Optimization of wavelet filters to improve recognition accuracy of a volume holographic correlator

被引：1

作者：

Feng, WY ^{[1
]}

Yan, YB ^{[1
]}

Huang, GG ^{[1
]}

Jin, GF ^{[1
]}

Wu, MX ^{[1
]}

机构：

[1] Tsing Hua Univ, Dept Precis Instruments, State Key Lab Precis Measurement Technol & Instru, Beijing 100084, Peoples R China

来源：

WAVELET APPLICATIONS IN SIGNAL AND IMAGE PROCESSING VII | 1999年 / 3813卷

关键词：

volume holographic storage; wavelet transform; neural network; filter design; optimization; human face recognition;

D O I：

10.1117/12.366768

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The concept of the associative storage in a photorefractive material offers suitable methods to design a multichannel correlator for image identification. Wavelet transform is introduced to improve recognition accuracy of the system, which provides a sharper peak and lower sidelobes than the conventional correlation. The recognition accuracy of the system is significantly affected by the choice of wavelet function and its parameters. A neural network is proposed to optimize parameters of the wavelet filters to improve recognition performance of the system. The object function for optimization is to maximize the difference of correlation outputs among different categories and minimize the variation of correlation outputs in a same category. Simulation and experimental results are given to testify the effect of optimization. Its application in human face recognition is studied. The results show that it is attractive to use neural network to refine parameters of filters.

引用

页码：949 / 956

页数：4

共 14 条

[1]

BURR GW, 1994, P SOC PHOTO-OPT INS, V2297, P402, DOI 10.1117/12.187311

[2] NEURAL-NET DESIGN OF MACRO GABOR WAVELET FILTERS FOR DISTORTION-INVARIANT OBJECT DETECTION IN CLUTTER [J].