Skip to main navigation Skip to search Skip to main content

Face Virtual Sample Generation with 3D Model Based on Generative Adversarial Networks

  • School of Electronics and Information Engineering, Harbin Institute of Technology

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

Abstract

Generating virtual multi-view face images from a single face image has always been a challenge in the area of computer vision. It often suffers from appearance distortions and artifacts if the generation rule is not well-defined. In order to generate virtual samples that can contribute to recognition accuracy, this paper proposes a three-dimensional face model reconstruction method based on generative adversarial networks to expand the training dataset. It transforms single training sample per person face recognition into multi-training sample face recognition by expanding the training dataset. Our generated virtual samples have been proved efficient in improving recognition rate on face database using different algorithms.

Original languageEnglish
Title of host publicationAdvances in Intelligent Information Hiding and Multimedia Signal Processing - Proceeding of the IIH-MSP 2021 and FITAT 2021
EditorsJeng-Shyang Pan, Zhenyu Meng, Jianpo Li, Maria Virvou
PublisherSpringer Science and Business Media Deutschland GmbH
Pages79-89
Number of pages11
ISBN (Print)9789811910524
DOIs
StatePublished - 2022
Externally publishedYes
Event17th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2021, in conjunction with the 14th International Conference on Frontiers of Information Technology, Applications and Tools, FITAT 2021 - Kaohsiung, Taiwan, Province of China
Duration: 29 Oct 202131 Oct 2021

Publication series

NameSmart Innovation, Systems and Technologies
Volume278
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026

Conference

Conference17th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2021, in conjunction with the 14th International Conference on Frontiers of Information Technology, Applications and Tools, FITAT 2021
Country/TerritoryTaiwan, Province of China
CityKaohsiung
Period29/10/2131/10/21

Keywords

  • Generative adversarial networks
  • Single sample face recognition
  • Three-dimensional face model

Fingerprint

Dive into the research topics of 'Face Virtual Sample Generation with 3D Model Based on Generative Adversarial Networks'. Together they form a unique fingerprint.

Cite this