Anomaly Detection Neural Network with Dual Auto-Encoders GAN and Its Industrial Inspection Applications

Recently, researchers have been studying methods to introduce deep learning into automated optical inspection (AOI) systems to reduce labor costs. However, the integration of deep learning in the industry may encounter major challenges such as sample imbalance (defective products that only account for a small proportion). Therefore, in this study, an anomaly detection neural network, dual auto-encoder generative adversarial network (DAGAN), was developed to solve the problem of sample imbalance. With skip-connection and dual auto-encoder architecture, the proposed method exhibited excellent image reconstruction ability and training stability. Three datasets, namely public industrial detection training set, MVTec AD, with mobile phone screen glass and wood defect detection datasets, were used to verify the inspection ability of DAGAN. In addition, training with a limited amount of data was proposed to verify its detection ability. The results demonstrated that the areas under the curve (AUCs) of DAGAN were better than previous generative adversarial network-based anomaly detection models in 13 out of 17 categories in these datasets, especially in categories with high variability or noise. The maximum AUC improvement was 0.250 (toothbrush). Moreover, the proposed method exhibited better detection ability than the U-Net auto-encoder, which indicates the function of discriminator in this application. Furthermore, the proposed method had a high level of AUCs when using only a small amount of training data. DAGAN can significantly reduce the time and cost of collecting and labeling data when it is applied to industrial detection.

[1]  Yung-Nien Sun,et al.  A new model-based approach for industrial visual inspection , 1992, Pattern Recognit..

[2]  Georg Langs,et al.  Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery , 2017, IPMI.

[3]  David Berthelot,et al.  BEGAN: Boundary Equilibrium Generative Adversarial Networks , 2017, ArXiv.

[4]  Bernd Scholz-Reiter,et al.  Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection , 2016 .

[5]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[7]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[9]  Abhijit Mahalanobis,et al.  Attention Guided Anomaly Localization in Images , 2020, ECCV.

[10]  See-Kiong Ng,et al.  Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series , 2018, ArXiv.

[11]  Hayit Greenspan,et al.  GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification , 2018, Neurocomputing.

[12]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Toby P. Breckon,et al.  Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[14]  Yi Yang,et al.  Random Erasing Data Augmentation , 2017, AAAI.

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

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

[17]  Hongwei Liu,et al.  Convolutional Neural Network With Data Augmentation for SAR Target Recognition , 2016, IEEE Geoscience and Remote Sensing Letters.

[18]  Ye Han,et al.  A CNN-Based Defect Inspection Method for Catenary Split Pins in High-Speed Railway , 2019, IEEE Transactions on Instrumentation and Measurement.

[19]  Ke Li,et al.  Double Encoder Conditional GAN for Facial Expression Synthesis , 2018, 2018 37th Chinese Control Conference (CCC).

[20]  Hyung-Jo Jung,et al.  Diagnosis of crack damage on structures based on image processing techniques and R-CNN using unmanned aerial vehicle (UAV) , 2018, Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[21]  Lei Shi,et al.  MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks , 2019, ICANN.

[22]  Xiaohua Zhai,et al.  The GAN Landscape: Losses, Architectures, Regularization, and Normalization , 2018, ArXiv.

[23]  Ajay Kumar,et al.  Computer-Vision-Based Fabric Defect Detection: A Survey , 2008, IEEE Transactions on Industrial Electronics.

[24]  Carsten Steger,et al.  MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Toby P. Breckon,et al.  GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training , 2018, ACCV.

[26]  Ian Goodfellow,et al.  Generative adversarial networks , 2020, Commun. ACM.

[27]  R.P. Kruger,et al.  A technical and economic assessment of computer vision for industrial inspection and robotic assembly , 1981, Proceedings of the IEEE.

[28]  Syed Aziz Shah,et al.  Respiration Symptoms Monitoring in Body Area Networks , 2018 .

[29]  Cewu Lu,et al.  Inverse-Transform AutoEncoder for Anomaly Detection , 2019, ArXiv.

[30]  Paul Bergmann,et al.  Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Mohammad R. Jahanshahi,et al.  NB-CNN: Deep Learning-Based Crack Detection Using Convolutional Neural Network and Naïve Bayes Data Fusion , 2018, IEEE Transactions on Industrial Electronics.