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

Wenyi Feng; Yingbai Yan; Gaogui Huang; Guofan Jin; Minxian Wu

doi:10.1117/12.366768

26 October 1999 Optimization of wavelet filters to improve recognition accuracy of a volume holographic correlator

Wenyi Feng, Yingbai Yan, Gaogui Huang, Guofan Jin, Minxian Wu

Proceedings Volume 3813, Wavelet Applications in Signal and Image Processing VII; (1999) https://doi.org/10.1117/12.366768
Event: SPIE's International Symposium on Optical Science, Engineering, and Instrumentation, 1999, Denver, CO, United States

Abstract

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.

Citation Download Citation

Wenyi Feng, Yingbai Yan, Gaogui Huang, Guofan Jin, and Minxian Wu "Optimization of wavelet filters to improve recognition accuracy of a volume holographic correlator", Proc. SPIE 3813, Wavelet Applications in Signal and Image Processing VII, (26 October 1999); https://doi.org/10.1117/12.366768

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available