-
Notifications
You must be signed in to change notification settings - Fork 16
Metrics
Bernhard Froehler edited this page Sep 3, 2024
·
3 revisions
Includes filters for computing:
- Image quality measures (without reference):
- Signal-to-Noise Ratio (SNR)
- Contrast-to-Noise-Ratio (CNR)
- Q Measure
- Similarity metrics
- Peak Signal-to-Noise Ratio
- Structural Similarity Index (SSIM)
- Mean Absolute Error
- Mean Squared Error (MSE)
- Root Mean Square Error (RMSE)
- Normalized Root Mean Square Error
- Normalized Correlation
- Joint Entropy (+ per-image entropy)
- Mutual Information
- Normalized Mutual Information
- Equal Pixel Rate
- Segmentation quality measures (computed via ITK's LabelOverlapMeasuresImageFilter):
- Total overlap
- Union overlap (also known as Jaccard index)
- Mean overlap (also known as Dice coefficient)
- Volume similarity
See the Metrics module code.
Back to Tools.
open_iA Documentation, licensed under CC BY-NC-SA 4.0