Generative adversarial network-based synthesis of visible faces from polarimetrie thermal faces

He Zhang, Vishal M. Patel, Benjamin S. Riggan, Shuowen Hu

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

22 Scopus citations

Abstract

The large domain discrepancy between faces captured in polarimetric (or conventional) thermal and visible domain makes cross-domain face recognition quite a challenging problem for both human-examiners and computer vision algorithms. Previous approaches utilize a two-step procedure (visible feature estimation and visible image reconstruction) to synthesize the visible image given the corresponding polarimetric thermal image. However, these are regarded as two disjoint steps and hence may hinder the performance of visible face reconstruction. We argue that joint optimization would be a better way to reconstruct more photo-realistic images for both computer vision algorithms and human-examiners to examine. To this end, this paper proposes a Generative Adversarial Network-based Visible Face Synthesis (GAN-VFS) method to synthesize more photo-realistic visible face images from their corresponding polarimetric images. To ensure that the encoded visible-features contain more semantically meaningful information in reconstructing the visible face image, a guidance sub-network is involved into the training procedure. To achieve photo realistic property while preserving discriminative characteristics for the reconstructed outputs, an identity loss combined with the perceptual loss are optimized in the framework. Multiple experiments evaluated on different experimental protocols demonstrate that the proposed method achieves state-of-the-art performance.

Original languageEnglish (US)
Title of host publicationIEEE International Joint Conference on Biometrics, IJCB 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages100-107
Number of pages8
ISBN (Electronic)9781538611241
DOIs
StatePublished - Jan 29 2018
Event2017 IEEE International Joint Conference on Biometrics, IJCB 2017 - Denver, United States
Duration: Oct 1 2017Oct 4 2017

Publication series

NameIEEE International Joint Conference on Biometrics, IJCB 2017
Volume2018-January

Other

Other2017 IEEE International Joint Conference on Biometrics, IJCB 2017
CountryUnited States
CityDenver
Period10/1/1710/4/17

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Instrumentation
  • Signal Processing
  • Biomedical Engineering

Fingerprint Dive into the research topics of 'Generative adversarial network-based synthesis of visible faces from polarimetrie thermal faces'. Together they form a unique fingerprint.

Cite this