Measuring Inter-image distances
Euclidean Distance:
The simple method for comparing disagreement among two images is to take their per-pixel difference. This is sensitive to small misalignments though.
Shuffle Distance:
In our experiments we have defined image distance as the shuffle distance between two images, as illustrated below
3#3 = 6#6 The computation of the shuffle distance
3#3 = 7#7 The product of a shuffle transform
3#3 = 8#8 The effect of increasing the shuffle radius