Fusion of the Infrared and Color Visible Images Using Bidimensional EMD

摘要

A novel color fusion method is proposed for infrared and color visible images which based on the Bidimensional Empirical Model Decomposition (BEMD). Firstly, the original color visible image is transformed into the IHS color space. Then, the intensity component (I) and infrared image are decomposed into a set of Intrinsic Mode Functions (IMFs) and residues respectively by means of the BEMD. The gray scope of IMFs obtained from the infrared image is adjusted to match the scope of IMFs obtained from the intensity component of visible image. The IMFs and residues are fused by the weighted average algorithm. The fused IMFs and residue are reconstructed into the new intensity component. At last, the IHS color space included new intensity component is transformed back into the RGB color space. Compared with the traditional image fusion methods: DWT and PCA, the experimental results demonstrate that this proposed method not only have a superior fusion performance but also can effectively produce a color fused image with the similar natural characteristics as the original color visible image .