Pixel-Wise Defect Detection by CNNs without Manually Labeled Training Data

References

• Alimohamadi, H., A. Ahmadyfard, and E. Shojaee. 2009. Defect detection in textiles using morphological analysis of optimal gabor wavelet filter response. 2009 International Conference on Computer and Automation Engineering, 26–30. IEEE. doi:10.1109/ICCAE.2009.43.
   Google Scholar
• Ayad, A., M. Shaban, and W. Gabriel. 2017. Unsupervised Anomaly Detection with Generative Adversarial Networks on MIAS dataset. Accessed June 11 , 2018. https://github.com/xtarx/Unsupervised-Anomaly-Detection-with-Generative-Adversarial-Networks.
   Google Scholar
• Bodnarova, A., J. A. Williams, M. Bennamoun, and K. K. Kubik. 1997. Optimal textural features for flaw detection in textile materials. Proceedings of IEEE TENCON '97 - Brisbane, Australia. IEEE Region 10 Annual Conference. Speech and Image Technologies for Computing and Telecommunications, ed. M. Deriche, M. Moody and M. Bennamoun, 307–10. New York, NY, USA, IEEE. doi:10.1109/TENCON.1997.647318.
   Google Scholar
• Chandola, V., A. Banerjee, and V. Kumar. 2009. Anomaly detection: A survey. ACM Computing Surveys 41: doi: 10.1145/1541880.1541882.
   Web of Science ®Google Scholar
• Chicco, D. 2017. Ten quick tips for machine learning in computational biology. BioData Mining 10:35. doi:10.1186/s13040-017-0155-3.
   PubMed Web of Science ®Google Scholar
• Choudhury, D. K., and S. Dash. 2018. Defect detection of fabrics by grey-level co-occurrence matrix and artificial neural network. In Handbook of research on modeling, analysis, and application of nature-inspired metaheuristic algorithms, 285–97. doi:10.4018/978-1-5225-2857-9.ch014.
   Google Scholar
• Davis, J., and M. Goadrich. 2006. The relationship between precision-recall and ROC curves. Proceedings of the 23rd international conference on machine learning - ICML ’06, ed. W. Cohen and A. Moore, 233–40. New York, NY: ACM Press. doi:10.1145/1143844.1143874.
   Google Scholar
• Haselmann, M., and D. Gruber. 2017. Supervised machine learning based surface inspection by synthetizing artificial defects. 2017 16th IEEE international conference on machine learning and applications (ICMLA), 390–95. IEEE. doi:10.1109/ICMLA.2017.0-130.
   Google Scholar
• Haselmann, M., and D. P. Gruber. 2016. Anomaly detection on arbitrarily distorted 2D patterns by computation of a virtual golden sample. 2016 IEEE international conference on image processing (ICIP), 4398–402. IEEE. doi:10.1109/ICIP.2016.7533191.
   Google Scholar
• Haselmann, M., D. P. Gruber, and P. Tabatabai. 2018. Anomaly Detection Using Deep Learning Based Image Completion, International Conference on Machine Learning and Applications (ICMLA) - Orlando, Florida, USA. 1237–1242. New York, NY, USA, IEEE. doi:10.1109/ICMLA.2018.00201
   Google Scholar
• Huang, S.-H., and Y.-C. Pan. 2014. Automated visual inspection in the semiconductor industry: A survey. Computers in Industry 66:1–10. doi:10.1016/j.compind.2014.10.006.
   Web of Science ®Google Scholar
• Iivarinen, J. 2000. Surface defect detection with histogram-based texture features. In Intelligent robots and computer vision XIX: algorithms, techniques and active vision, ed. D. P. Casasent. 140–45. Bellingham, Washington, USA, SPIE. doi:10.1117/12.403757.
   Google Scholar
• Iivarinen, J., J. Rauhamaa, and A. Visa. 1996. Unsupervised segmentation of surface defects. Proceedings of 13th international conference on pattern recognition, vol. 4, 356–60. IEEE. doi:10.1109/ICPR.1996.547445.
   Google Scholar
• Jeni, L. A., J. F. Cohn, and F. de La Torre. 2013. Facing imbalanced data: recommendations for the use of performance metrics. International conference on affective computing and intelligent interaction and workshops: [proceedings]. ACII (conference) 2013, 245–51. doi:10.1109/ACII.2013.47.
   Google Scholar
• Kholief, E. A., S. H. Darwish, and N. Fors. 2017. Detection of steel surface defect based on machine learning using deep auto-encoder network. In Industrial engineering and operations management, ed. A. Ali and I. Kissani. IEOM Society. 218–29.
   Google Scholar
• Kwon, D., H. Kim, J. Kim, S. C. Suh, I. Kim, and K. J. Kim. 2017. A survey of deep learning-based network anomaly detection. Cluster Computing 9:205. doi:10.1007/s10586-017-1117-8.
   Google Scholar
• Long, J., E. Shelhamer, and T. Darrell. 2015. Fully convolutional networks for semantic segmentation. Conference of computer vision and pattern recognition (CVPR) - Boston, MA, USA, 1–8. New York, NY, USA, IEEE. doi:10.1109/CVPR.2015.7298965
   Google Scholar
• Matthews, B. W. 1975. Comparison of the predicted and observed secondary structure of T4 phage lysozyme, Biochimica et Biophysica Acta (BBA). Protein Structure 405:442–51. doi:10.1016/0005-2795(75)90109-9.
   Google Scholar
• Mei, S., Y. Wang, and G. Wen. 2018. Automatic fabric defect detection with a multi-scale convolutional denoising autoencoder network model. Sensors (Basel, Switzerland) 18:1064. doi:10.3390/s18041064.
   PubMed Web of Science ®Google Scholar
• Neogi, N., D. K. Mohanta, and P. K. Dutta. 2014. Review of vision-based steel surface inspection systems. EURASIP Journal on Image and Video Processing 50:3. doi:10.1186/1687-5281-2014-50.
   Google Scholar
• Ng, H.-F. 2006. Automatic thresholding for defect detection. Pattern Recognition Letters 27:1644–49. doi:10.1016/j.patrec.2006.03.009.
   Web of Science ®Google Scholar
• Pimentel, M. A., D. A. Clifton, L. Clifton, and L. Tarassenko. 2014. A review of novelty detection. Signal Processing 99:215–49. doi:10.1016/j.sigpro.2013.12.026.
   Web of Science ®Google Scholar
• Ralló, M., M. S. Millán, and J. Escofet. 2009. Unsupervised novelty detection using gabor filters for defect segmentation in textures. Journal of the Optical Society of America A 26:1967. doi:10.1364/JOSAA.26.001967.
   Google Scholar
• Richter, S. R., V. Vineet, S. Roth, and V. Koltun, Playing for data: ground truth from computer games, 2016. Accessed http://arxiv.org/pdf/1608.02192v1.
   Google Scholar
• Schlegl, T., P. Seeböck, S. M. Waldstein, U. Schmidt-Erfurth, and G. Langs. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery, 2017. Accessed: http://arxiv.org/pdf/1703.05921v1.
   Google Scholar
• Theiler, J. P., and D. M. Cai. 2003. Resampling approach for anomaly detection in multispectral images. SPIE proceedings, Proc. SPIE 5093, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery IX - Orlando, Florida, USA, ed. S. S. Shen and P. E. Lewis, 230. SPIE. doi:10.1117/12.487069.
   Google Scholar
• Tsai, D.-M., S.-T. Chuang, and Y.-H. Tseng. 2007. One-dimensional-based automatic defect inspection of multiple patterned TFT-LCD panels using Fourier image reconstruction. International Journal of Production Research 45:1297–321. doi:10.1080/00207540600622464.
   Web of Science ®Google Scholar
• Xie, X. 2008. A review of recent advances in surface defect detection using texture analysis techniques. Electronic Letters on Computer Vision and Image Analysis 7:1–22. doi:10.5565/rev/elcvia.268.
   Google Scholar
• Xu, J., L. Xiang, Q. Liu, H. Gilmore, J. Wu, J. Tang, and A. Madabhushi. 2016. Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images. IEEE Transactions on Medical Imaging 35:119–30. doi:10.1109/TMI.2015.2458702.
   PubMed Web of Science ®Google Scholar
• Zhang, M., J. Wu, H. Lin, P. Yuan, and Y. Song. 2017. The application of one-class classifier based on CNN in image defect detection. Procedia Computer Science 114:341–48. doi:10.1016/j.procs.2017.09.040.
   Google Scholar