基于多尺度边缘保持分解与PCNN的医学图像融合

Medical Image Fusion Based on Multi-Scale Edge-Preserving Decomposition and PCNN

在医学图像融合过程中,传统多尺度分析方法多采用线性滤波器,由于无法保留图像边缘特征导致分解阶段的强边缘处出现模糊,从而产生光晕。为提高融合图像的视觉感知效果,通过结合多尺度边缘保持分解方法与脉冲耦合神经网络(PCNN),提出一种新的图像融合方法。对源图像进行加权最小二乘滤波分解得到图像的基础层和细节层,采用高斯滤波器对基础层进行二次分解得到低频层和边缘层,将分解过程中每级边缘层和细节层叠加构建高频层,并引入非下采样方向滤波器组进行方向分析。在此基础上,利用改进的空间频率以及区域能量激励PCNN融合高频层和低频层,通过逆变换得到最终的融合图像。实验结果表明,该方法能够突出医学图像的边缘轮廓并增强图像细节,可将更多的显著特征从源图像分离并转移到融合图像中。

In medical image fusion,most traditional multi-scale analysis methods using linear filters fail in protection of edge features,and thus lead to edge halo in the decomposition stage.To improve the visual effects of fused images,this paper proposes a new image fusion method combining multi-scale edge-preserving decomposition and Pulse Coupled Neural Network(PCNN).In this method,the source image is decomposed into the basic layer and the detail layer by Weighted Least Square(WLS)filter,and the basic layer is decomposed into the low-frequency layer and the edge layer by using the Gaussian filter.The edge layer and the detail layer in each scale during decomposition are combined to construct a high-frequency layer,and the Non-subsampled Directional Filter Bank(NDFB)is introduced for the direction analysis.On this basis,the improved spatial frequency and regional energy are used to stimulate PCNN to fuse the high-frequency layer and the low-frequency layer.The final fusion image is obtained through inverse transformation.The experimental results show that this method can highlight the edge contour of the medical images and enhance the image details,which can separate more salient features from the source image and transfer them to the fusion image.