We are trying to register images using the TranslationTransform, GradientDescentStepOptimizer, and the Mean Square Image to Image metric, but are having a problem with the convergence of the method, in that the metric values do
<br>not seem to converge to a minimum at all. The original images are 0 - ~6500 in intensity value range.<br><br>We have tried registration using the ITK Examples file ImageRegistration1.cxx and have tried adjusting the values for the Optimizer, maximum step length and minimum step length. Any suggestions for optimizer parameter selection?
<br><br>// optimizer->SetMaximumStepLength( 4.00 ); <br>// optimizer->SetMinimumStepLength( 0.01 );<br> optimizer->SetMaximumStepLength( 0.01 ); <br> optimizer->SetMinimumStepLength( 0.0001 );<br><br>0 =
2.72438e+006 : [-2.08739, -3.41216]<br>1 = 1.73376e+006 : [-1.98374, -1.41484]<br>2 = 2.01186e+006 : [-2.5951, -2.2062]<br>3 = 1.70106e+006 : [-3.36987, -2.83844]<br>4 = 1.6264e+006 : [-3.03848, -2.46403]<br>5 = 1.64197e+006
: [-2.67566, -2.11999]<br>6 = 1.70971e+006 : [-2.86588, -2.28223]<br>7 = 1.66576e+006 : [-3.04977, -2.45159]<br>8 = 1.64041e+006 : [-2.95655, -2.36831]<br>9 = 1.65473e+006 : [-2.99801, -2.41508]<br>10 = 1.65153e+006 : [-
3.01273, -2.47582]<br>11 = 1.64687e+006 : [-2.99193, -2.4525]<br>12 = 1.6475e+006 : [-2.96613, -2.47014]<br>13 = 1.64447e+006 : [-2.96402, -2.50132]<br>14 = 1.64206e+006 : [-2.98953, -2.51937]<br>15 = 1.64255e+006 : [-3.01521
, -2.53718]<br>16 = 1.64318e+006 : [-3.04244, -2.55252]<br>17 = 1.6372e+006 : [-3.07013, -2.567]<br>18 = 1.63179e+006 : [-3.09843, -2.58026]<br>19 = 1.62691e+006 : [-3.12752, -2.59168]<br>20 = 1.62251e+006 : [-3.15762, -2.60005
]<br>21 = 1.61852e+006 : [-3.18874, -2.6029]<br>22 = 1.61484e+006 : [-3.2191, -2.5955]<br>23 = 1.61146e+006 : [-3.24348, -2.57595]<br>24 = 1.60868e+006 : [-3.26375, -2.55217]<br>25 = 1.60643e+006 : [-3.28371, -2.52812]<br>
26 = 1.60444e+006 : [-3.30364, -2.50405]<br>27 = 1.60269e+006 : [-3.32351, -2.47993]<br>28 = 1.60117e+006 : [-3.31086, -2.47077]<br>29 = 1.60208e+006 : [-3.29818, -2.46164]<br>30 = 1.60315e+006 : [-3.28548, -2.45253]<br>31 =
1.60439e+006 : [-3.27277, -2.44345]<br>32 = 1.60579e+006 : [-3.26002, -2.43441]<br>33 = 1.60736e+006 : [-3.24725, -2.42541]<br>34 = 1.6091e+006 : [-3.23444, -2.41646]<br>35 = 1.61101e+006 : [-3.22159, -2.40757]<br>36 = 1.61309e+006
: [-3.20869, -2.39876]<br>37 = 1.61534e+006 : [-3.19573, -2.39003]<br>38 = 1.61777e+006 : [-3.18269, -2.38143]<br>39 = 1.62038e+006 : [-3.16955, -2.37297]<br>40 = 1.62317e+006 : [-3.15627, -2.36474]<br>41 = 1.62614e+006 : [-
3.1428, -2.35682]<br>42 = 1.6293e+006 : [-3.12903, -2.34942]<br>43 = 1.63265e+006 : [-3.11478, -2.34303]<br>44 = 1.63618e+006 : [-3.09962, -2.33923]<br>45 = 1.63979e+006 : [-3.08574, -2.34639]<br>46 = 1.64205e+006 : [-3.08088
, -2.36125]<br>47 = 1.64154e+006 : [-3.0654, -2.36335]<br>Result =<br> Translation X = -3.0654<br> Translation Y = -2.36335<br> Iterations = 49<br> Metric value = 1.64479e+006<br><br>