基于小波变换的多模态医学图像的融合方法

摘要

Since the single modal image can′t provide enough information,it is necessary to fuse the complementary images. A medical image fusion method based on discrete wavelet transform(DWT)is proposed. DWT is performed for the multimodal medical images under fusion to obtain the low⁃frequency and high⁃frequency components respectively. A method based on the lo⁃cal regional energy is adopted to fuse low⁃frequency components. The weighted sum method based on difference of the local re⁃gions coefficients is used to fuse the high⁃frequency components. The fusion image is obtained by means of the inverse DWT. The experimental results prove that,in comparison with the similar research methods,the method can enhance the spatial detail expressive ability of the image while ensuring the image quality.%针对单一模态的图像不能提供足够的信息，可以将互补的图像进行融合。提出一种基于小波变换的医学图像融合方法。首先对待融合的医学图像进行小波变换，分别得到低频和高频分量。对于低频分量，采用基于局部区域能量的方法进行融合；对于高频分量，采用基于局部区域系数之差的加权和方法进行融合；最后通过小波逆变换得到融合图像。实验结果表明，相比同类研究方法，该算法在保证图像质量的同时可增强图像的空间细节表现能力。