View-based 3D model retrieval with probabilistic graph model

  • Authors:

  • Yue Gao;Jinhui Tang;Haojie Li;Qionghai Dai;Naiyao Zhang

  • Affiliations:

  • Department of Automation, Tsinghua University, China and Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, China;School of Computing, National University of Singapore, Singapore;School of Software, Dalian University of Technology, China;Department of Automation, Tsinghua University, China and Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, China;Department of Automation, Tsinghua University, China and Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, China

  • Venue:
  • Neurocomputing
  • Year:
  • 2010

Quantified Score

Hi-index 0.01

Visualization

Abstract

In this paper, we present a view-based 3D model retrieval algorithm using probabilistic graph model. In this work, five circle camera arrays are employed, and five groups of views are captured from each 3D model. Each captured view set is modeled as a first order Markov Chain. The task of 3D model retrieval is defined as a probabilistic analysis procedure, and the comparison between the query and other 3D models is changed to compute the conditional probabilities of 3D models in the database given the query model. The purpose to search 3D model is to find the maximal a posterior probability of the models in the database given the query model. Then, we present a solution to estimate the conditional probabilities. The proposed 3D model retrieval algorithm has been evaluated on the NTU 3D model database. Experimental results and comparison with other methods show the effectiveness of the proposed approach.