PDF version of this entire document

Validation using Warped Images

Figure  plots each of the four variants of the generalised overlap measure, as a function of 79#79, the degree of misregistration. As expected, the value decreases monotonically with increasing misregistration, in each case. This shows that our two gold-standard measures of misregistration (mean pixel displacement and ground-truth overlap) are in agreement, which validates the experimental framework.

Similarly, Figures  &  plot Generalisation and Specificity as functions of 79#79, for different values of shuffle radius 66#66. The results are qualitatively similar to those obtained for generalised overlap, except that both measures increase monotonically with increasing misregistration, as expected (see Section . These results show that, over the range of misregistrations investigated, the model-based measures are good surrogates for 79#79, the mean pixel misregistration. Since the warps used to introduce controlled misregistration were of very general form, there is no reason to suppose that this result is dependent on the pattern of misregistration.

Figure: Mean sensitivity of different NRR assessment methods over the full range of deformations 79#79, shown with 95#95one standard error errorbars

99#99