OFS: A Feature Selection Method for Shape-based 3D Model Retrieval

We focus on improving the effectiveness of shape-based similarity retrieval in 3D model repositories. Motivated by retrieval performance of several individual 3D model descriptors for projected images in shape-based approaches, we present an optimized feature selection (OFS) method to choose a perfect feature vector based on each query model. Experimental results show that the OFS method for shape-based 3D model retrieval has achieved significant improvements on retrieval effectiveness of 3D shape search with several measures on a standard 3D database, and it provides a retrieval performance 45.5% better than the average precision of several descriptors. Compared to the currently best method light field descriptor (LFD), OFS has better retrieval effectiveness. Furthermore, the feature vector components of our approach are only 6.77% of that in LFD.