Guo Yijing, Zhong Linwei, Qiu Yi, Wang Huawei, Gao Fengqiang, Wen Zongheng, Zhan Choujun
School of Information Science and Technology, Xiamen University Tan Kah Kee College, Zhangzhou, 363105, China.
School of Informatics, Xiamen University, Xiamen, 361005, China.
Sci Rep. 2022 Jul 8;12(1):11604. doi: 10.1038/s41598-022-15855-7.
Surface defect detection is a vital process in industrial production and a significant research direction in computer vision. Although today's deep learning defect detection methods based on computer vision can achieve high detection accuracy, they are mainly based on supervised learning. They require many defect samples to train the model, which is not compatible with the current situation that industrial defect sample is difficult to obtain and costly to label. So we propose a new unsupervised small sample defect detection model-ISU-GAN, which is based on the CycleGAN architecture. A skip connection, SE module, and Involution module are added to the Generator, enabling the feature extraction capability of the model to be significantly improved. Moreover, we propose an SSIM-based defect segmentation method that applies to GAN-based defect detection and can accurately extract defect contours without the need for redundant noise reduction post-processing. Experiments on the DAGM2007 dataset show that the unsupervised ISU-GAN can achieve higher detection accuracy and finer defect profiles with less than 1/3 of the unlabelled training data than the supervised model with the full training set. Relative to the supervised segmentation models UNet and ResUNet++ with more training samples, our model improves the detection accuracy by 2.84% and 0.41% respectively and the F1 score by 0.025 and 0.0012 respectively. In addition, the predicted profile obtained using our method is closer to the real profile than other models used for comparison.
表面缺陷检测是工业生产中的一个重要过程，也是计算机视觉领域的一个重要研究方向。尽管如今基于计算机视觉的深度学习缺陷检测方法能够实现较高的检测精度，但它们主要基于监督学习。它们需要大量缺陷样本训练模型，这与当前工业缺陷样本难以获取且标注成本高昂的现状不相符。因此，我们提出了一种基于CycleGAN架构的新型无监督小样本缺陷检测模型——ISU-GAN。在生成器中添加了跳跃连接、SE模块和卷积模块，使得模型的特征提取能力得到显著提升。此外，我们提出了一种基于结构相似性（SSIM）的缺陷分割方法，该方法适用于基于生成对抗网络（GAN）的缺陷检测，无需进行冗余的降噪后处理就能准确提取缺陷轮廓。在DAGM2007数据集上的实验表明，无监督的ISU-GAN使用不到1/3的未标注训练数据，就能比使用完整训练集的监督模型实现更高的检测精度和更精细的缺陷轮廓。相对于具有更多训练样本的监督分割模型UNet和ResUNet++，我们的模型检测精度分别提高了2.84%和0.41%，F1分数分别提高了0.025和0.0012。此外，与其他用于比较的模型相比，使用我们的方法获得的预测轮廓更接近真实轮廓。
