Image fusion method based on the local neighborhood feature and nonsubsampled contourlet transform

In order to improve image fusion quality, a novel image fusion method based on the local neighborhood feature and NSCT is proposed. Firstly, the NSCT is performed on the source image to obtain the low frequency subband and the high frequency subbands in each direction; Secondly, a weighted fusion strategy based on the gray mean deviation is adopted for the low frequency subband, and a weighted fusion strategy based on the local region energy is used for the high frequency subbands; Finally, the fused image is obtained by NSCT inverse transform. The simulation results show that the method we proposed has good fusion effect on multi-focus images, medical images and infrared and visible light images.