An Image Fusion Algorithm Based on Non-subsampled Shearlet Transform and Compressed Sensing

In order to obtain rapid fusion speed, an image fusion algorithm based on Nonsubsampled Shearlet Transform (NSST) and Compressed Sensing (CS) is presented. The source images are decomposed with NSST. Based on local area energy, the low-frequency coefficients are fused. The high-frequency coefficients are compressed, fused and reconstructed with CS. Based on global gradient, the measurements of high-frequency coefficients are fused. The inverse NSST is used to get the final fused image. During the fusion course, only the compressed data of the high-frequency coefficients are fused, so the fusion effects can’t be affected. At the same time, the running time can be reduced. In this paper, the multi-focus images are used to verify the algorithm effectiveness. The simulation results indicate that the fusion image can be achieved without prior knowledge of the original images. Although the fusion quality is sacrificed when the sampling rate becomes higher, the algorithm can significantly reduce the time cost and hardware requirements. The algorithm provides an idea on how to satisfy the real time requirements in the fusion system.