缺陷检测是工业上非常重要的一个应用，由于缺陷多种多样，传统的机器视觉算法很难做到对缺陷特征完整的建模和迁移，复用性不大，要求区分工况，这会浪费大量的人力成本。深度学习在特征提取和定位上取得了非常好的效果，越来越多的学者和工程人员开始将深度学习算法引入到缺陷检测领域中。

 

本文介绍了几种深度学习算法在缺陷检测领域中的应用。

包括：

1、A fast and robust convolutional neural network-based defect detection model in product quality control

论文链接：https://link.springer.com/article/10.1007/s00170-017-0882-0

2、Automatic Defect Detection of Fasteners on the Catenary Support Device Using Deep Convolutional Neural Network

论文链接：https://ieeexplore.ieee.org/document/8126877

3、Automatic Fabric Defect Detection with a Multi-Scale Convolutional Denoising Autoencoder Network Model

论文链接：https://pubmed.ncbi.nlm.nih.gov/29614813/

4、An Unsupervised-Learning-Based Approach for Automated Defect Inspection on Textured Surfaces

论文链接：https://ieeexplore.ieee.org/document/8281622

5、Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks

论文链接：https://www.researchgate.net/publication/327494004_Automatic_Metallic_Surface_Defect_Detection_and_Recognition_with_Convolutional_Neural_Networks

6、Autonomous Structural Visual Inspection Using Region-Based Deep Learning for Detecting Multiple Damage Types

论文链接：https://onlinelibrary.wiley.com/doi/abs/10.1111/mice.12334

7、A Surface Defect Detection Method Based on Positive Samples

论文链接：https://link.springer.com/chapter/10.1007/978-3-319-97310-4_54

8、Segmentation-based deep-learning approach for surface-defect detection

论文链接：https://link.springer.com/article/10.1007/s10845-019-01476-x

 

内容中包含的图片若涉及版权问题，请及时与我们联系删除