Eye detection using discriminatory Haar features and a new efficient SVM

作者：

Highlights：

• A discriminating feature extraction (DFE) method for two-class problems is proposed.

• The DFE method is applied to derive the discriminatory Haar features (DHFs) for eye detection.

• An efficient support vector machine (eSVM) is proposed to improve the efficiency of the SVM.

• An accurate and efficient eye detection method is presented using the DHFs and the eSVM.

摘要

•A discriminating feature extraction (DFE) method for two-class problems is proposed.•The DFE method is applied to derive the discriminatory Haar features (DHFs) for eye detection.•An efficient support vector machine (eSVM) is proposed to improve the efficiency of the SVM.•An accurate and efficient eye detection method is presented using the DHFs and the eSVM.

论文关键词：Discriminatory feature extraction (DFE),Discriminatory Haar features (DHFs),Efficient support vector machine (eSVM),Eye detection,Fisher linear discriminant (FLD),Principal component analysis (PCA),Face Recognition Grand Challenge (FRGC),BioID database

论文评审过程：Received 12 September 2012, Revised 9 September 2014, Accepted 21 October 2014, Available online 7 November 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.10.007