An improved coupled dictionary and multi-norm constraint fusion method for CT/MR medical images

To solve the problems that a single dictionary is difficult to obtain accurate sparse representation of images, and a single norm as activity level measurement of the source image block does not preserve more details of the image, leading to poor image fusion results, this paper proposes an improved coupled dictionary and multi-norm constraint image fusion method for CT/MR images. In the paper, CT and MR image pairs are used as training set, and the coupled CT dictionary and the MR dictionary are obtained by using the improved K-SVD algorithm respectively. The fusion dictionary is obtained by combining coupled CT dictionary and MR dictionary with the spatial domain method. First, the registered source images are compiled into the column vectors and the means are removed. The exact sparse representation coefficients are calculated by the CoefROMP algorithm under the fusion dictionary. Then the multi-norm constraint of the sparse representation coefficients is taken as activity level measurement of the source image blocks, and the sparse representation coefficients are fused by the rule of “choosing the maximum”. Finally, the fused images are obtained by reconstruction. The experimental results show that the proposed method in this paper can effectively retain more image details, improve fusion image contrast and clarity, focal prominent, accelerate the running speed of the algorithm and be applied to clinical diagnosis and auxiliary treatment.