Surface defects inspection of cylindrical metal workpieces based on weakly supervised learning

In industrial vision system, metal surface is anisotropic under light in all directions and it is inevitable to cause local overexposure due to the natural reflection of active strong light, especially on the cylindrical metal surface. In this paper, injector valve is taken as the representative of cylindrical metal workpieces. Since the variety and complexity of cylindrical metal workpieces defects, and its contrast with the background of workpieces fluctuates, making samples annotating time-consuming and be of high cost. In order to solve the above challenges, this paper proposes an end-to-end weakly supervised learning framework to classify and segment defects. Firstly, a deep integrated residual attention convolutional neural network (IRA-CNN) is designed. IRA-CNN is composed of multiple IRA-Block. Two residual maps are included in IRA-Block to improve its bilateral nonlinearity and the robustness. IRA-block adds integrated attention module (IAM) which includes channel attention submodule and spatial attention submodule. The channel attention submodule adaptively extracts information from the global average pool layer and the global maximum pool layer to obtain the channel attention feature map. IAM can be well integrated into the IRA-CNN makes the neural network suppress the interference of useless background area and highlight the defect area. Finally, the weakly supervised segmentation method relies on Grad-CAM++ to generate saliency map to improve segmentation accuracy. The experimental results show that the accuracy of defect classification reaches 97.7\% and the segmentation accuracy is significantly improved compared with the benchmark method in the injector valve dataset which include 6747 images.

[1]  Kun Liu,et al.  Solar cell surface defect inspection based on multispectral convolutional neural network , 2018, Journal of Intelligent Manufacturing.

[2]  Q. M. Jonathan Wu,et al.  Salient object detection via multi-scale attention CNN , 2018, Neurocomputing.

[3]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.

[5]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[6]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Liu Zhoufeng,et al.  AdaBoost learning for fabric defect detection based on HOG and SVM , 2011, 2011 International Conference on Multimedia Technology.

[8]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[9]  Yixin Yin,et al.  Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network , 2018 .

[10]  Xinggang Wang,et al.  Automated defect inspection of LED chip using deep convolutional neural network , 2019, J. Intell. Manuf..

[11]  Lin Tang,et al.  Polycrystalline silicon wafer defect segmentation based on deep convolutional neural networks , 2020, Pattern Recognit. Lett..

[12]  Xiuxi Li,et al.  A Weakly Supervised Surface Defect Detection Based on Convolutional Neural Network , 2020, IEEE Access.

[13]  Kay Chen Tan,et al.  A Generic Deep-Learning-Based Approach for Automated Surface Inspection , 2018, IEEE Transactions on Cybernetics.

[14]  Xiongbin Wu,et al.  SDD-CNN: Small Data-Driven Convolution Neural Networks for Subtle Roller Defect Inspection , 2019, Applied Sciences.

[15]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[17]  J. Tomas,et al.  A deep learning-based model for defect detection in laser-powder bed fusion using in-situ thermographic monitoring , 2020, Progress in Additive Manufacturing.

[18]  Jack Chin Pang Cheng,et al.  A unified convolutional neural network integrated with conditional random field for pipe defect segmentation , 2019, Comput. Aided Civ. Infrastructure Eng..

[19]  Jure Skvarč,et al.  Segmentation-based deep-learning approach for surface-defect detection , 2019, Journal of Intelligent Manufacturing.

[20]  Rytis Augustauskas,et al.  Improved Pixel-Level Pavement-Defect Segmentation Using a Deep Autoencoder , 2020, Sensors.

[21]  Ivan Jordanov,et al.  Feature selection for surface defect classification of extruded aluminum profiles , 2016 .

[22]  De Xu,et al.  Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks , 2018, Applied Sciences.

[23]  Dong-Joong Kang,et al.  Fast defect detection for various types of surfaces using random forest with VOV features , 2015 .

[24]  Chang Ouk Kim,et al.  Convolutional Neural Network for Wafer Surface Defect Classification and the Detection of Unknown Defect Class , 2019, IEEE Transactions on Semiconductor Manufacturing.

[25]  Binyi Su,et al.  BAF-Detector: An Efficient CNN-Based Detector for Photovoltaic Solar Cell Defect Detection , 2020, ArXiv.

[26]  Vineeth N. Balasubramanian,et al.  Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[27]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[28]  Yunhui Yan,et al.  A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects , 2013 .

[29]  Kun Liu,et al.  A robust weakly supervised learning of deep Conv-Nets for surface defect inspection , 2020, Neural Computing and Applications.

[30]  Enhua Wu,et al.  Squeeze-and-Excitation Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.