Table 5: Areas under the ROC curves for scaling index (SI) method using FLDA. The rows represent the motion compensation as given by Table 1. Numbers in boldface show the best results.

Feature typeArea under the ROC curve (%)

SI max.74.666.664.369.362.880.3 69.160.962.8
SI mean80.3 79.879.680.078.680.577.179.677.5
SI st. dev.52.781.5 73.370.874.461.167.479.272.5
SI entropy70.871.475.072.771.668.965.175.076.5