An Image Fusion Method Based on Wavelet Transform and ICM

The purpose of image fusion is to merge the redundant and complementary information of multi-sensor to get a new image which is more propitious to image processing. A novel image fusion method based on wavelet transform and intersecting cortical model (ICM) is proposed in this paper. The original image is decomposed into high-frequency subimage and low-frequency subimage firstly. A region-based method is applied to high-frequency subimage to get the fused high-frequency subimage. For the low-frequency subimage, the edge metric is computed firstly, then the edge metric is used as the input of ICM and we can get the firing map of two subimage. By comparing the firing times of each nerve cell, the fused low-frequency subimage is obtained. The fused image is then obtained by inverse wavelet transform. The effectiveness of the proposed algorithm is verified by the experimental results.