Figure 1.

Average image power spectrumw(1) for different pictures. The values presented below images are values of the w(1) feature. A preliminary image analysis shows that the higher the homogeneity – lower frequency of changes, the lower the value of coefficient w(1). Higher, in terms of amplitude, changes, a higher frequency, a higher value of w(1). This feature is one of the 10 features that take part in creating a decision tree for classification of healthy subjects from patients. In this case, this feature is associated with Fourier decomposition and, to be more exact, with average image power spectrum.