Medical Image Fusion in Compressed Sensing Based on Non-subsampled Contourlet Transform

摘要

In order to get better results and faster speed on medical image fusion, a method based on non-sub sampled contour let transform in compressed sensing was proposed. Because of the large sparsity and sharp contrast between the black and the white of medical images, the energy and average gradient were utilized to design the fusion rules to fuse the low-frequency components and the high-frequency components respectively. The image entropy, relative quality, average gradient, standard deviation and spatial frequency were used to evaluate the fusion results objectively. Experiments show that under the premise of maintaining a certain reconstruction quality the sample rates and calculation amounts are lower, the convergence can be sped up and the fusion results can be improved.