In this paper, we propose an objective evaluation approach of polygonal 3D mesh segmentation algorithms. Our approach is based on region classification. For that, we classify first manual segmented mesh into convex, concave and planar regions. Secondly, we present three quality measures that quantify the similarity of each type of region of the ground-truth relatively to the segmentation obtained by an automatic algorithm. We apply this approach on eight wellselected existing algorithms on heterogeneous images. This provides better understanding as to the strengths and weaknesses of each technique in function of each mesh-regions type in the aim to make the better choice concerning the segmentation algorithms for different applications.