Using bagging and boosting algorithms for 3D object labeling

Machine learning has recently become an interesting research field in 3D objects preprocessing. However, few algorithms using this automatic technique have been proposed to learn 3D objects parts. The aim of this paper is to present two simple and efficient approaches to learn parts of a 3D object. These approaches use Bagging or multiclass Boosting algorithms and the Shape Spectrum Descriptor (SSD) to build the classification models. The trained models will assign an appropriate label to each part of the 3D object of the database. The high quality of the quantitative and qualitative results obtained demonstrated the efficiency and the performance of the proposed approaches.