Format

Send to:

Choose Destination
See comment in PubMed Commons below
IEEE Trans Pattern Anal Mach Intell. 2013 Jun 12. [Epub ahead of print]

Learning Discriminant Face Descriptor.

Author information

  • 1Institute of Automation, Chinese Academy of Sciences, Beijing.

Abstract

Local feature descriptor is an important module for face recognition and those like Gabor and local binary patterns (LBP) have proven effective face descriptors. Traditionally, the form of such local descriptors is pre-defined in a handcrafted way. In this paper, we propose a method to learn a discriminant face descriptor (DFD) in a data-driven way. The idea is to learn the most discriminant local features that minimize the difference of the features between images of the same person and maximize that between images from different persons. In particular, we propose to enhance the discriminative ability of face representation in three aspects. First, the discriminant image filters are learned. Second, the optimal neighborhood sampling strategy is soft determined. Third, the dominant patterns are statistically constructed. We further apply the proposed method to the heterogeneous (cross-modality) face recognition problem and learn DFD in a coupled way (coupled DFD or C-DFD) to reduce the gap between features of heterogeneous face images to improve the performance of this challenging problem. Extensive experiments on FERET, CAS-PEAL-R1, LFW and HFB face databases validate the effectiveness of the proposed DFD learning on both homogeneous and heterogeneous face recognition problems.

PMID:
23775461
[PubMed - as supplied by publisher]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for IEEE Computer Society
    Loading ...
    Write to the Help Desk