### Table 1: Coefficients fhk;lg of the Markov random field wood model [14].

1997

"... In PAGE 21: ... The 64x64 pixels were divided into groups g1 and g2: g1 contains the pixels in the upper left and lower right of the image, and g2 contains the pixels in the diagonal band running through the center of the image. The prior model for g1 is the wood model of Table1 ; the prior model for g2 uses the same coefficients in Table 1, but with the table rotated by 90 degrees. The cross correlation between groups g1 and g2 is zero.... ..."

Cited by 34

### Table 2. Registration results of Sound Terrain range images.

"... In PAGE 5: ...5) 2,412,693 8.5 Table2 shows the alignment results of the terrain range images using our p-field method. The number of sample points used in the registration is the N in Equation 2.... ..."

### Table 5: Search Strategies used in Image Registration

1992

"... In PAGE 47: ... An example might be in aerial photographs taken at di erent times. Search Strategies: Table5 gives several examples of search strategies and the kinds of problems for which they are used. Alternatively, specialized ar- chitectures have been designed to speed up the performance of certain regis- tration methods.... ..."

Cited by 468

### Table 4: Similarity Metrics used in Image Registration

1992

Cited by 468

### Table 1. The mean volume overlap and surface distance after the affine 4D registration,after the deformable 3D and after spatio-temporal deformable registration.

"... In PAGE 6: ... In order to calculate the overlap of the anatomical structures and the surface distance we used segmented images. Table1... ..."

Cited by 3

### Table 1: Number of sampling locations for various fea- ture types. MRF: Markov Random Field model, IG: in- tensity gradient. Gabor and IG are extracted only from femur images.

2004

"... In PAGE 3: ... Markov Random Field (MRF) texture model ex- tracts features from moderate-sized sampling regions. In the current implementation, the number of sampling lo- cations is set as shown in Table1 . Figure 2 illustrates an example of adaptive sampling at the femoral neck.... ..."

Cited by 4

### Table 2: Gibbs Sampler timings for a binary (G = 2) image (execution time in seconds per iteration on a CM-5 with vector units) 3.2.1 Iterative Gaussian Markov Random Field Sampler The Iterative Gaussian Markov Random Field Sampler is similar to the Gibbs Sampler, but instead of the binomial distribution, as shown in step 3.2 of Algorithm 1, we use the continuous Gaussian Distribution as the probability function. For a neighborhood model N, the conditional probability function for a GMRF is:

in Scalable Data Parallel Algorithms for Texture Synthesis and Compression using Gibbs Random Fields

1995

"... In PAGE 14: ...omplexity, and steps 2.3 and 2.4 in O(G np ) computational time, yielding a computation complexity of Tcomp(n; p) = O( n (G+jNsj) p ) and communication complexity of 8 gt; lt; gt; : Tcomm(n; p) = O(jNsj qnp ), on the CM-2; Tcomm(n; p) = O(jNsj( (p) + qnp )), on the CM-5, per iteration for a problem size of n = I J. Table 1 shows the timings of a binary Gibbs sampler for model orders 1, 2, and 4, on the CM-2, and Table2 shows the corresponding timings for the CM-5. Table 3 presents the timings on the CM-2 for a Gibbs sampler with xed model order 4, but varies the number of gray levels, G.... ..."

Cited by 7

### Table 1 Process outline of the registration of seven standard field images

### Table 1: Fields Observed

"... In PAGE 7: ... These elds are selected at random, subject to the constraints that they have low extinction in the Burstein amp; Heiles (1982) map, and be free of bright (R lt; 14) stars or galaxies. The characteristics of these control elds are listed in Table1 . Although these control exposures were not taken during the same run as the Coma image, they are all in the same lter band, all are taken at prime focus of either the KPNO or CTIO 4-meter telescopes, and all using thinned Tek1024 CCDs.... In PAGE 8: ...77 pixels. The FWHM of the processed control elds, listed in Table1 , range from 2.... In PAGE 8: ...7.7 mag arcsec?2); the control elds have noise levels from 29.19 to 29.37 mag per pixel. The noise power spectra, not just the RMS levels, are matched. In Table1 we list the noise spectral densities of the Coma and matched control- eld images. These numbers give the amplitude of the at part of the noise power spectrum in our images; recall that some short-wavelength noise is removed by the bilinear interpolation during image registration.... In PAGE 12: ...ssuming an R-band extinction AR = 2:5EB?V . AR is only 0.03 mag in the Coma eld itself. The detected R magnitudes of all objects in each control elds are adjusted brightward by the relative extinction corrections listed in Table1 . These corrections bring the control elds into agreement with the Coma extinction, not to zero extinction.... ..."