Mask2Defect: A Prior Knowledge-Based Data Augmentation Method for Metal Surface Defect Inspection

Yang, Benyi; Liu, Zhenyu; Duan, Guifang; Tan, Jianrong

doi:10.1109/tii.2021.3126098

Cited by 24 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of industrial images with surface defects, recently, several GAN-based methods have been proposed. One of these methods is Mask2Defect GAN [ 30 ], which proposes a GAN model to generate a large volume of surface defect images with different features and shapes. The algorithm separates the generation process into two steps: the first step uses the mask-to-defect construction network (M2DCNet) to render the defect details according to the binary mask, and the second step uses the fake-to-real domain transformation GAN (F2RDT-GAN) to add background textures and transform the synthesized defects from the rendered domain to the real defect domain.…”

Section: Related Workmentioning

confidence: 99%

Intraclass Image Augmentation for Defect Detection Using Generative Adversarial Neural Networks

Sampath

Maurtua

Martín

et al. 2023

Sensors

View full text Add to dashboard Cite

Surface defect identification based on computer vision algorithms often leads to inadequate generalization ability due to large intraclass variation. Diversity in lighting conditions, noise components, defect size, shape, and position make the problem challenging. To solve the problem, this paper develops a pixel-level image augmentation method that is based on image-to-image translation with generative adversarial neural networks (GANs) conditioned on fine-grained labels. The GAN model proposed in this work, referred to as Magna-Defect-GAN, is capable of taking control of the image generation process and producing image samples that are highly realistic in terms of variations. Firstly, the surface defect dataset based on the magnetic particle inspection (MPI) method is acquired in a controlled environment. Then, the Magna-Defect-GAN model is trained, and new synthetic image samples with large intraclass variations are generated. These synthetic image samples artificially inflate the training dataset size in terms of intraclass diversity. Finally, the enlarged dataset is used to train a defect identification model. Experimental results demonstrate that the Magna-Defect-GAN model can generate realistic and high-resolution surface defect images up to the resolution of 512 × 512 in a controlled manner. We also show that this augmentation method can boost accuracy and be easily adapted to any other surface defect identification models.

show abstract

Section: Related Workmentioning

confidence: 99%

Intraclass Image Augmentation for Defect Detection Using Generative Adversarial Neural Networks

Sampath

Maurtua

Martín

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Our scope covers basic image manipulations, including flipping, rotation, contrast, and noise injection, because those changes are typical of a manufacturing environment. Nevertheless, these methods only create data by imagelevel linear transformations and may not represent new distributions introduced by unknown defects with changes in the defects' shape or lighting orientations [27].…”

Section: Data Augmentationmentioning

confidence: 99%

Relational-based transfer learning for automatic optical inspection based on domain discrepancy

Salgado¹,

Yan

Hong

et al. 2023

Optoelectronic Imaging and Multimedia Technology IX

View full text Add to dashboard Cite

Transfer learning is a promising method for AOI applications since it can significantly shorten sample collection time and improve efficiency in today’s smart manufacturing. However, related research enhanced the network models by applying TL without considering the domain similarity among datasets, the data long-tailedness of a source dataset, and mainly used linear transformations to mitigate the lack of samples. This research applies relational-based TL via domain similarity to improve the overall performance and data augmentation in both target and source domains to enrich the data quality and reduce the imbalance. Given a group of source datasets from similar industrial processes, we define which group is the most related to the target through the domain discrepancy score and the number of samples each has. Then, we transfer the chosen pre-trained backbone weights to train and fine-tune the target network. Our research suggests increases in the F1 score and the PR curve up to 20% compared with TL using benchmark datasets.

show abstract

“…A defect transfer GAN (DT-GAN) was developed in [12] to produce realistic surface defect images. The Mask2Defect GAN was suggested in [13] to create surface defect images obtained from an automobile part stamping plan. A region-and strength-controllable GAN for creating synthesized defects in metal surfaces was also proposed in [14] based on the idea of image inpainting.…”

Section: Previous Work On Data Augmentation Using a Ganmentioning

confidence: 99%

Generating Defective Epoxy Drop Images for Die Attachment in Integrated Circuit Manufacturing via Enhanced Loss Function CycleGAN

Alam

Kehtarnavaz

2023

Sensors

View full text Add to dashboard Cite

In integrated circuit manufacturing, defects in epoxy drops for die attachments are required to be identified during production. Modern identification techniques based on vision-based deep neural networks require the availability of a very large number of defect and non-defect epoxy drop images. In practice, however, very few defective epoxy drop images are available. This paper presents a generative adversarial network solution to generate synthesized defective epoxy drop images as a data augmentation approach so that vision-based deep neural networks can be trained or tested using such images. More specifically, the so-called CycleGAN variation of the generative adversarial network is used by enhancing its cycle consistency loss function with two other loss functions consisting of learned perceptual image patch similarity (LPIPS) and a structural similarity index metric (SSIM). The results obtained indicate that when using the enhanced loss function, the quality of synthesized defective epoxy drop images are improved by 59%, 12%, and 131% for the metrics of the peak signal-to-noise ratio (PSNR), universal image quality index (UQI), and visual information fidelity (VIF), respectively, compared to the CycleGAN standard loss function. A typical image classifier is used to show the improvement in the identification outcome when using the synthesized images generated by the developed data augmentation approach.

show abstract

Mask2Defect: A Prior Knowledge-Based Data Augmentation Method for Metal Surface Defect Inspection

Cited by 24 publications

References 27 publications

Intraclass Image Augmentation for Defect Detection Using Generative Adversarial Neural Networks

Intraclass Image Augmentation for Defect Detection Using Generative Adversarial Neural Networks

Relational-based transfer learning for automatic optical inspection based on domain discrepancy

Generating Defective Epoxy Drop Images for Die Attachment in Integrated Circuit Manufacturing via Enhanced Loss Function CycleGAN

Contact Info

Product

Resources

About