–10 µm under the normal mastication stress, which was in good agreement with the value reported in the literature. Conclusions The crack on the surface of the simulated cracked tooth could be detected based on the proposed DIC-based method. The proposed method may provide a new solution for the rapid clinical diagnosis of cracked teeth and the calculated crack information would be helpful for the subsequent clinical treatment of cracked teeth.

show abstract

Section: Introductionmentioning

confidence: 99%

A method of crack detection based on digital image correlation for simulated cracked tooth

Zhang

Guo

et al. 2021

BMC Oral Health

View full text Add to dashboard Cite

show abstract

“…Ali et al proposed a customized convolutional neural network for crack detection in concrete structures, which can achieve higher crack detection accuracy [ 31 ]. In [ 32 ], a two-stage data enhancement method was used to construct a CNN-based crack detector. The results show that the crack detector with two-stage data enhancement training on a small dataset has a better crack detection effect.…”

Section: Related Workmentioning

confidence: 99%

Automatic Pixel-Level Pavement Crack Recognition Using a Deep Feature Aggregation Segmentation Network with a scSE Attention Mechanism Module

Qiao

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

Pavement crack detection is essential for safe driving. The traditional manual crack detection method is highly subjective and time-consuming. Hence, an automatic pavement crack detection system is needed to facilitate this progress. However, this is still a challenging task due to the complex topology and large noise interference of crack images. Recently, although deep learning-based technologies have achieved breakthrough progress in crack detection, there are still some challenges, such as large parameters and low detection efficiency. Besides, most deep learning-based crack detection algorithms find it difficult to establish good balance between detection accuracy and detection speed. Inspired by the latest deep learning technology in the field of image processing, this paper proposes a novel crack detection algorithm based on the deep feature aggregation network with the spatial-channel squeeze & excitation (scSE) attention mechanism module, which calls CrackDFANet. Firstly, we cut the collected crack images into 512 × 512 pixel image blocks to establish a crack dataset. Then through iterative optimization on the training and validation sets, we obtained a crack detection model with good robustness. Finally, the CrackDFANet model verified on a total of 3516 images in five datasets with different sizes and containing different noise interferences. Experimental results show that the trained CrackDFANet has strong anti-interference ability, and has better robustness and generalization ability under the interference of light interference, parking line, water stains, plant disturbance, oil stains, and shadow conditions. Furthermore, the CrackDFANet is found to be better than other state-of-the-art algorithms with more accurate detection effect and faster detection speed. Meanwhile, our algorithm model parameters and error rates are significantly reduced.

show abstract

“…This is because, the generation of artificial images directly contributes to increase the capacity for the generalization of the Deep Learning model and thus decrease the chance of overfitting [ 4 , 9 ]. In this respect, one of the challenges of using Data Augmentation is the definition of which transformations (such as zoom, rotation, flip) will be applied to the images [ 6 , 28 , 34 , 44 , 48 ]. In terms of Machine Learning, this problem can be treated as in the area of Hyperparameter Tuning [ 19 , 20 , 27 , 30 , 31 , 39 , 40 ].…”

Section: Introductionmentioning

confidence: 99%

Tuning of data augmentation hyperparameters in deep learning to building construction image classification with small datasets

Ottoni

Amorim

Novo

et al. 2022

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Deep Learning methods have important applications in the building construction image classification field. One challenge of this application is Convolutional Neural Networks adoption in a small datasets. This paper proposes a rigorous methodology for tuning of Data Augmentation hyperparameters in Deep Learning to building construction image classification, especially to vegetation recognition in facades and roofs structure analysis. In order to do that, Logistic Regression models were used to analyze the performance of Convolutional Neural Networks trained from 128 combinations of transformations in the images. Experiments were carried out with three architectures of Deep Learning from the literature using the Keras library. The results show that the recommended configuration (Height Shift Range = 0.2; Width Shift Range = 0.2; Zoom Range =0.2) reached an accuracy of in the test step of first case study. In addition, the hyperparameters recommended by proposed method also achieved the best test results for second case study: .

show abstract

CNN Training with Twenty Samples for Crack Detection via Data Augmentation

Cited by 26 publications

References 26 publications

A method of crack detection based on digital image correlation for simulated cracked tooth

A method of crack detection based on digital image correlation for simulated cracked tooth

Automatic Pixel-Level Pavement Crack Recognition Using a Deep Feature Aggregation Segmentation Network with a scSE Attention Mechanism Module

Tuning of data augmentation hyperparameters in deep learning to building construction image classification with small datasets

Contact Info

Product

Resources

About