3D mesh becomes a common tool used in several computer vision applications. The performances of these applications depend highly on its quality. In order to quantify it, several methods have been proposed in the literature. In this paper, we propose a 3D Mesh Quality Measure based on the fusion of some selected features. The goal is here to take into account the advantages of these features and thus improve the global performance. The selected features are here some 3D mesh quality metrics and a geometric attribute. The fusion step has been realized using a Support Vector Regression (SVR) model. The 3D Mesh General database has been used to evaluate our method. The obtained results, in terms of correlation with the subjective judgments, show the relevance of the proposed framework.