3D Model Retrieval Via Multiple Feature Fusion

With the rapid development of computer hardware and computer graphics tech-niques, especially the modeling and rendering techniques, more and more 3-dimensional (3D) models have been created and used in a wide range of applications, and it also en-couraged the development of 3D model retrieval researches. In these researches, view-based multiple features retrieval obtains a better performance. Since each visual feature only reflects a unique characteristic about a 3-dimensional (3D) model and differen-t visual features have diverse discriminative power in model representation, it would be beneficial to fuse multiple visual features in 3D model retrieval, and learn a more compact yet discriminative fusion feature to improve the retrieval performance.To this end, we propose view-based 3D model retrieval framework in this thesis. This framework comprises two parts:1) a Multiple Feature Fusion algorithm (MFF), and 2) an efficient Online Projection Learning algorithm (OPL). First, MFF is used to learn a compact yet discriminative feature representation from the original multiple vi-sual features; Then, OPL is designed to fast transfer the input multiple visual features of a newcome model into its corresponding low-dimensional feature representation. In this framework, many existing ranking algorithms such as the simple distance-based ranking method can be directly adopted for sorting all 3D models in the database. Ex-tensive experiments on two public 3D model databases demonstrate the efficiency and the effectiveness of the proposed approach over its competitors.