Fusion of visual and thermal images using complex extension of EMD

Empirical mode decomposition (EMD) is a fully data driven technique for decomposing signals into their natural scale components. Given its ability to separate spatial frequencies, it is natural to consider EMD for image fusion. However the problem of uniqueness, caused by the empirical nature of the algorithm and its sensitivity to parameters, makes it difficult to perform fusion of data from heterogeneous sources. A recently proposed solution to this problem is to use complex extensions of EMD which guarantees the same number of decomposition levels, that is the uniqueness of the scales. A new fusion rule based on the inherent properties of the decompositions is proposed. The methodology is used to address the fusion of images from different modalities (visual and thermal).