基于多层次多方向分解的医学图像融合算法  

Medical Image Fusion Algorithm Based on Multi-layer and Multi-direction Decomposition

作　　者：宋瑞霞[1] 王孟[1] 王小春[2] 余建德[3] 

机构地区：[1]北方工业大学理学院,北京100144 [2]北京林业大学理学院,北京100083 [3]澳门科技大学资讯科技学院,澳门999078

出　　处：《计算机工程》2017年第10期179-185,共7页Computer Engineering

基　　金：国家自然科学基金(61272026;61571046);澳门科学技术发展基金(097/2013/A3)

摘　　要：传统多模态医学图像融合技术融合后图像的细节表达不清晰、病灶不明显。为此,设计一种V-变换与非下采样Contourlet变换(NSCT)相结合的融合方法。对源图像进行多层次V-分解,使其被分解为轮廓图像和细节图像两部分,对其中的轮廓图像做NSCT变换,在NSCT域中设计融合方案,针对细节图像给出细节信息的融合策略,将融合后的轮廓图像和细节图像叠加,以得到最终融合图像。实验结果表明,与传统离散小波变换、NSCT变换的方法相比,该算法在视觉效果和评价指标方面都有较好的表现。Fused images obtained using the traditional multi-modal medical image fusion technology cannot express details clearly and lesion obviously. In view of this, a new fusion method which combines the V-transform and Non- subsampled Contourlet Transform（NSCT） is proposed. The source images are first decomposed into contour sub-image and detail sub-images by applying the multi-layer V-decomposition, and then NSCT transform is performed on the contour sub-image. Fusion rule in NSCT domain is designed. Fusion strategy for detail information is presented on detail sub-images. The fused image is finally obtained by overlaying the fused contour image and fused detail image together. Experimental results show that the proposed algorithm outperforms the traditional discrete wavelet transform and NSCT transform in both visual effect and evaluation indexes.

关 键 词：图像融合 医学图像 V-系统 多层次V分解 非下采样CONTOURLET变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]