Author Affiliations
1Department of Basic Teaching, Suzhou Vocational and Technical College, Suzhou, Anhui 234099, China2Department of Computer Information, Suzhou Vocational and Technical College, Suzhou, Anhui 234099, Chinashow less
Fig. 1. Structure diagram of GANs
Fig. 2. Generate network structure diagram
Fig. 3. Structure of densely connected blocks
Fig. 4. Discriminant network model
Fig. 5. Comparison of butterfly reconstruction effect. (a) Original image; (b)method in Ref. [23]; (c) method in Ref. [5]; (d) method in Ref. [7]; (e) method in Ref. [8]; (f) method in Ref. [13]; (g) method in Ref. [16]; (h)proposed method
Fig. 6. Comparison of lenna reconstruction effect. (a) Original image; (b)method in Ref. [23]; (c) method in Ref. [5]; (d) method in Ref. [7]; (e) method in Ref. [8]; (f) method in Ref. [13]; (g) method in Ref. [16]; (h)proposed method
Fig. 7. Comparison of 253027 reconstruction effect. (a) Original image; (b)method in Ref. [23]; (c) method in Ref. [5]; (d) method in Ref. [7]; (e) method in Ref. [8]; (f) method in Ref. [13]; (g) method in Ref. [16]; (h)proposed method
Fig. 8. Comparison of barbara reconstruction effect. (a) Original image; (b)method in Ref. [23]; (c) method in Ref. [5]; (d) method in Ref. [7]; (e) method in Ref. [8]; (f) method in Ref. [13]; (g) method in Ref. [16]; (h)proposed method
Fig. 9. Comparison of the number of parameters
Fig. 10. Comparison of image edge extraction before and after convolution operation. (a)--(c) Images after convolution operation; (d)--(f) corresponding images before convolution operation
Dataset | Scale | Method inRef. [23] | Method inRef. [5] | Method inRef. [7] | Method inRef.[8] | Method inRef.[13] | Method inRef. [16] | Proposedmethod |
---|
Set5 | 234 | 33.5730.4229.00 | 31.39 | 36.6131.9930.27 | 36.7232.8530.56 | 37.4433.4531.12 | 37.7133.9031.62 | 37.9334.1131.79 | Set14 | 234 | 30.2427.5526.00 | 28.31 | 32.2829.1327.32 | 32.4529.3027.50 | 33.0329.7728.01 | 33.2329.9228.14 | 33.4430.0828.35 | B100 | 234 | 29.4927.1125.88 | 27.83 | 30.9728.1026.79 | 31.4528.3826.96 | 31.5728.9627.22 | 31.9029.0127.38 | 32.1329.3027.57 | Urban100 | 234 | 26.7624.5923.30 | 25.35 | 28.9426.0124.45 | 29.4926.3324.65 | 30.6927.2325.09 | 30.8527.4425.36 | 30.9727.5825.63 |
|
Table 1. Comparison of PSNR between proposed algorithm and mainstream algorithm on four test sets unit:dB
Dataset | Scale | Method inRef. [23] | Method inRef. [5] | Method inRef. [7] | Method inRef.[8] | Method inRef.[13] | Method inRef. [16] | Proposedmethod |
---|
Set5 | 234 | 0.92930.86710.8115 | 0.8819 | 0.95000.90030.8622 | 0.95390.90880.8630 | 0.95760.92090.8839 | 0.95770.92280.8871 | 0.96030.92390.8877 | Set14 | 234 | 0.86790.77380.7026 | 0.7937 | 0.90700.81770.7487 | 0.90570.82090.7521 | 0.91300.83250.7669 | 0.91310.83290.7678 | 0.91430.83260.7687 | B100 | 234 | 0.84290.73830.6680 | 0.7458 | 0.88540.78440.7069 | 0.88800.78570.7100 | 0.89550.79680.7247 | 0.89580.79810.7266 | 0.89930.79940.7280 | Urban100 | 234 | 0.84110.73380.6567 | 0.7554 | 0.89220.79080.7183 | 0.89510.79760.7233 | 0.91350.82660.7509 | 0.91500.82460.7537 | 0.91640.82990.7551 |
|
Table 2. Comparison of SSIM between proposed algorithm and mainstream algorithm on four test sets
Dataset | Scale | Method inRef. [23] | Method inRef. [5] | Method inRef. [7] | Method inRef.[8] | Method inRef.[13] | Method inRef. [16] | Proposedmethod |
---|
Set5 | 234 | --- | 0.47 | 0.580.320.24 | 2.192.232.19 | 0.130.140.12 | 0.210.190.22 | 0.110.130.12 | Set14 | 234 | --- | 0.51 | 0.840.560.38 | 4.324.404.39 | 0.250.260.25 | 0.270.230.21 | 0.220.210.20 | B100 | 234 | --- | 0.52 | 0.590.330.26 | 2.512.582.51 | 0.160.210.21 | 0.300.270.25 | 0.130.170.15 | Urban100 | 234 | --- | 0.69 | 2.961.671.21 | 22.1219.3518.46 | 0.981.081.06 | 1.011.001.03 | 0.910.981.02 |
|
Table 3. Comparison of time consumption between proposed algorithm and mainstream algorithms on four test sets unit:s