Pattern recognition with fast feature extraction

被引：1

作者：

Nakhodkin, MG ^{[1
]}

Musatenko, YS ^{[1
]}

Kurashov, VN ^{[1
]}

机构：

[1] Kyiv Univ, Radiophys Dept, Opt Proc Lab, Kyiv, Ukraine

来源：

OPTICAL MEMORY AND NEURAL NETWORKS | 1998年 / 3402卷

关键词：

sign selection; pattern recognition; Karhunen-Loeve transform;

D O I：

10.1117/12.304963

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The comparison of recently suggested algorithms of fast approximate Karhunen-Loeve(KL) transform when applied to pattern recognition problem is presented. Tt is known that adequate signs selection is still the problem. Ln the paper we consider several algorithms that can perform fast and qualitative signs selection Among them are wavelet based algorithm of approximate XL transform, 2D algorithm of KL, transform, algorithm with projection Into proper orthogonalized basis, and real time algorithm of KL transform. To compare quality of the algorithms they are applied to human faces recognition problem The efficiency of the all abovementioned algorithms is demonstrated.

引用

页码：333 / 343

页数：11