Appendix 7—table 2. Comparison between the results obtained with three different over/under segmentation factor $(0.5,0.6,0.7)$.

The effect of tuning this parameter is mostly reflected in the VOIs scores. In this case the best result have been obtained by steering the segmentation towards the over segmentation.

ds3 confocal + rescaling
Dataset	Over/under factor 0.5			Over/under factor 0.6 (Default)			Over/under factor 0.7
	ARand	VOIsplit	VOImerge	ARand	VOIsplit	VOImerge	ARand	VOIsplit	VOImerge
Anther	0.548	0.540	1.131	0.265	0.748	0.650	0.215	1.130	0.517
Filament	0.740	0.417	1.843	0.232	0.608	0.601	0.159	0.899	0.350
Leaf	0.326	0.281	0.825	0.149	0.361	0.342	0.117	0.502	0.247
Pedicel	0.624	0.585	2.126	0.402	0.807	1.161	0.339	1.148	0.894
Root	0.244	0.334	0.972	0.123	0.442	0.592	0.113	0.672	0.485
Sepal	0.904	0.494	2.528	0.713	0.652	1.615	0.346	0.926	1.211
Valve	0.831	0.432	2.207	0.586	0.578	1.443	0.444	0.828	1.138
Average	0.602	0.441	1.662	0.353	0.600	0.915	0.248	0.872	0.691