A Survey of Surface Defect Detection Based on Deep Learning

Yang, Wei

doi:10.2991/978-2-494069-51-0_51

Cited by 6 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The lack of defective datasets results in poor model training, which requires a model with strong generalization ability that can adapt to changes in different scenarios and maintain high detection accuracy and robustness. However, in practical applications, it is difficult to ensure good generalization ability of the model due to the quality and quantity of the dataset as well as the structure and parameters of the model, which leads to false detection or missed detection when the model is faced with new or unknown defects [13].…”

Section: Machine Vision Has Amentioning

confidence: 99%

PreCaCycleGAN: Perceptual Capsule Cyclic Generative Adversarial Network for Industrial Defective Sample Augmentation

Yang

Luan

et al. 2023

Electronics

View full text Add to dashboard Cite

Machine vision is essential for intelligent industrial manufacturing driven by Industry 4.0, especially for surface defect detection of industrial products. However, this domain is facing sparse and imbalanced defect data and poor model generalization, affecting industrial efficiency and quality. We propose a perceptual capsule cycle generative adversarial network (PreCaCycleGAN) for industrial defect sample augmentation, generating realistic and diverse defect samples from defect-free real samples. PreCaCycleGAN enhances CycleGAN with a U-Net and DenseNet-based generator to improve defect feature propagation and reuse and adds a perceptual loss function and a capsule network to improve authenticity and semantic information of generated features, enabling richer and more realistic global and detailed features of defect samples. We experiment on ten datasets, splitting each dataset into training and testing sets to evaluate model generalization across datasets. We train three defect detection models (YOLOv5, SSD, and Faster-RCNN) with original data and augmented data from PreCaCycleGAN and other state-of-the-art methods, such as CycleGAN-TSS and Tree-CycleGAN, and validate them on different datasets. Results show that PreCaCycleGAN improves detection accuracy and rate and reduces the false detection rate of detection models compared to other methods on different datasets, demonstrating its robustness and generalization under various defect conditions.

show abstract

Section: Machine Vision Has Amentioning

confidence: 99%