Defect attention template generation cycleGAN for weakly supervised surface defect segmentation

Niu, Shuanlong; Li, Bin; Wang, Xinggang; He, Songping; Peng, Yaru

doi:10.1016/j.patcog.2021.108396

Cited by 23 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to recent studies, using GAN is becoming popular when discussing image-level annotations. Niu et al [174] designed a defects cycle-consistency loss to properly restore defect-free patterns in the image, by adding structural similarity to the original L1 loss function, to account for structural and texture of weak defects. Subsequently, the precise defective region is segmented by thresholding defect saliency map.…”

Section: A: Image-level Supervisionmentioning

confidence: 99%

Deep Learning for Automatic Vision-Based Recognition of Industrial Surface Defects: A Survey

et al. 2023

View full text Add to dashboard Cite

Automatic vision-based inspection systems have played a key role in product quality assessment for decades through the segmentation, detection, and classification of defects. Historically, machine learning frameworks, based on hand-crafted feature extraction, selection, and validation, counted on a combined approach of parameterized image processing algorithms and explicated human knowledge. The outstanding performance of deep learning (DL) for vision systems, in automatically discovering a feature representation suitable for the corresponding task, has exponentially increased the number of scientific articles and commercial products aiming at industrial quality assessment. In such a context, this article reviews more than 220 relevant articles from the related literature published until February 2023, covering the recent consolidation and advances in the field of fully-automatic DL-based surface defects inspection systems, deployed in various industrial applications. The analyzed papers have been classified according to a bi-dimensional taxonomy, that considers both the specific defect recognition task and the employed learning paradigm. The dependency on large and high-quality labeled datasets and the different neural architectures employed to achieve an overall perception of both well-visible and subtle defects, through the supervision of fine or/and coarse data annotations have been assessed. The results of our analysis highlight a growing research interest in defect representation power enrichment, especially by transferring pre-trained layers to an optimized network and by explaining the network decisions to suggest trustworthy retention or rejection of the products being evaluated.

show abstract

Section: A: Image-level Supervisionmentioning

confidence: 99%

Deep Learning for Automatic Vision-Based Recognition of Industrial Surface Defects: A Survey

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Similarly, [6] integrated industrial domain knowledge into GANs to augment data for less frequently occurring defect samples. To resolve the challenge of small-sample surface defect segmentation in industrial products, [16] presented the CycleGAN, which generates a unique defect-free template for each test image to accurately locate and segment the defect areas. However, it is widely acknowledged that the training regimen for GANs is notably demanding, often necessitating the expertise of seasoned machine learning specialists for meticulous hyperparameter tuning and neural architecture optimization.…”

Section: Generative Artificial Intelligence Frameworkmentioning

confidence: 99%

“…Owing to rapid advancements in generative Artificial Intelligence (AI) methods, such as Generative Adversarial Networks (GANs) [16,17], a plethora of innovative solutions have emerged for SDD methodologies that leverage generative AI. A segment of researchers is endeavoring to mitigate the scarcity of negative samples in SDD through the application of generative AI technologies.…”

Section: Introductionmentioning

confidence: 99%

Industrial Product Surface Defect Detection via the Fast Denoising Diffusion Implicit Model

wang,

Yang,

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

In the age of intelligent manufacturing, surface defect detection plays a pivotal role in the automated quality control of industrial products, constituting a fundamental aspect of smart factory evolution. Considering the diverse sizes and feature scales of surface defects on industrial products and the difficulty in procuring high-quality training samples, the achievement of real-time and high-quality surface defect detection through artificial intelligence technologies remains a formidable challenge. To address this, we introduce a defect detection approach grounded in the Fast Denoising Probabilistic Implicit Model. Firstly, we propose a noise predictor influenced by the spectral radius feature tensor of image. This enhancement augments the ability of generative model to capture nuanced details in non-defective areas, thus overcoming limitations in model versatility and detail portrayal. Furthermore, we present a loss function constraint based on the Perron root. This is designed to incorporate the constraint within the representational space, ensuring the denoising model consistently produces high-quality samples. Lastly, comprehensive experiments on both the Magnetic Tile and Market-PCB datasets, benchmarked against nine most representative models, underscore the exemplary detection efficacy of our proposed approach.

show abstract

“…Structural similarity index metric (SSIM) : This index has been extensively utilized to assess image quality [ 7 ] and has been used as loss function for numerous image processing applications [ 35 , 36 ] as well as for GAN-based solutions [ 32 , 37 , 38 ]. It was created under the presumption that the human visual system is extremely well suited for sifting through structural data in a visual input.…”

Section: Generating Synthesized Defective Images Via Cycleganmentioning

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

Defect attention template generation cycleGAN for weakly supervised surface defect segmentation

Cited by 23 publications

References 20 publications

Deep Learning for Automatic Vision-Based Recognition of Industrial Surface Defects: A Survey

Deep Learning for Automatic Vision-Based Recognition of Industrial Surface Defects: A Survey

Industrial Product Surface Defect Detection via the Fast Denoising Diffusion Implicit Model

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

Contact Info

Product

Resources

About