Diferencia entre revisiones de «GIC-experimental-databases/OASIS deformation feature vectors»
De Grupo de Inteligencia Computacional (GIC)
| Línea 26: | Línea 26: | ||
* [[media:JD_prctile995.zip | Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.995 percentile]] | * [[media:JD_prctile995.zip | Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.995 percentile]] | ||
* [[media:JD_prctile999.zip | Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.999 percentile]] | * [[media:JD_prctile999.zip | Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.999 percentile]] | ||
Contact: Alexandre Savio. | |||
Revisión del 03:28 3 ene 2011
Datasets of features extracted from the subset of 98 females from OASIS
These features are based on deformation measures (displacement vector magnitudes and Jacobian determinant of gradient matrices) of a custom template made with all the 98 subjects registered to each subject.
Be careful of some feature sets, some are empty because of the percentile limit.
Pipelines trying to explain how these features were extracted:
- Obtaining the measures of the displacement vectors.
- Obtaining the correlation values from the displacement measures.
Feature sets extracted from transformation displacement magnitudes (DM)
- Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.990 percentile
- Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.995 percentile
- Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.999 percentile
Feature sets extracted from transformation gradient Jacobian matrices determinant (JD)
- Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.990 percentile
- Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.995 percentile
- Feature sets of Pearson, Spearman and Kendall correlation measures over a 0.999 percentile
Contact: Alexandre Savio.
