[image fusion] MRI-CT image fusion based on gradient energy, local energy and PCA fusion rules with matlab code

1 brief introduction

​ Most image fusion algorithms only fuse one feature of the image , It is easy to cause loss of other characteristic information . In response to this problem , In this paper, a new method based on Haar wavelet transform is proposed , Consider gradient energy 、 Local energy 、 PCA Three characteristics , The method of combining regional variance and transform coefficient is used for fusion , Finally, the fusion result is obtained by inverse Haar wavelet transform .

2 Part of the code

clearx1=imread('ct.jpg');subplot(221);imshow(x1);title('ct Images ');x2=imread('mri.jpg');subplot(222);imshow(x2);title('mri Images ');X1=double(x1);X2=double(x2);% First level the two images db4 Wavelet transform [ca1,ch1,cv1,cd1]=dwt2(X1,'db4');subplot(223);b1=uint8([ca1 ch1;cv1 cd1]);imshow(b1);title('ct Image level db4 Wavelet decomposition ');[ca2,ch2,cv2,cd2]=dwt2(X2,'db4');subplot(224);b2=uint8([ca2 ch2;cv2 cd2]);imshow(b2);title('mri Image level db4 Wavelet decomposition ');% Merge according to certain fusion rules ca=dipinchuli(ca1,ca2);ch=PCAfusion(ch1,ch2);cv=PCAfusion(cv1,cv2);cd=PCAfusion(cd1,cd2);figure;subplot(121);imshow(uint8([ca ch;cv cd]));title(' Wavelet coefficients after fusion ');X=idwt2(ca,ch,cv,cd,'db4');subplot(122);imshow(uint8(X));title(' Reconstructed image after fusion ');

3 Simulation results

4 reference

[1] Zhanghongyi , Ellen pau , Linyongping . Image fusion algorithm based on gradient and energy [J]. Journal of Xiamen Institute of technology , 2010, 18(1):5.

About bloggers ： Good at intelligent optimization algorithms 、 Neural networks predict 、 signal processing 、 Cellular automata 、 The image processing 、 Path planning 、 UAV and other fields Matlab Simulation , relevant matlab Code problems can be exchanged by private letter .

Some theories cite network literature , If there is infringement, contact the blogger to delete .