Partial 3D object retrieval using local binary QUICCI descriptors and dissimilarity tree indexing

A complete pipeline is presented for accurate and efficient partial 3D object retrieval based on Quick Intersection Count Change Image (QUICCI) binary local descriptors a novel indexing tree. It shown how modification to the QUICCI query descriptor makes it ideal retrieval. An structure called Dissimilarity Tree proposed which can significantly accelerate searching large space of descriptors; this applicable other descriptors. The index exploits distribution bits within tested artificial part SHREC’16 dataset with near-ideal results.