Selection and Combination of Local Gabor Classiﬁers for Robust Face Veriﬁcation
Gabor features have been extensively used for facial image analysis due to their powerful representation capabilities. This paper focuses on selecting and combining multiple Gabor classiﬁers that are trained on, for example, different scales and local regions. The system exploits curvature Gabor features in addition to conventional Gabor features. Final classiﬁer is obtained by combining selected classiﬁers using Sequential Forward Floating Search-based selection mechanism. In addition, we combine classiﬁers trained on different local representations at score-level by learning he weights with partial least square regression. The system is evaluated on Face Recognition Grand Challenge (FRGC) version 2.0 Experiment 4. The proposed system achieves 94.16% veriﬁcation rate @ 0.1% FAR, which is the highest accuracy reported on this experiment so far in the literature.