Partial face biometry using shape decomposition on 2D conformal maps of faces

Abstract : In this paper, we introduce a new approach for partial 3D face recognition, which makes use of shape decomposition over the rigid1 part of a face. To explore the descriptiveness of shape dissimilarity over an isometric part of a face, which has lower probability to be influenced by expression, we transform a 3D shape to a 2D domain using conformal mapping and use shape decomposition as a similarity measurement. In our work we investigate several classifiers as well as several shape descriptors for recognition purposes. Recognition tests on a subset of the FRGC data set show approximately 80% rank-one recognition rate using only the eyes and nose part of the face.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01381512
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Friday, October 14, 2016 - 2:47:23 PM
Last modification on : Thursday, November 21, 2019 - 2:22:11 AM

Identifiers

Citation

Przemyslaw Szeptycki, Mohsen Ardabilian, Liming Chen, Wei Zeng, David Gu, et al.. Partial face biometry using shape decomposition on 2D conformal maps of faces. International Conference on Pattern Recognition , Aug 2010, Istanbul, Turkey, Turkey. pp.1-4, ⟨10.1109/ICPR.2010.372⟩. ⟨hal-01381512⟩

Share

Metrics

Record views

222