3D Object Retrieval by using View- Model Joint Relevance Technique

Abstract: Extensive research efforts have been dedicated to 3D model retrieval in recent decades. Recently, view- based methods have attracted much research attention due to the high discriminative property of multi-views for 3D object representation.3-D object retrieval has been extensively used wide range in various digital image processing applications which includes medicine, security, biometrics, genetics etc. In this work, collaboration of both view-model relevance among 3D objects for retrieval and 3D objects perception is performed based on various graph structures. Object hypergraph structure (view information) is implemented at initial stage to perceive the 3D objects in multiple views and an object graph is constructed for model data for obtaining the information about the relationship between the different features of the obtained 3D objects. Better performance and high efficiency show the supremacy of proposed work over traditional state-of-art methods.

Keywords: 3D object retrieval, Object hypergraph structure, View-model relevance, object graph.