Combining view-based pose normalization and feature transform for cross-pose face recognition

Hua Gao, Hazim Kemal Ekenel, Rainer Stiefelhagen

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

Abstract

Automatic face recognition across large pose changes is still a challenging problem. Previous solutions apply a transform in image space or feature space for normalizing the pose mismatch. For feature transform, the feature vector extracted on a probe facial image is transferred to match the gallery condition with regression models. Usually, the regression models are learned from paired gallery-probe conditions, in which pose angles are known or accurately estimated. The solution based on image transform is able to handle continuous pose changes, yet the approach suffers from warping artifacts due to misalignment and self-occlusion. In this work, we propose a novel approach, which combines the advantage of both methods. The algorithm is able to handle continuous pose mismatch in gallery and probe set, mitigating the impact of inaccurate pose estimation in feature-transform-based method. We evaluate the proposed algorithm on the FERET face database, where the pose angles are roughly annotated. Experimental results show that our proposed method is superior to solely image/feature transform methods, especially when the pose angle difference is large.

Original languageEnglish (US)
Title of host publicationProceedings of 2015 International Conference on Biometrics, ICB 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages487-492
Number of pages6
ISBN (Electronic)9781479978243
DOIs
StatePublished - Jun 29 2015
Event8th IAPR International Conference on Biometrics, ICB 2015 - Phuket, Thailand
Duration: May 19 2015May 22 2015

Publication series

NameProceedings of 2015 International Conference on Biometrics, ICB 2015

Conference

Conference8th IAPR International Conference on Biometrics, ICB 2015
Country/TerritoryThailand
CityPhuket
Period5/19/155/22/15

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science Applications
  • Biomedical Engineering
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Combining view-based pose normalization and feature transform for cross-pose face recognition'. Together they form a unique fingerprint.

Cite this