A statistical method for 2-D facial landmarking

Hamdi Dibeklioglu*, Albert Ali Salah, Theo Gevers

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Many facial-analysis approaches rely on robust and accurate automatic facial landmarking to correctly function. In this paper, we describe a statistical method for automatic facial-landmark localization. Our landmarking relies on a parsimonious mixture model of Gabor wavelet features, computed in coarse-to-fine fashion and complemented with a shape prior. We assess the accuracy and the robustness of the proposed approach in extensive cross-database conditions conducted on four face data sets (Face Recognition Grand Challenge, Cohn-Kanade, Bosphorus, and BioID). Our method has 99.33% accuracy on the Bosphorus database and 97.62% accuracy on the BioID database on the average, which improves the state of the art. We show that the method is not significantly affected by low-resolution images, small rotations, facial expressions, and natural occlusions such as beard and mustache. We further test the goodness of the landmarks in a facial expression recognition application and report landmarking-induced improvement over baseline on two separate databases for video-based expression recognition (Cohn-Kanade and BU-4DFE).

Original languageEnglish
Article number5963714
Pages (from-to)844-858
Number of pages15
JournalIEEE Transactions on Image Processing
Volume21
Issue number2
DOIs
Publication statusPublished - 1 Feb 2012

Keywords

  • Facial feature localization
  • facial landmarking
  • factor analysis
  • Gabor wavelet features
  • mixture models
  • shape prior
  • structural analysis

Fingerprint

Dive into the research topics of 'A statistical method for 2-D facial landmarking'. Together they form a unique fingerprint.

Cite this