A Generic Deep-Learning-Based Approach for Automated Surface Inspection

By Ruoxu Ren, Terence Hung, Kay Chen Tan. IEEE Transactions on Cybernetics, 2018

422 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/1d2105616d122389efbd1b0ac7c04c0c2f8ac996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Yu He
2. Q. Meng
3. Yunhui Yan
4. Kechen Song
5. Liang Gao
6. Xinyu Li
7. Long Wen
8. Xun Cheng

In Computer Vision and Pattern Recognition

1. Yu He
2. Q. Meng
3. Yunhui Yan
4. Kechen Song
5. Xiao Fu
6. Liang Gao
7. Hongwen Dong
8. Xiaoming Lv

In Industrial and Manufacturing Engineering

1. Yu He
2. Q. Meng
3. Long Wen
4. Xinyu Li
5. Yunhui Yan
6. Kechen Song
7. Liang Gao
8. Xun Cheng

Citations in the corpus

• An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features (2020, methodology): “[17] perform an extra defect segmentation task on classification results to define the boundary of a defect.”
• A transfer convolutional neural network for fault diagnosis based on ResNet-50 (2019, methodology): “Ren et al. [35] applied the feature transferring based on Decaf for automatically surface inspection.”
• Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks (2018, methodology): “The traditional image processing method uses the primitive attributes reflected by local anomalies to detect and segment defects, which can be further divided into the structural method, threshold method, spectral method, and model-based method [11].”
• PGA-Net: Pyramid Feature Fusion and Global Context Attention Network for Automated Surface Defect Detection (2020, background): “[37] proposed a deep-learning-based framework for defect classifi-cation, then obtain the pixel-wise prediction through the trained classifier convoluted with raw image.”
• Automated Visual Defect Detection for Flat Steel Surface: A Survey (2020, methodology): “[115] proposed a general approach requiring small training data for automated surface inspection.”
• Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network (2020, background): “Traditional image processing techniques extract hand-crafted features to describe and detect defects, which can be mainly divided into four categories: structural-based, threshold-based, spectral-based, and model-based methods [7].”