A Photo-Realistic Generator of Most Expressive and Discriminant Changes in 2D Face Images

I. Xavier, M. Pereira, G. Giraldi, S. Gibson, C. Solomon, D. Rueckert, D. Gillies, C. Thomaz

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

3 Scopus citations

Abstract

This work describes a photo-realistic generator that creates semi-automatically face images of unseen subjects. Unlike previously described methods for generating face imagery, the approach described herein incorporates texture and shape information in a single computational framework based on high dimensional encoding of variance and discriminant information from sample groups. The method produces realistic, frontal pose, images with minimum manual intervention. We believe that the work presented describes a useful tool for face perception applications where privacy-preserving analysis might be an issue and the goal is not the recognition of the face itself, but rather its characteristics like gender, age or race, commonly explored in social and forensic contexts.

Original languageEnglish
Title of host publicationProceedings - 2015 6th International Conference on Emerging Security Technologies, EST 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages80-85
Number of pages6
ISBN (Electronic)9781467397995
DOIs
StatePublished - 8 Mar 2016
Externally publishedYes
Event6th International Conference on Emerging Security Technologies, EST 2015 - Braunschweig, Germany
Duration: 3 Sep 20155 Sep 2015

Publication series

NameProceedings - 2015 6th International Conference on Emerging Security Technologies, EST 2015

Conference

Conference6th International Conference on Emerging Security Technologies, EST 2015
Country/TerritoryGermany
CityBraunschweig
Period3/09/155/09/15

Keywords

  • face images
  • photo-realistic generator

Fingerprint

Dive into the research topics of 'A Photo-Realistic Generator of Most Expressive and Discriminant Changes in 2D Face Images'. Together they form a unique fingerprint.

Cite this