Feature Fusion of Palmprint and Face Based on KFDA

摘要：

Feature fusion of palmprint and face based on Kernel Fisher discriminant analysis (KFDA) was proposed in the paper.The essence of KFDA is Kernel Principal Component Analysis (KPCA) plus Linear Discriminant Analysis (LDA).Thus we first obtained the KPCA fusion features,and then calculated the final fusion features by LDA.The discriminant vectors existing in null space and range space of within-class scatter matrix were calculated respectively by dual space analysis.The experiment results showed that multimodality outperformed than the unimodality in both identification and authentication aspect.

关键词： Feature-level fusion KFDA Dual space

作者: Yucheng Wang Dongmei Sun

作者单位: Institute of information science,Beijing Jiaotong University,Beijing,China

会议类型: 国际会议

会议名称: 9th International Conference on Signal Processing(第九届国际信号处理学术会议)(ICSP08)

会议地点: 北京

会议语种:英文

在线出版日期: 2008-10-26（万方平台首次上网日期，不代表论文的发表时间）