2020
DOI: 10.1007/s10845-020-01710-x
|View full text |Cite
|
Sign up to set email alerts
|

Synthetic data augmentation for surface defect detection and classification using deep learning

Abstract: Deep learning techniques, especially Convolutional Neural Networks (CNN), dominate the benchmarks for most computer vision tasks. These state-of-the-art results are typically obtained through supervised learning, for which large annotated datasets are required. However, acquiring such datasets for manufacturing applications remains a challenging proposition due to the time and costs involved in their collection. To overcome this disadvantage, a novel framework is proposed for data augmentation by creating synt… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

2
43
0
1

Year Published

2021
2021
2023
2023

Publication Types

Select...
5
4
1

Relationship

0
10

Authors

Journals

citations
Cited by 139 publications
(46 citation statements)
references
References 33 publications
2
43
0
1
Order By: Relevance
“…However, this system has few limitation, since the synthetic defect data were generated based on the knowledge of the experts, the classifier fails to detect unknown defects. Jain et al [9] suggested a data augmentation method using Generative adversarial networks to generate synthetic data then they used Convolutional Neural Network to classify surface defects in hot-rolled steel strips . Shon et al [10] proposed automatic data augmentation with : rotation, flipping, shifting, shearing range, and zooming techniques and deep learning method to identify defects of wafer.…”
Section: Defect Detection Methods With Data Augmentationmentioning
confidence: 99%
“…However, this system has few limitation, since the synthetic defect data were generated based on the knowledge of the experts, the classifier fails to detect unknown defects. Jain et al [9] suggested a data augmentation method using Generative adversarial networks to generate synthetic data then they used Convolutional Neural Network to classify surface defects in hot-rolled steel strips . Shon et al [10] proposed automatic data augmentation with : rotation, flipping, shifting, shearing range, and zooming techniques and deep learning method to identify defects of wafer.…”
Section: Defect Detection Methods With Data Augmentationmentioning
confidence: 99%
“…By generating artificial data that are similar to the original data, and thus augmenting the training dataset, GANs can be used for data augmentation. GANs, for example, in the papers by Shao et al [22], Ortego et al [19], and more recently in Jain et al [12] are intended to produce realistic synthesized signals with labels for further use in machine fault diagnosis. A limitation of such methods is that all augmented samples produced may not be physically plausible and may show unrealistic artifacts.…”
Section: Background and Related Work 21 Small Sample ML And Data Augm...mentioning
confidence: 99%
“…Therefore they trained their GAN with 2000 original images. Jain et al (2020) evaluated different GAN based techniques for augmenting an image dataset for training a CNN classifier for the detection of defects on metallic surfaces. They first applied a Geometrical Transformation to generate a set of 9000 images.…”
Section: Review On Training Data Sets From Related Researchmentioning
confidence: 99%