Reconstruction from the multi-component AM-FM image representation

We present powerful multi-component AM-FM image models capable of efficiently representing complicated nonstationary multi-partite images, and show how the representation can be computed in a practical implementation. With images of this type, important structural and perceptual information is often manifest in the nonstationarities. Highly localized nonlinear operators are used to simultaneously estimate the amplitude and frequency modulating functions associated with each of the multiple components on a pixel-by-pixel basis. For the first time, we also demonstrate image reconstruction from the AM-FM representation