Feature Extraction Using Kernel Inverse FDA

摘要：

This paper presents a new feature extraction method called kernel inverse Fisher discriminant analysis for face recognition. In the method, the nonlinear kernel trick is first applied to map the input data into an implicit feature space. Then the inverse Fisher discriminant analysis is used to analyze the data for producing nonlinear discriminating features Experimental results on ORL face database show that the proposed method is effective in classifying.

关键词： Kernel Inverse FDA Kernel PCA Feature extraction Face recognition

作者: Zhongxi Sun Changyin Sun Zhenyu Wang Wankou Yang

作者单位: School of Automation, Southeast University, Nanjing 210096, China College of Science, Hohai Universi School of Automation, Southeast University, Nanjing 210096, China

会议类型: 国际会议

会议名称: The 31st Chinese Control Conference(第三十一届中国控制会议)

会议地点: 合肥

会议语种:英文

页码: 3672-3675

在线出版日期: 2012-07-01（万方平台首次上网日期，不代表论文的发表时间）