# Context
Automatic detection of the defect with no detectives samples often requires detecting them in Industrial anomaly detection
This dataset is for educational purposes

# Acknowledgements
Based on the public dataset by the MVTec company
Paul Bergmann, Michael Fauser, David Sattlegger, Carsten Steger. MVTec AD - A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection; in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019

# Inspiration
The main goal of this dataset is to explore self-supervised learning on capsule images in order to solve anomaly detection problems.