### Table 1: PSNR Improvements of the Images Reconstructed with Various Algorithms.

1997

"... In PAGE 4: ... Images reconstructed with these algorithms were then compared with each other. Table1 shows their PSNR improvement, with respect to the JPEG-decoded blocky image. The proposed approach is obviously superior.... ..."

Cited by 5

### Table 1: PSNR Improvements of the Images Reconstructed with Various Algorithms.

1997

"... In PAGE 4: ... Images reconstructed with these algorithms were then compared with each other. Table1 shows their PSNR improvement, with respect to the JPEG-decoded blocky image. The proposed approachisobviously superior.... ..."

Cited by 5

### Table 2: Comparison of image reconstruction using PCA and ICA

2003

"... In PAGE 5: ... Therefore, the basis depends on the number of components and on the number of sub- images. This relation is not linear, as exempli ed by the results shown in Table2 . This table describes an example of reconstructed images using PCA (left-side) and ICA (right-side), with 5,10,15,20,25 components.... ..."

### Table 1: PSNR results for different images and reconstruction techniques.

"... In PAGE 8: ... The pairs used are Foreman frames 156 and 155 (CIF), Stefan frames 87 and 86 (SIF), News frames 90 and 89 (CIF), Table frames 49 and 48 (SIF), Coastguard frames 73 and 71 (CIF), Mother Daughter frames 59 and 57 (QCIF), Weather frames 19 and 17 (CIF). The results shown in Table1 are given for both the strategies which use the weighted average of all reconstructions and the strategies which use the parameter with the highest probability for reconstruction. Images from the pairs from Foreman and News are shown in Figure 3 and Figure 4.... ..."

### Table 1: PSNR and COR values for the color image reconstructions.

2007

"... In PAGE 4: ... 2(f). Table1 shows the PSNR and COR values for bicubic interpolation, the method in [20], and the best reconstruction obtained by the proposed method. From this table it is clear that the proposed method outperforms all previous methods both in terms of both the PSNR and correlation of the high frequency components metrics.... ..."

Cited by 1

### Table 1. PSNR and COR values for the color image reconstructions. PSNR COR

"... In PAGE 9: ... Bicubic interpolation of each band was used as a reference method for comparison. Table1 depicts the resulting PSNR and COR values for all the re- constructed images. The table clearly shows that the proposed methods performs better than bicubic interpolation and that using a local image model provides considerably better results than using a global image one.... ..."

### Table 5: The results of the super-resolution image reconstruction.

"... In PAGE 17: ...(0; 0); (0; 2); (1; 1); (1; 3); (2; 0); (2; 2); (3; 1); (3; 3)g, see Figure 5. As in x4.2.2, the tensor product of the lowpass lter m in Example 2 is used to generate the low-resolution images, and white noises at SNR = 40dB are added. Table5 shows the results of the least squares model, and Algorithms 2 and 3 with symmetric boundary conditions. The optimal in Step 2 and Step 4 are 0:0121 and 0:0105 for the least squares method and 0:0170 and 0:0161 for Algorithm 2 respectively.... ..."

### Table 5: The results of the super-resolution image reconstruction.

"... In PAGE 17: ...(0; 0); (0; 2); (1; 1); (1; 3); (2; 0); (2; 2); (3; 1); (3; 3)g, see Figure 5. As in x4.2.2, the tensor product of the lowpass lter m in Example 2 is used to generate the low-resolution images, and white noises at SNR = 40dB are added. Table5 shows the results of the least squares model, and Algorithms 2 and 3 with symmetric boundary conditions. The optimal in Step 2 and Step 4 are 0:0121 and 0:0105 for the least squares method and 0:0170 and 0:0161 for Algorithm 2 respectively.... ..."

### TABLE II Notations Commonly Used in Astronomical Image Reconstruction

in Cross Log Entropy Maximization and Its Application to Ringing Suppression in Image Reconstruction