Kernel Methods and Its Application in Wavefront Reconstruction

摘要：

　　Kernel methods can effectively deal with the nonlinear problem.The methods not only can be used for data de-noising,also be effective for classification problems.Using kernel PCA method,we provide a more precise Zernike expansion,which can apparently improve the reconstruction accuracy.At the same time,explore learning the kernel function by the alignment.We verify that the alignment value and recognition rate is proportional relationship.

关键词： Kernel PCA Adaptive optics Zernike polynomials Alignment

作者: Zhiying Tan Ying Chen Kun She Yong Feng

作者单位: School of Computer Science & Engineering, University of Electronic Science & Technology of China,Che Chongqing Inst.of Green and Intelligent Technology, Chinese Academy of Sciences,Chongqing, China

会议类型: 国际会议

会议名称: 2012 2nd International Conference on Computer and Information Applications(ICCIA2012)(2012第二届计算机和信息应用国际会议)

会议地点: 太原

会议语种:英文

页码: 117-120

在线出版日期: 2012-12-08（万方平台首次上网日期，不代表论文的发表时间）