Earticle

초록

영어

The segmentation technique of 3D mesh models plays a key role in comprehending and processing digital geometric models. A new segmentation algorithm for 3D mesh models based on conformal factor and k-means clustering is proposed to deal with the existing problems in segmentation methods, which includes a lack of semantic information and low performance in segmentation results. It is easy to obtain an effective segmentation results with semantic information since the conformal factors carry global feature information of the model. Firstly, the discrete Gaussian curvatures of each vertex are figured out. Secondly, the conformal factors are calculated by employing Laplace-Beltrami operators. Finally, the clustering of meshes is realized by modified k-means clustering algorithm. Experimental results show that the proposed algorithm not only can achieve meaningful segmentation of 3D models, but also has good anti-jamming performance caused by pose variation of the model.

목차

Abstract
 1. Introduction
 2. Related Work
 3. Gaussian Curvature and Laplace-Beltrami Operator
  3.1. Gaussian Curvature
  3.2. Laplace-Beltrami Operator
 4. Conformal Factor
 5. Modified k-means Clustering Algorithm
 6. Experimental Results and Discussion
 7. Conclusion
 Acknowledgments
 References

키워드

저자

• Yang Jun [ School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China ]
• Wang Maozheng [ School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China ]
• Yan Han [ School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Grid and Distributed Computing

• 간기

  격월간

• pISSN

  2005-4262

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605