当前位置: X-MOL 学术J. Circuits Syst. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Attention U-Net with Feature Fusion Module for Robust Defect Detection
Journal of Circuits, Systems and Computers ( IF 1.5 ) Pub Date : 2021-05-25 , DOI: 10.1142/s0218126621502728
Yu-Jie Xiong 1 , Yong-Bin Gao 1 , Hong Wu 2 , Yao Yao 2
Affiliation  

U-Net shows a remarkable performance and makes significant progress for segmentation task in medical images. Despite the outstanding achievements, the common case of defect detection in industrial scenes is still a challenging task, due to the noisy background, unpredictable environment, varying shapes and sizes of the defects. Traditional U-Net may not be suitable for low-quality images with low illumination and corruption, which are often presented in the practical collections in real-world scenes. In this paper, we propose an attention U-Net with feature fusion module for combining multi-scale features to detect the defects in noisy images automatically. Feature fusion module contains convolution kernels of different scales to capture shallow layer features and combine them with the high-dimensional features. Meanwhile, attention gates are used to enhance the robustness of skip connection between the feature maps. The proposed method is evaluated on two datasets. The best precision rate and MIoU of defect detection are 95.6% and 92.5%. The best F-score of concrete crack detection is 95.0%. Experimental results show that the proposed approach achieves promising results in both datasets. It demonstrates that our approach consistently outperforms other U-Net-based approaches for defect detection in low-quality images. Experimental results have shown the possibility of developing a mixture system that can be deployed in many applications, such as remote sensing image analysis, earthquake disaster situation assessment, and so on.

中文翻译:

带有特征融合模块的注意力 U-Net 用于鲁棒缺陷检测

U-Net 表现出卓越的性能,并在医学图像的分割任务上取得了重大进展。尽管取得了显著成绩,但由于背景嘈杂、环境不可预测、缺陷的形状和大小各不相同,工业场景中的常见缺陷检测仍然是一项具有挑战性的任务。传统的 U-Net 可能不适用于低照度和损坏的低质量图像,这些图像经常出现在现实世界场景的实际集合中。在本文中,我们提出了一种带有特征融合模块的注意力 U-Net,用于结合多尺度特征来自动检测噪声图像中的缺陷。特征融合模块包含不同尺度的卷积核来捕获浅层特征并将它们与高维特征结合。同时,注意门用于增强特征图之间跳过连接的鲁棒性。所提出的方法在两个数据集上进行评估。缺陷检测的最佳准确率和MIoU分别为95.6%和92.5%。混凝土裂缝检测的最佳 F 分数为 95.0%。实验结果表明,所提出的方法在两个数据集中都取得了可喜的结果。它表明我们的方法始终优于其他基于 U-Net 的低质量图像缺陷检测方法。实验结果表明,开发一种可以部署在许多应用中的混合系统是可能的,例如遥感图像分析、地震灾害情况评估等。缺陷检测的最佳准确率和MIoU分别为95.6%和92.5%。混凝土裂缝检测的最佳 F 分数为 95.0%。实验结果表明,所提出的方法在两个数据集中都取得了可喜的结果。它表明我们的方法始终优于其他基于 U-Net 的低质量图像缺陷检测方法。实验结果表明,开发一种可以部署在许多应用中的混合系统是可能的,例如遥感图像分析、地震灾害情况评估等。缺陷检测的最佳准确率和MIoU分别为95.6%和92.5%。混凝土裂缝检测的最佳 F 分数为 95.0%。实验结果表明,所提出的方法在两个数据集中都取得了可喜的结果。它表明我们的方法始终优于其他基于 U-Net 的低质量图像缺陷检测方法。实验结果表明,开发一种可以部署在许多应用中的混合系统是可能的,例如遥感图像分析、地震灾害情况评估等。它表明我们的方法始终优于其他基于 U-Net 的低质量图像缺陷检测方法。实验结果表明,开发一种可以部署在许多应用中的混合系统是可能的,例如遥感图像分析、地震灾害情况评估等。它表明我们的方法始终优于其他基于 U-Net 的低质量图像缺陷检测方法。实验结果表明,开发一种可以部署在许多应用中的混合系统是可能的,例如遥感图像分析、地震灾害情况评估等。
更新日期:2021-05-25
down
wechat
bug