International Journal of Applied Mathematics and Machine LearningAuthor's: Liu Shuaiqi, Zhang Tao, Zhao Jie, Li Huiya and Wang Xuehu
Pages: [13] - [30]
Received Date: May 20, 2015
Submitted by: Haitao Xu.
DOI: http://dx.doi.org/10.18642/ijamml_7100121500
Many fusion methods have been proposed to fuse medical image, but these approaches alway lead to fusion image distortion or image information loss. To overcome the above disadvantages, combined with nonsubsampled shearlet transform (NSST) and spiking cortical model (SCM), a new medical image fusion is proposed. First, NSST is utilized for decomposition of the source images. Secondly, the low and high frequency coefficients of NSST are all fused by fired map of improved SCM (ISCM), which motivated by larger sum-modified-Laplacian (SML). Finally, the fusion image is gained by inverse NSST. The algorithm can both preserve the information of the source images well and suppress pixel distortion. Experimental results demonstrate that the proposed method outperforms the state-of-the-art fusion methods.
medical image fusion, nonsubsampled shearlet transform, spiking cortical model.
