To define a WN, we begin
by taking a family of wavelet functions
with parameter vectors
of some mother wavelet :
and |
It should be mentioned that it was proposed before [Daubechies, 1990,Daugman, 1988,Lee, 1996] to use an energy functional (2) in order to find the optimal set of weights for a fixed set of non-orthogonal wavelets . The WN concept enhances these approaches by finding also the optimal parameters for each (not-necessarily orthonormal) wavelet . WNs also appear to enhance the RBF neural network approach considerably. This was pointed out recently by [Reyneri, 1999], even though he investigated a considerably simplified version of WNs with radial wavelets which limits the potentials of the WNs considerably.
The parameters are chosen from continuous phase space and the wavelets are positioned with sub-pixel accuracy. This is precisely the main advantage over the discrete approach of [Daubechies, 1990,Lee, 1996]. While in the case of a discrete phase space local image structure has to be approximated by a combination of wavelets, only a single wavelet needs to be chosen in the continuous case to reflect precise the local image structure. This assures that a maximum of the image information can be encoded with only a small number of wavelets.
In order to find a WN , for a function , we use the Levenberg-Marquardt method. As initialization, we distribute the wavelets homogeneously over the region of interest. The orientations are initialized randomly, the scales are initialized to a constant value that is related to the density with which the wavelets are distributed. We constrained the wavelet parameters to prevent degenerated wavelet shapes. For the two wavelet types in this paper (odd Gabor, difference-of-Gaussian) we used constrains according to [Daugman, 1985]. In several experiments we have found that this rough initialization is sufficient. Also, we apply a coarse-to-fine strategy by first optimizing a set of wavelets initialized to coarse scale, followed by the optimization of a set of wavelets, initialized to a finer scale. Intuitively, a coarse-to-fine strategy for optimization makes sense because this minimizes the energy functional (2) more efficiently. To optimize a WN with 16 wavelets it takes about 30s on a 750 MHz Pentium processor.
Using the optimal wavelets and weights of the wavelet network of an image , can be (closely) reconstructed by a linear combination of the weighted wavelets:
|
The images in fig. 2 show the relation between the optimized positions of the wavelets (right), and their reconstructions(left) for two different mother wavelets: the odd Gabor function (top) and an anisotropic difference-of-Gaussian (DOF) (bottom).
|