A fusion method for visible light and infrared images based on FFST and compressed sensing

In order to enhance the efficiency in the process of image fusion, a novel fusion algorithm of infrared and visible images is proposed. First of all, fast finite shearlet transform (FFST) on both the infrared image and the visible image is performed to get a low frequency sub-band and a certain amount of high frequency sub-bands. Then, the Sum Modified Laplacian (SML) fusion algorithm is used for the low frequency sub-band. For the each directional high frequency sub-bands, the compressive measurements are obtained by the block Compressed Sensing (CS). And the measurements are fused with the rule of maximum variance. The fused measurements are reconstructed through the Smoothed Projected Landweber (SPL) algorithm. Finally, the fused image is reconstructed by using inverse FFST. Experimental results demonstrate that the proposed algorithm can obtain better fusion effect and improve the operation efficiency.