Algorithm BOSS (Bag-of-Salient local Spectrums) for non-rigid and partial 3D object retrieval

The aim of the proposed algorithm is to expedite three-dimensional objects indexing and retrieval. Investigating the Bag-of-Features (BoF) paradigm, we focus on a set of extracted local descriptors from 3D objects. Using scalar function calculated on the surface mesh, the algorithm extracts the salient points, and then associates each of these points with a local Fourier descriptor. The descriptor is computed on the neighboring salient points by projecting the geometry onto the first eigenvectors of Laplace–Beltrami operator. Additionally, through an offline learning step, a visual dictionary is built by clustering a large set of feature descriptors. Then, each 3D shape is described by a histogram of these visual words occurrences weighted using the number of their local descriptors. Experimental results show the highly discriminative capability of the proposed approach against rigid and non-rigid transformations, noise and geometry changes. The performance of our algorithm is also demonstrated on global and partial shape retrieval.