Image enhancement by the tensor transform

In this paper a new method of image enhancement based on the tensor transform of images with respect to the Fourier transform is described. The method is based on the fact that the two-dimensional (2-D) image can be represented uniquely by a set of 1-D signals that split the 2-D Fourier transform into different groups of samples. Each splitting signal carries information of the 2-D Fourier transform at samples of a specific group. The image enhancement procedure can be reduced to processing splitting-signals. The experimental results shows that the enhancement can be achieved by processing only one or a few splitting signals. The enhancement of images is considered with respect to the quantitative measure of image enhancement based on the Weber definition of the contrast.