3D model retrieval based on deep Autoencoder neural networks

Zhao Ming Liu, Yung Yao Chen, S. Hidayati, Shih Che Chien, Feng Chia Chang, Kai Lung Hua

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

8 Citations (Scopus)

Abstract

The rapid growth of 3D model resources for 3D printing has created an urgent need for 3D model retrieval systems. Benefiting from the evolution of hardware devices, visualized 3D models can be easily rendered using a tablet computer or handheld mobile device. In this paper, we present a novel 3D model retrieval method involving view-based features and deep learning. Because 2D images are highly distinguishable, constructing a 3D model from multiple 2D views is one of the most common methods of 3D model retrieval. Normalization is typically challenging and time-consuming for view-based retrieval methods; however, this work utilized an unsupervised deep learning technique, called Autoencoder, to refine compact view-based features. Therefore, the proposed method is rotation-invariant, requiring only the normalization of the translation and the scale of the 3D models in the dataset. For robustness, we applied Fourier descriptors and Zernike moments to represent the 2D features. The experimental results testing our method on the online Princeton Shape Benchmark Dataset demonstrate more accurate retrieval performance than other existing methods.

Original languageEnglish
Title of host publicationProceedings - International Conference on Signals and Systems, ICSigSys 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages290-296
Number of pages7
ISBN (Electronic)9781509067480
DOIs
Publication statusPublished - 30 Jun 2017
Externally publishedYes
Event1st IEEE International Conference on Signals and Systems, ICSigSys 2017 - Bali, Indonesia
Duration: 16 May 201718 May 2017

Publication series

NameProceedings - International Conference on Signals and Systems, ICSigSys 2017

Conference

Conference1st IEEE International Conference on Signals and Systems, ICSigSys 2017
Country/TerritoryIndonesia
CityBali
Period16/05/1718/05/17

Keywords

  • 3D Model Retrieval
  • Autoencoder
  • Fourier Descriptor
  • Zernike Moments

Fingerprint

Dive into the research topics of '3D model retrieval based on deep Autoencoder neural networks'. Together they form a unique fingerprint.

Cite this