Good appearance and shape descriptors for object category recognition

Abstract

In the problem of object category recognition, we have studied different families of descriptors exploiting RGB and 3D information. Furthermore, we have proven practically that 3D shape-based descriptors are more suitable for this type of recognition due to low shape intra-class variance, as opposed to image texture-based. In addition, we have also shown how an efficient Naive Bayes Nearest Neighbor (NBNN) classifier can scale to a large hierarchical RGB-D Object Dataset [2] and achieve, with a single descriptor type, an accuracy close to state-of-art learning based approaches using combined descriptors.