The optimal usage of the Fourier transform for pattern recognition

被引：12

作者：

Gelman, L ^{[1
]}

Braun, S

机构：

[1] Natl Tech Univ Ukraine, Kiev, Ukraine

[2] Technion Israel Inst Technol, Fac Mech Engn, IL-32000 Haifa, Israel

来源：

MECHANICAL SYSTEMS AND SIGNAL PROCESSING | 2001年 / 15卷 / 03期

关键词：

Fourier transforms - Gaussian noise (electronic) - Machinery - Numerical analysis - Optimization;

D O I：

10.1006/mssp.2000.1373

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

A new general optimal approach is presented, for those cases where one and multidimensional Fourier transforms are used for pattern recognition. It consists in using both the real and imaginary components of Fourier transform as features. The use of the power spectral density and phase spectrum is shown to be a specific case of this general approach. Specific examples demonstrating the proposed approach are presented. This dealt with the recognition of Gaussian stationary zero mean signal. A specific case using the short-time Fourier transform, where a different feature vector is optimal is presented. The gain of usage optimal feature vector is shown by using Fisher's criterion. (C) 2001 Academic Press.

引用

页码：641 / 645

页数：5