Abstract

Wavelet networks (WNs) were introduced in 1992 as a combination of artificial neural radial basis function (RBF) networks and wavelet decomposition. Since then, however, WNs have received only a little attention. We believe that the potential of WNs has been generally underestimated. WNs have the advantage that the wavelet coefficients are directly related to the image data through the wavelet transform. In addition, the parameters of the wavelets in the WNs are subject to optimization, which results in a direct relation between the represented function and the optimized wavelets, leading to considerable data reduction (thus making subsequent algorithms much more efficient) as well as to wavelets that can be used as an optimized filter bank. In our study we analyze some WN properties and highlight their advantages for object representation purposes. We then present a series of results of experiments in which we used WNs for face tracking. We exploit the efficiency that is due to data reduction for face recognition and face-pose estimation by applying the optimized-filter-bank principle of the WNs.

© 2002 Optical Society of America

Wavelet transform as a bank of the matched filters

Harold Szu, Yunlong Sheng, and Jing Chen
Appl. Opt. 31(17) 3267-3277 (1992)

Wigner functions from the two-dimensional wavelet group

S. Twareque Ali, A. E. Krasowska, and R. Murenzi
J. Opt. Soc. Am. A 17(12) 2277-2287 (2000)

Wavelet transforming characteristic of a lens

Liying Tan, Jing Ma, Qi Wang, and Qiwen Ran
Appl. Opt. 41(29) 6182-6186 (2002)

Discriminant analysis for recognition of human face images

Kamran Etemad and Rama Chellappa
J. Opt. Soc. Am. A 14(8) 1724-1733 (1997)

Wavelet operators for nonlinear optical pulse propagation

Iestyn Pierce, Paul Rees, and K. Alan Shore
J. Opt. Soc. Am. A 17(12) 2431-2439 (2000)