一种基于正交投影的特征抽取方法  

Orthogonal Projection Method Based Feature Extraction

作　　者：涂庆华[1] 杨健[1] 杨静宇[1] 

机构地区：[1]南京理工大学计算机科学系,江苏南京210094

出　　处：《小型微型计算机系统》2003年第3期555-557,共3页Journal of Chinese Computer Systems

摘　　要：本文结合 Fisher鉴别准则给出了一组正交投影矢量 ,并引入了一种度量投影矢量相关性的简捷方法 .与经典的 Foley- Sam mon鉴别分析法相比 ,所提出的正交投影法具有较强的消除样本特征之间相关性的能力和良好的鉴别能力 .最后 ,在 CENPARMI手写体阿拉伯数字库的试验结果证实了该特征抽取方法明显优于 Foley- SammConsidering the Fisher discriminant criterion, a new orthogonal projection method for feature extraction is presented in this paper. Besides, a simple approach is introduced to measure the correlation between the projective vectors. Comparing to the classical Foley Sammon discriminant analysis, the proposed orthogonal projection method has more powerful capability to eliminate the correlation between features. Finally, the experiment on Concordia University CENPARMI handwriting numeral database indicates that the proposed orthogonal projection method is more effective than Foley Sammon discriminant analysis.

关 键 词：正交投影 特征抽取方法 FISHER鉴别准则 手写体数字识别 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]