Sampling Strategies for 3D Partial Shape Matching and Retrieval Using Bag-of-Words Model

This paper investigates the feature sampling strategies for 3D partial shape retrieval using bag-of-words model. The SHREC 09’ parts query models [3] are tested for comparison. These parts models are obtained by cutting parts from complete models, which are different from range scans. Dense sampling and pyramid sampling are proposed to extract local salient features from the depth images of the 3D models. Bag-of-words model is used to represent of both of parts query and complete target models. The optimal sampling configurations for the proposed feature extraction strategies are obtained by comparing the retrieval accuracy using maximum histogram intersection distance (MHID). The results suggest that extracting more features does not guarantee better retrieval accuracy using the bag-of-words model. The feature sampling configurations also have significant impacts on the retrieval accuracy.