Fejer filtering for multiscale signal decomposition

Multiscale signal decomposition is required in computational vision for the analysis of the information content of an image. The authors use the Fejer filtering multispectral signal decomposition technique, which uses the Fejer kernel in the classical Fourier analysis. It is built on a diffraction imaging model from the perspective of Fourier optics based on the uncertainty principle and the argument that a real signal should be bandlimited. The implementation is based on its first-order approximation form.<
>