Multi-modal Color Medical Image Fusion Using Quaternion Discrete Fourier Transform

作者：Nawaz Qamar; Xiao Bin^*; Hamid Isma; Jiao Du

来源：Sensing and Imaging, 2016, 17(1): 7.

DOI：10.1007/s11220-016-0131-x

• Color image fusions
• Experimental evaluation
• Frequency domains
• Gray-scale images
• Multi-modal image
• Multimodal image fusions
• Quaternion representation
• State of the art

Multimodal image fusion is a process of combining multiple images, generated by identical or diverse imaging modalities, to get precise inside information about the same body organ. In recent years, various multimodal image fusion algorithms have been proposed to fuse medical image. However, most of them focus on fusing grayscale images. This paper proposes a novel algorithm for the fusion of multimodal color medical images. The proposed algorithm divides source images into blocks, converts each RGB block into quaternion representation and transforms them from special domain to frequency domain by applying quaternion discrete Fourier transform. The fused coefficients are obtained by calculating and comparing contrast values of corresponding coefficients in transformed blocks. The resultant fused image is reconstructed by merging all the blocks after applying inverse quaternion discrete Fourier transform on each block. Experimental evaluation demonstrates that the proposed algorithm qualitatively outperforms many existing state-of-the-art multimodal image fusion algorithms.

• 出版日期2016