School of Automation and Information Engineering, Sichuan University of Science and Engineering, Yibin 644000, China.
Artificial Intelligence Key Laboratory of Sichuan Province, Sichuan University of Science and Engineering, Yibin 644000, China.
Sensors (Basel). 2023 Jun 26;23(13):5922. doi: 10.3390/s23135922.
The surface defect detection of industrial products has become a crucial link in industrial manufacturing. It has a series of chain effects on the control of product quality, the safety of the subsequent use of products, the reputation of products, and production efficiency. However, in actual production, it is often difficult to collect defect image samples. Without a sufficient number of defect image samples, training defect detection models is difficult to achieve. In this paper, a defect image generation method DG-GAN is proposed for defect detection. Based on the idea of the progressive generative adversarial, D2 adversarial loss function, cyclic consistency loss function, a data augmentation module, and a self-attention mechanism are introduced to improve the training stability and generative ability of the network. The DG-GAN method can generate high-quality and high-diversity surface defect images. The surface defect image generated by the model can be used to train the defect detection model and improve the convergence stability and detection accuracy of the defect detection model. Validation was performed on two data sets. Compared to the previous methods, the FID score of the generated defect images was significantly reduced (mean reductions of 16.17 and 20.06, respectively). The YOLOX detection accuracy was significantly improved with the increase in generated defect images (the highest increases were 6.1% and 20.4%, respectively). Experimental results showed that the DG-GAN model is effective in surface defect detection tasks.
工业产品表面缺陷检测已成为工业制造中至关重要的环节。它对产品质量的控制、产品后续使用的安全性、产品的声誉和生产效率都有一系列连锁影响。然而，在实际生产中，往往难以收集到缺陷图像样本。如果没有足够数量的缺陷图像样本，训练缺陷检测模型就很难实现。本文提出了一种用于缺陷检测的缺陷图像生成方法 DG-GAN。该方法基于渐进式生成对抗的思想，引入了 D2 对抗损失函数、循环一致性损失函数、数据增强模块和自注意力机制，以提高网络的训练稳定性和生成能力。DG-GAN 方法可以生成高质量、高多样性的表面缺陷图像。模型生成的表面缺陷图像可用于训练缺陷检测模型，提高缺陷检测模型的收敛稳定性和检测精度。在两个数据集上进行了验证。与之前的方法相比，生成的缺陷图像的 FID 得分显著降低（分别平均降低 16.17 和 20.06）。随着生成的缺陷图像数量的增加，YOLOX 检测精度显著提高（最高分别提高了 6.1%和 20.4%）。实验结果表明，DG-GAN 模型在表面缺陷检测任务中是有效的。
