The Computer Vision Toolbox™ Automated Visual Inspection Library offers functions that enable you to train, calibrate, and evaluate anomaly detection networks.
The library enables:
- Creating and training deep learning networks to detect anomalies.
- Calibrating the trained network by setting the anomaly thresholds for max number of false positive and negatives that are acceptable.
- Evaluating the trained networks quantitively using validation metrics and qualitatively by visualizing anomaly heatmaps.
- Labeling training and calibration ground truth data using the image labeler app by marking defective areas with a segmentation mask.
For more information, please visit the automated visual inspection documentation page which shows you how to get started with anomaly detection using deep learning and features dedicated examples.
MATLAB Release Compatibility
Created with R2022b
Compatible with R2022b
Platform CompatibilityWindows macOS Linux
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!