Use pre-trained AlexNet and 1-class SVM for anomaly detection
https://github.com/mathworks/Deep-Learning-Image-anomaly-detection-for-production-line
You are now following this Submission
- You will see updates in your followed content feed
- You may receive emails, depending on your communication preferences
When we apply deeplearning to anomaly detection for image on production line, there are few abnomal units to train your classifier.
Through this demo, you can learn how to try anomaly detection without training data of abnomal unit and labeling.
-kernel methods with 1class SVM and pre-trained AlexNet
-focus on production line and manufacturing.
-unsupervised classification (without labeling)
-feature visualization with t-SNE
This demo include hundreds training and test images. So you can try this now.
You can download the AlexNet support package here:
https://www.mathworks.com/matlabcentral/fileexchange/59133-neural-network-toolbox-tm--model-for-alexnet-network
Cite As
Takuji Fukumoto (2026). Deep Learning: Image anomaly detection for production line ~ (https://github.com/mathworks/Deep-Learning-Image-anomaly-detection-for-production-line/releases/tag/1.0.1), GitHub. Retrieved .
General Information
- Version 1.0.1 (12.8 MB)
-
View License on GitHub
MATLAB Release Compatibility
- Compatible with any release
Platform Compatibility
- Windows
- macOS
- Linux
| Version | Published | Release Notes | Action |
|---|---|---|---|
| 1.0.1 | See release notes for this release on GitHub: https://github.com/mathworks/Deep-Learning-Image-anomaly-detection-for-production-line/releases/tag/1.0.1 |
||
| 1.0.0.0 |