基于特征金字塔匹配和自监督的表面缺陷检测

Surface-Defect Detection Based on Feature Pyramid Matching and Self-Supervision

针对传统表面缺陷检测无法适应工业复杂背景等问题,提出一种基于特征金字塔匹配和自监督的表面缺陷检测算法。首先,将两个基于通道注意力的残差网络提取的特征构成金字塔,根据网络各层输出的差异找到缺陷。其次,网络预训练的方式上采用了自我引导潜能(BYOL)自监督学习,经过自监督学习的网络可以提取通用特征,并提高缺陷检测方法的泛化性。最后,在遇到模糊图像时,采用基于不同分辨率的蒸馏训练来让学生网络充分学会提取图像的深度特征。对所提算法在3个数据集上进行了测试,实验结果证明,所提方法好于对照组,具有更高的缺陷检测精度。

To solve the problem of traditional surface defect detection’s inadaptability to a complex industrial background,a surfacedefect detection algorithm based on feature pyramid matching and selfsupervision is proposed.First,the features extracted from two ResNet networks based on channel attention are structured into a pyramid,which enables defect detection using the output differences of each layer of the network.Second,bootstrap your own latent(BYOL)selfsupervised learning is used in the training mode of the pretrained network;the network with selfsupervised learning can extract general features and improve the generalization of the defect detection method.Finally,for fuzzy images,distillation training based on different resolutions is used to let a student network fully learn to extract the depth features of images.The proposed algorithm is tested on three datasets.Experiments show that the proposed method is better than the control group and has a higher defect detection accuracy.