Treść książki
Przejdź do opcji czytnikaPrzejdź do nawigacjiPrzejdź do informacjiPrzejdź do stopki
104Results
37
Figure109:Imagesreconstructedfromnoisydata(SNR120dB)withAlgorithm4for
k1300:δ1100,;150(left);δ1100,;11000(middle);δ1100,;15000(right)
distance
0.65
0.55
0.45
0.35
0.25
0.7
0.6
0.5
0.4
0.3
0.2
50
100
iterationno.
150
200
δ=50,β=50
δ=20,β=50
δ=100,β=50
δ=150,β=50
δ=100,β=500
250
distance
0.9
0.8
0.7
0.6
0.5
0.4
50
100
iterationno.
150
200
δ=100,β=50
δ=100,β=1000
δ=100,β=2000
δ=100,β=5000
δ=200,β=2000
250
relativeerror
0.6
0.5
0.4
0.3
0.2
0.1
50
100
iterationno.
150
200
δ=50,β=50
δ=20,β=50
δ=100,β=50
δ=150,β=50
δ=100,β=500
250
relativeerror
0.9
0.8
0.7
0.6
0.5
0.4
0.3
0.2
0.1
1
50
100
iterationno.
150
200
δ=100,β=50
δ=100,β=1000
δ=100,β=2000
δ=100,β=5000
δ=200,β=2000
250
Figure1010:Distances(left)andrelativeerrors(right)obtainedwithAlgorithm4:(top)
noise-freedata,(bottom)noisydata(SNR120dB)
Likelihood(ML)approachproposedin[52].Assumingthepartitionfunction
Zin(1.12)simplifiestotheformZ1δNz(;),thenormalizedlog-priorcanbe
writtenas:
N
1
lnp(x)1−
2N
;
j11
∑
N
n∈Nj
∑
wjnV(xj−xn,δ)−lnδ−
N
1
lnz(;).
(1.52)