Clustering personalized 3D printing models with multiple modal CNN

  • Jianwei Chen
  • , Lin Zhang*
  • , Xinyu Dong
  • *Corresponding author for this work

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

Abstract

Clustering personalized 3D printing models is very useful for a cloud manufacturing management system, but it is difficult to cluster directly because of the complexity and abstraction of the 3D print model input. In this paper we use the convolution neural networks (CNNs) to learn the similarities of 3D print model pairs in different input modes and integrate these similarities by multi-channel spectral clustering. The three-dimensional CNN and the view-based CNN are used for different input modes. Our experiments show that the accuracy of the clustering can be improved by merging training results of different input modes.

Original languageEnglish
Title of host publicationProceedings of 2017 Chinese Intelligent Systems Conference
EditorsJunping Du, Weicun Zhang, Yingmin Jia
PublisherSpringer Verlag
Pages703-712
Number of pages10
ISBN (Print)9789811064951
DOIs
StatePublished - 2018
EventChinese Intelligent Systems Conference, CISC 2017 - Mudanjiang, China
Duration: 14 Oct 201715 Oct 2017

Publication series

NameLecture Notes in Electrical Engineering
Volume459
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceChinese Intelligent Systems Conference, CISC 2017
Country/TerritoryChina
CityMudanjiang
Period14/10/1715/10/17

Keywords

  • CNNs
  • Personalized 3D print model
  • Similarity classifier
  • Spectral cluster

Fingerprint

Dive into the research topics of 'Clustering personalized 3D printing models with multiple modal CNN'. Together they form a unique fingerprint.

Cite this