Roberto Valerio, 5/27/03
<br><br>
Instituto de Optica (CSIC), Madrid, Spain
<br><br>

A nonlinear image representation based on the divisive normalization
with statistically independent features
<br><br>

Current models of primary visual cortex (V1) include a linear
filtering stage followed by a gain control mechanism that explains
some of the nonlinear behavior of neurons. The nonlinear stage has
been modeled as a divisive normalization in which each input linear
response is squared and then divided by a weighted sum of squared
linear responses in a certain neighborhood. Simoncelli and colleagues
have suggested that this normalization reduces the statistical
dependence of neuron responses. In this talk, I will present an
implementation of these ideas as a practical image representation. The
linear stage is implemented as a four-level orthogonal wavelet
decomposition based on Daubechies filters, and the nonlinear
normalization stage uses an improved version of Simoncelli´s
scheme. The normalization parameters are adapted to minimize
statistical dependence between the output responses, so that the
resulting representation consists of a set of statistically
independent features or visual events.