Skip to main navigation Skip to search Skip to main content

3D model retrieval based on projected area at mesh vertex

  • School of Mechatronics Engineering, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The conventional shape feature-based method did not describe the local feature enough. This paper proposed a new 3D model retrieval method based on projected area at mesh vertex. First, sum the projected area on vertical plane of the normal vector at mesh vertex, then normalized the list of the projected area distributions and transfer these data by Fourier transform method. Then the result is defined as 3D model's feature vector which can be used to calculate the similarity of different models. Experiments were conducted to evaluate the proposed algorithm utilizing the Engineering Shape Benchmark (ESB) database. The experiential results show that the proposed methods effectively reflect the similarity among engineering models, and the match result of the models is accurate and the retrieval performance is significantly improved compared to traditional shape distribution method.

Original languageEnglish
Title of host publicationProceedings - 2012 3rd International Conference on Digital Manufacturing and Automation, ICDMA 2012
Pages1-4
Number of pages4
DOIs
StatePublished - 2012
Externally publishedYes
Event2012 3rd International Conference on Digital Manufacturing and Automation, ICDMA 2012 - Guilin, Guangxi, China
Duration: 31 Jul 20122 Aug 2012

Publication series

NameProceedings - 2012 3rd International Conference on Digital Manufacturing and Automation, ICDMA 2012

Conference

Conference2012 3rd International Conference on Digital Manufacturing and Automation, ICDMA 2012
Country/TerritoryChina
CityGuilin, Guangxi
Period31/07/122/08/12

Keywords

  • 3D model retrieval
  • Fourier transform
  • Projected area

Fingerprint

Dive into the research topics of '3D model retrieval based on projected area at mesh vertex'. Together they form a unique fingerprint.

Cite this