Complex-valued Independent Component Analysis of Natural Images

Linear independent component analysis (ICA) learns simple cell receptive fields from natural images. Here, we show that linear complex-valued ICA learns complex cell properties from Fourier transformed natural images, i.e. two Gabor-like filters with quadrature phase relationship. Conventional methods for complex-valued ICA assume that the phases of the output signals have uniform distribution. We relax this assumption by modeling of the phase information of the output sources in the complex-valued ICA estimation. The resulting model of phases shows that the distributions are often far from uniform, and the shapes of the Gabor filters are also changed.

References: 18