Face recognition using Extended Curvature Gabor classifier bunch

作者：

Highlights：

• We propose extended curvature Gabor kernels as complementary features.

• Homogeneous Classifier Bunch increases accuracy in low/mid-resolution images.

• Parallel boosting method effectively selects salient features from many features.

• We report the best verification rate using the FRGC version 2.0 database.

• We have extensive experimental results.

摘要

Highlights•We propose extended curvature Gabor kernels as complementary features.•Homogeneous Classifier Bunch increases accuracy in low/mid-resolution images.•Parallel boosting method effectively selects salient features from many features.•We report the best verification rate using the FRGC version 2.0 database.•We have extensive experimental results.

论文关键词：Face recognition,Extended Curvature Gabor wavelet,Feature extraction,Face Recognition Grand Challenge (FRGC)

论文评审过程：Received 16 August 2013, Revised 10 May 2014, Accepted 28 September 2014, Available online 12 November 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.09.029