当前位置: X-MOL 学术Adv. Appl. Clifford Algebras › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-modal Medical Image Fusion Based on Geometric Algebra Discrete Cosine Transform
Advances in Applied Clifford Algebras ( IF 1.5 ) Pub Date : 2022-02-20 , DOI: 10.1007/s00006-021-01197-6
Rui Wang 1 , Nian Fang 1 , Yinmei He 1 , Yanping Li 1 , Wenming Cao 2 , Haiquan Wang 3
Affiliation  

Multi-modal medical image fusion refers to the combination of patient area images obtained under diverse or identical imaging modalities, which improves the clinical applicability and provides more specific disease information for diagnosis. However, most of the existing image fusion algorithms usually divided color images into three channels of R, G, B for processing separately, which ignores the correlation between the channels and easily causes image information loss and blurring. This paper proposes a multi-modal color medical image fusion algorithm based on geometric algebra discrete cosine transform (GA-DCT). The GA-DCT algorithm combines the character of GA, which represents the multi-vector signal as a whole, can improve the quality of the fusion image and avoid a large number of complex operations related to encoding and decoding. Firstly, the source images are divided into several image blocks and expressed in GA multi-vector form; Secondly, we extend the traditional DCT to GA space and propose GA-DCT; Thirdly, we use GA-DCT to decompose the image to obtain AC and DC coefficients and finally a fusion algorithm are used to fuse the images. The experimental results show that the proposed algorithm can get clear and comprehensive fusion image, which also has great advantages under different compression ratios.



中文翻译:

基于几何代数离散余弦变换的多模态医学图像融合

多模态医学图像融合是指在不同或相同的成像模态下获得的患者区域图像的组合,提高了临床适用性,为诊断提供了更具体的疾病信息。然而,现有的大多数图像融合算法通常将彩色图像分成R、G、B三个通道分别处理,忽略了通道之间的相关性,容易造成图像信息丢失和模糊。提出一种基于几何代数离散余弦变换(GA-DCT)的多模态彩色医学图像融合算法。GA-DCT算法结合了GA的特点,将多向量信号作为一个整体来表示,可以提高融合图像的质量,避免大量与编码和解码相关的复杂操作。第一,将源图像划分为若干个图像块,以GA多向量形式表示;其次,我们将传统的DCT扩展到GA空间,提出GA-DCT;第三,我们使用 GA-DCT 对图像进行分解以获得 AC 和 DC 系数,最后使用融合算法对图像进行融合。实验结果表明,所提算法能够得到清晰、全面的融合图像,在不同压缩比下也具有很大优势。

更新日期:2022-02-21
down
wechat
bug