Composite Fourier-plane nonlinear filter for distortion-invariant pattern recognition

被引：20

作者：

Javidi, B

Wang, WL

Zhang, GS

机构：

[1] University of Connecticut, Dept. of Elec. and Syst. Engineering, Storrs

[2] Dept. of Electrical Engineering, University of Connecticut

[3] IEEE, Lasers and Electro-Optics Society, Tech. Comm. on Electro-Optics Sys.

[4] Optical Proc. and Comp. Working Grp., Optical Engineering Society

[5] Dept. of Elec. and Syst. Engineering, University of Connecticut

[6] Tsinghua University, Beijing

来源：

OPTICAL ENGINEERING | 1997年 / 36卷 / 10期

关键词：

correlation pattern recognition; composite Fourier-plane nonlinear filters; distortion-invariant pattern recognition; nonlinear joint transform correlator;

D O I：

10.1117/1.601319

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

We investigate composite Fourier-plane nonlinear filters for distortion-invariant pattern recognition. Different types of noise such as spatially nonoverlapping color background noise, other nontarget objects, real scene noise, and additive white noise are used to investigate the performance of the filler. Computer simulation results are presented to show the, performance enhancement using Fourier-plane nonlinearities in the composite filter designs. The training image sets and the test image sets are generated by in-plane and out-plane rotation of different aircraft. (C) 1997 Society of Photo-Optical Instrumentation Engineers.

引用

页码：2690 / 2696

页数：7

共 16 条

[1] MULTIVARIANT TECHNIQUE FOR MULTICLASS PATTERN-RECOGNITION [J].