Skip to main navigation Skip to search Skip to main content

Facial pose estimation via dense and sparse representation

  • University of Portsmouth

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

Abstract

Facial pose estimation is an important part for facial analysis such as face and facial expression recognition. In most existing methods, facial features are essential for facial pose estimation. However, occluded key features and uncontrolled illumination of face images make the facial feature detection vulnerable. In this paper, we propose methods for facial pose estimation via dense reconstruction and sparse representation but avoid localizing facial features. The Sparse Representation Classifier (SRC) method has achieved successful results in face recognition. In this paper, we explore SRC in pose estimation. Sparse representation learns a dictionary of base functions, so each input pose can be approximated by a linear combination of just a sparse subset of the bases. The experiment conducted on the CMU Multiple face database has shown the effectiveness of the proposed method.

Original languageEnglish
Title of host publicationIEEE SSCI 2014
Subtitle of host publication2014 IEEE Symposium Series on Computational Intelligence - RiiSS 2014: 2014 IEEE Symposium on Robotic Intelligence in Informationally Structured Space, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479944651
DOIs
StatePublished - 13 Jan 2015
Externally publishedYes
Event2014 IEEE Symposium on Robotic Intelligence in Informationally Structured Space, RiiSS 2014 - Orlando, United States
Duration: 9 Dec 201412 Dec 2014

Publication series

NameIEEE SSCI 2014: 2014 IEEE Symposium Series on Computational Intelligence - RiiSS 2014: 2014 IEEE Symposium on Robotic Intelligence in Informationally Structured Space, Proceedings

Conference

Conference2014 IEEE Symposium on Robotic Intelligence in Informationally Structured Space, RiiSS 2014
Country/TerritoryUnited States
CityOrlando
Period9/12/1412/12/14

Keywords

  • 3D face
  • human face
  • linear regression
  • pose analysis

Fingerprint

Dive into the research topics of 'Facial pose estimation via dense and sparse representation'. Together they form a unique fingerprint.

Cite this