Face Image Generation for Illustration by WGAN-GP Using Landmark Information

Miho Takahashi, Hiroshi Watanabe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

With the spread of social networking services, face images for illustration are being used in a variety of situations. Attempts have been made to create illustration face images using adversarial generation networks, but the quality of the images has not been sufficient. It would be much easier to generate face images for illustrations if they could be generated by simply specifying the shape and expression of the face. Also, if images can be generated using landmark information, which is the location of the eyes, nose, and mouth of a face, it will be possible to capture and learn the features of the face. Therefore, in this paper, we propose a method to generate face images for illustration using landmark information. Our method can learn the location of landmarks and produce high quality images on creation of illustration face images.

Original languageEnglish
Title of host publication2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages936-937
Number of pages2
ISBN (Electronic)9781665436762
DOIs
Publication statusPublished - 2021
Event10th IEEE Global Conference on Consumer Electronics, GCCE 2021 - Kyoto, Japan
Duration: 2021 Oct 122021 Oct 15

Publication series

Name2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021

Conference

Conference10th IEEE Global Conference on Consumer Electronics, GCCE 2021
Country/TerritoryJapan
CityKyoto
Period21/10/1221/10/15

ASJC Scopus subject areas

  • Computer Science Applications
  • Signal Processing
  • Biomedical Engineering
  • Electrical and Electronic Engineering
  • Media Technology
  • Instrumentation

Fingerprint

Dive into the research topics of 'Face Image Generation for Illustration by WGAN-GP Using Landmark Information'. Together they form a unique fingerprint.

Cite this