C1
C2
C3
C4
C5
C6
3
1
5
64
192
ReLU
C7
C8
C9
C10
32
16
Algorithm MFEnet training and testing algorithms
Training
Input:Training set source image Ii
Output:Reconstructed image Io
1)Randomly select m source images from the training set I1,⋯,Im
2)Input m source images into the feature extraction module to generate source image features F
3)Input F into the reconstruction module to generate a reconstructed image Io
4)Use Adam optimizer to update the parameters of the feature extraction module and reconstruction module:
∇θ1WHIo-IiF2+α∇Io-∇IiF2
5)If the number of iterations is equal to epoch,the training ends,otherwise repeat steps 1)-4)
Testing
Input:Testing set source images I1 and I2
Output:Fused image If
1)Input I1 and I2 into the feature extraction module to get the source image features F1 and F2
2)Input I1 and I2 into the edge enhancement module to get the source image edge maps E1 and E2
3)Input F1 and F2 into the fusion module and the reconstruction module to obtain the intermediate fusion image Ifm
4)Combine Ifm,E1,and E2 to get the final fusion image If
FW-Net
GF
CNN
NSCT
NSCT-PRPCNN
Proposed method
0.8182
0.8595
0.8637
0.873
0.8448
0.8741
0.7776
0.8910
1.1123
0.969
1.2690
1.2879
0.5108
0.6612
0.5717
0.6160
0.6350
0.7412
0.0072
0.0167
0.0134
0.0155
0.0122
0.0069
0.6600
0.8407
0.7165
0.7311
0.7575
0.8422
0.0199
0.0912
9.601
3.43
0.0189
Addition[35]
Average[36]
Weighted average[37]
Max value[34]
0.8728
0.8689
0.8708
1.1951
1.1703
1.2456
0.7422
0.7270
0.7337
0.0071
0.0068
0.0073
0.8116
0.8095
0.8119
Set citation alerts for the article
Please enter your email address
CancelConfirm