样本库的形成与签字鉴别的分类  

Pattern Library Formation and Signature Identification Classification

作　　者：赵永健[1] 娄兰芳[1] 李永勃[1] 

机构地区：[1]山东大学威海分校信息工程学院,威海264209

出　　处：《计算机工程》2005年第3期173-174,197,共3页Computer Engineering

摘　　要：为了形成稳定有效的签字样本库,利用Fisher鉴别准则即为Rayleigh商这一特点,根据广义Rayleigh商的极值性质,提出了一种如何在样本库的形成过程中采用学习机制的新方法,进而设计出符合系统特点的分类器。经验证该方法具有良好的稳定性与可靠性。In order to form a stable and effective pattern library, the method is developed based on the fact that the Fisher distinction criterion function is a generalized Rayleigh quotient in essence. The extremum properties of generalized Rayleigh quotient are analyzed and a new way is given by studying system of organization in the course of producing pattern library, so a sorter is designed which adapt to the system peculiarity. This algorithm has good stability and reliability to the experiment.

关 键 词：签字样本库 小波变换 FISHER鉴别准则 特征抽取 K-L变换 阈值 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]