3D facial landmark localization via a local surface descriptor HoSNI

  • Authors:
  • Xiaobo Zhang;Yueming Wang;Gang Pan

  • Affiliations:
  • College of Computer Science and Technology, Zhejiang Univ., China;Qiushi Academy for Advanced Studies, Zhejiang Univ., China;College of Computer Science and Technology, Zhejiang Univ., China

  • Venue:
  • IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Facial landmarks of a 3D face model, such as nose-tip, inner-eyes, and mouth-corners, play an important role in many applications of 3D face models. This paper presents an effective approach to automatically detect landmarks of a 3D face. A novel discriminative surface descriptor, named HoSNI(Histogram of Shape Normal Information), is presented to characterize the local shape around a point on the facial surface. The HoSNI is applied to localize facial landmarks. The experiments are carried out to detect 19 facial landmarks on FRGC v2.0. The results demonstrate that our approach has high accuracy and is insensitive to expression variation.