Bidimentional emphirical mode decomposition based image fusion

The image fusion plays a crucial role in many fields such as remote sensing, medical and robotics applications. This paper is focused on image fusion of images of different focus depth. The aim is to study these concepts and provide simulations and evaluations on various implementations. When performing image fusion the images are decomposed by bi-dimensional Empirical mode decomposition (BEMD) to obtain high frequency coefficients which is used to determine which parts of the input images that makes it into the fused image. The same technique is tested on images of different modality. In this thesis, a novel bi-dimensional Empirical mode decomposition (BEMD) based image fusion scheme is proposed. The BEMD decomposes the source images into intrinsic mode functions (IMFs) and residual components. IMF components of the first signal in the decomposition of the source images are used to generate the fused images using appropriate fusion rule. Performance evaluation of fused images is done by computing fusion quality metrics and the fusion results are compared with other existing fusion schemes. It is seen that the performance of the proposed scheme is better as compared with the existing fusion schemes.