...
 
Commits (36)
This diff is collapsed.
Binary files a/Documentation/SoftwareGuide/Art/Cube_HPX.eps and /dev/null differ
#FIG 3.2
Landscape
Center
Inches
Letter
100.00
Single
-2
1200 2
6 975 1725 6600 2550
6 3075 1725 4500 2550
6 3825 1950 4425 2325
4 1 0 50 0 0 12 0.0000 0 135 135 4125 2325 Y\001
4 1 0 50 0 0 12 0.0000 0 180 465 4125 2100 Image\001
-6
6 3150 1950 3750 2325
4 1 0 50 0 0 12 0.0000 0 180 585 3450 2100 Casting\001
4 1 0 50 0 0 12 0.0000 0 135 405 3450 2325 Filter\001
-6
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
4500 2550 4500 1725 3075 1725 3075 2550 4500 2550
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
4425 2475 4425 1800 3825 1800 3825 2475 4425 2475
-6
6 5175 1725 6600 2550
6 5325 1950 5775 2325
4 1 0 50 0 0 12 0.0000 0 135 405 5550 2100 Filter\001
4 1 0 50 0 0 12 0.0000 0 135 120 5550 2325 B\001
-6
6 5925 1950 6525 2325
4 1 0 50 0 0 12 0.0000 0 180 465 6225 2100 Image\001
4 1 0 50 0 0 12 0.0000 0 135 120 6225 2325 Z\001
-6
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
6600 2550 6600 1725 5175 1725 5175 2550 6600 2550
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
6525 2475 6525 1800 5925 1800 5925 2475 6525 2475
-6
6 975 1725 2400 2550
6 1125 1950 1575 2325
4 1 0 50 0 0 12 0.0000 0 135 405 1350 2100 Filter\001
4 1 0 50 0 0 12 0.0000 0 135 135 1350 2325 A\001
-6
6 1725 1950 2325 2325
4 1 0 50 0 0 12 0.0000 0 180 465 2025 2100 Image\001
4 1 0 50 0 0 12 0.0000 0 135 135 2025 2325 X\001
-6
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
2325 2475 2325 1800 1725 1800 1725 2475 2325 2475
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
2400 2550 2400 1725 975 1725 975 2550 2400 2550
-6
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
2325 2175 3075 2175
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
4425 2175 5175 2175
-6
6 5175 3000 6600 3825
6 5325 3225 5775 3600
4 1 0 50 0 0 12 0.0000 0 135 405 5550 3375 Filter\001
4 1 0 50 0 0 12 0.0000 0 135 120 5550 3600 B\001
-6
6 5925 3225 6525 3600
4 1 0 50 0 0 12 0.0000 0 180 465 6225 3375 Image\001
4 1 0 50 0 0 12 0.0000 0 135 120 6225 3600 Z\001
-6
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
6600 3825 6600 3000 5175 3000 5175 3825 6600 3825
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
6525 3750 6525 3075 5925 3075 5925 3750 6525 3750
-6
6 975 3000 2400 3825
6 1125 3225 1575 3600
4 1 0 50 0 0 12 0.0000 0 135 405 1350 3375 Filter\001
4 1 0 50 0 0 12 0.0000 0 135 135 1350 3600 A\001
-6
6 1725 3225 2325 3600
4 1 0 50 0 0 12 0.0000 0 180 465 2025 3375 Image\001
4 1 0 50 0 0 12 0.0000 0 135 135 2025 3600 X\001
-6
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
2325 3750 2325 3075 1725 3075 1725 3750 2325 3750
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
2400 3825 2400 3000 975 3000 975 3825 2400 3825
-6
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
2325 3450 3965 3451
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
4342 3444 5175 3450
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
4500 3825 4500 3000 3075 3000 3075 3825 4500 3825
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 0 0 9
4350 3075 3225 3075 3225 3300 3975 3300 3972 3562 3233 3554
3225 3750 4350 3750 4350 3075
4 1 0 50 0 0 12 0.0000 0 180 615 3639 3232 Adaptor\001
4 1 0 50 0 0 12 0.0000 0 135 135 4164 3488 Y\001
set terminal postscript portrait eps color "Times Roman" 12
set xlabel "Iteration No."
set ylabel "Mean Squares Metric"
set output "ImageRegistration1TraceMetric.eps"
plot "ImageRegistration1OutputCleaned.txt" using 1:2 notitle with lines lt 1, "ImageRegistration1OutputCleaned.txt" using 1:2 notitle with points lt 0 pt 12 ps 1
set xlabel "X Translations (mm)"
set ylabel "Y Translations (mm)"
set parametric
set size square
set output "ImageRegistration1TraceTranslations.eps"
plot "ImageRegistration1OutputCleaned.txt" using 3:4 notitle with lines lt 1, "ImageRegistration1OutputCleaned.txt" using 3:4 notitle with points lt 0 pt 12 ps 1
#FIG 3.2
Landscape
Center
Metric
A4
100.00
Single
-2
1200 2
5 1 0 1 0 7 50 0 -1 0.000 0 0 1 0 5482.500 2542.500 5670 2655 5265 2565 5670 2430
1 1 1.00 45.00 90.00
6 5745 2325 6720 2700
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
6660 2700 6660 2385 5760 2385 5760 2700 6660 2700
4 1 0 50 0 0 12 0.0000 4 180 750 6210 2610 Optimizer\001
-6
6 5070 3000 6045 3375
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
5985 3330 5985 3015 5085 3015 5085 3330 5985 3330
4 1 0 50 0 0 12 0.0000 4 135 780 5535 3240 Transform\001
-6
6 3945 2550 5070 2925
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
5040 2925 5040 2610 4005 2610 4005 2925 5040 2925
4 1 0 50 0 0 12 0.0000 4 180 885 4545 2835 Interpolator\001
-6
6 4170 1950 4920 2325
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
4905 2295 4905 1980 4185 1980 4185 2295 4905 2295
4 1 0 50 0 0 12 0.0000 4 135 510 4545 2205 Metric\001
-6
6 2475 1950 3600 2325
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
3600 2295 3600 1980 2475 1980 2475 2295 3600 2295
4 1 0 50 0 0 12 0.0000 4 180 930 3060 2205 Fixed Image\001
-6
6 2475 3015 3555 3330
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
3555 3330 3555 3015 2475 3015 2475 3330 3555 3330
4 1 0 50 0 0 12 0.0000 4 180 1080 3015 3240 Moving Image\001
-6
6 7785 1710 9000 2295
2 2 0 1 0 7 50 0 -1 0.000 0 0 -1 0 0 5
7785 1710 9000 1710 9000 2295 7785 2295 7785 1710
4 1 0 50 0 0 12 0.0000 4 135 405 8415 2160 Filter\001
4 1 0 50 0 0 12 0.0000 4 180 750 8415 1935 Resample\001
-6
6 8025 2460 9000 2835
2 4 0 1 0 7 50 0 -1 0.000 0 0 7 0 0 5
8940 2790 8940 2475 8040 2475 8040 2790 8940 2790
4 1 0 50 0 0 12 0.0000 4 135 780 8490 2700 Transform\001
-6
6 9585 1845 10665 2385
2 2 0 1 0 7 50 0 -1 0.000 0 0 -1 0 0 5
9585 1845 10665 1845 10665 2385 9585 2385 9585 1845
4 1 0 50 0 0 12 0.0000 4 135 645 10125 2070 Subtract\001
4 1 0 50 0 0 12 0.0000 4 135 405 10125 2295 Filter\001
-6
6 10980 1935 11835 2340
2 2 0 1 0 7 50 0 -1 0.000 0 0 -1 0 0 5
10980 1935 11835 1935 11835 2340 10980 2340 10980 1935
4 1 0 50 0 0 12 0.0000 4 135 495 11385 2205 Writer\001
-6
6 9585 2970 10665 3510
2 2 0 1 0 7 50 0 -1 0.000 0 0 -1 0 0 5
9585 2970 10665 2970 10665 3510 9585 3510 9585 2970
4 1 0 50 0 0 12 0.0000 4 135 645 10125 3195 Subtract\001
4 1 0 50 0 0 12 0.0000 4 135 405 10125 3420 Filter\001
-6
6 10980 3060 11835 3465
2 2 0 1 0 7 50 0 -1 0.000 0 0 -1 0 0 5
10980 3060 11835 3060 11835 3465 10980 3465 10980 3060
4 1 0 50 0 0 12 0.0000 4 135 495 11385 3330 Writer\001
-6
6 7830 2925 9045 3510
2 2 0 1 0 7 50 0 -1 0.000 0 0 -1 0 0 5
7830 2925 9045 2925 9045 3510 7830 3510 7830 2925
4 1 0 50 0 0 12 0.0000 4 135 405 8460 3375 Filter\001
4 1 0 50 0 0 12 0.0000 4 180 750 8460 3150 Resample\001
-6
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 6210 2970 35 35 6210 2970 6245 2970
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 9225 3150 35 35 9225 3150 9260 3150
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 6930 3240 35 35 6930 3240 6965 3240
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 2250 3195 35 35 2250 3195 2285 3195
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 2205 2115 35 35 2205 2115 2240 2115
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 45.00 90.00
990 3195 1305 3195
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 45.00 90.00
990 2115 1305 2115
2 2 0 1 0 7 50 0 -1 0.000 0 0 -1 0 0 5
135 1935 990 1935 990 2340 135 2340 135 1935
2 2 0 1 0 7 50 0 -1 0.000 0 0 -1 0 0 5
135 2970 990 2970 990 3375 135 3375 135 2970
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 45.00 90.00
2160 2115 2475 2115
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 45.00 90.00
2160 3195 2475 3195
2 2 0 1 0 7 50 0 -1 0.000 0 0 -1 0 0 5
1305 1935 2160 1935 2160 2340 1305 2340 1305 1935
2 2 0 1 0 7 50 0 -1 0.000 0 0 -1 0 0 5
1305 2970 2160 2970 2160 3375 1305 3375 1305 2970
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 3
1 1 1.00 45.00 90.00
4905 2115 6210 2115 6210 2385
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 3
1 1 1.00 45.00 90.00
6210 2700 6210 3195 5985 3195
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 3
1 1 1.00 45.00 90.00
3555 3195 4185 3195 4275 2925
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 45.00 90.00
3600 2115 4185 2115
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 3
1 1 1.00 45.00 90.00
5085 3195 4815 3195 4725 2925
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 45.00 90.00
4545 2610 4545 2295
2 4 0 3 0 0 50 0 -1 0.000 0 0 7 0 0 5
6750 3465 3915 3465 3915 1800 6750 1800 6750 3465
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 45.00 90.00
9000 2025 9585 2025
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 45.00 90.00
9225 3150 9585 3150
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 4
1 1 1.00 60.00 120.00
6210 2970 7290 2970 7290 2655 8055 2655
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 45.00 90.00
8460 2475 8460 2295
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 60.00 120.00
9045 3375 9585 3375
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 45.00 90.00
10665 2115 10980 2115
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 45.00 90.00
10665 3240 10980 3240
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
1 1 1.00 60.00 120.00
6930 3240 7830 3240
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 5
1 1 1.00 60.00 120.00
2250 3195 2250 3780 6930 3780 6930 2025 7785 2025
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 5
1 1 1.00 60.00 120.00
2205 2115 2205 3645 9225 3645 9225 2250 9585 2250
4 1 0 50 0 0 12 0.0000 4 135 540 540 2205 Reader\001
4 1 0 50 0 0 12 0.0000 4 135 540 540 3240 Reader\001
4 1 0 50 0 0 12 0.0000 4 135 570 1710 3240 Smooth\001
4 1 0 50 0 0 12 0.0000 4 135 570 1755 2205 Smooth\001
4 1 0 50 0 0 12 0.0000 4 180 1560 5355 1710 Registration Method\001
4 0 0 50 0 0 12 0.0000 4 135 870 7020 2565 Parameters\001
#FIG 3.2
Landscape
Center
Metric
A4
100.00
Single
-2
1200 2
0 32 #494549
0 33 #8e8e8e
0 34 #494549
0 35 #8e8e8e
0 36 #494549
0 37 #8e8e8e
0 38 #494549
0 39 #8e8e8e
0 40 #494549
0 41 #8e8e8e
0 42 #494549
0 43 #8e8e8e
0 44 #494549
0 45 #8e8e8e
0 46 #494549
0 47 #8e8e8e
0 48 #494549
0 49 #8e8e8e
0 50 #cfcfcf
0 51 #cfcfcf
0 52 #cfcfcf
0 53 #cfcfcf
0 54 #cfcfcf
0 55 #cfcfcf
0 56 #cfcfcf
0 57 #cfcfcf
0 58 #cfcfcf
0 59 #cfcfcf
0 60 #cfcfcf
0 61 #cfcfcf
0 62 #cfcfcf
0 63 #cfcfcf
0 64 #cfcfcf
0 65 #cfcfcf
0 66 #cfcfcf
0 67 #cfcfcf
0 68 #cfcfcf
0 69 #cfcfcf
0 70 #cfcfcf
0 71 #cfcfcf
0 72 #cfcfcf
0 73 #cfcfcf
0 74 #414141
0 75 #868286
0 76 #bec3be
0 77 #868286
0 78 #bec3be
0 79 #dfe3df
0 80 #8e8e8e
0 81 #8e8e8e
0 82 #414141
0 83 #868286
0 84 #bec3be
0 85 #dfe3df
0 86 #c7b696
0 87 #effbff
0 88 #dfcba6
0 89 #aeaaae
0 90 #595559
0 91 #8e8e8e
0 92 #414141
0 93 #868286
0 94 #bec3be
0 95 #dfe3df
0 96 #414141
0 97 #868286
0 98 #bec3be
0 99 #dfe3df
0 100 #868286
0 101 #bec3be
0 102 #dfe3df
0 103 #414141
0 104 #868286
0 105 #bec3be
0 106 #414141
0 107 #bec3be
0 108 #dfe3df
0 109 #414141
0 110 #868286
0 111 #bec3be
0 112 #8e8e8e
0 113 #414141
0 114 #868286
0 115 #bec3be
0 116 #dfe3df
0 117 #414141
0 118 #868286
0 119 #bec3be
0 120 #dfe3df
0 121 #414141
0 122 #868286
0 123 #bec3be
0 124 #dfe3df
5 1 0 1 0 7 50 0 -1 0.000 0 0 1 0 1917.499 5224.285 1144 1480 1939 1401 2795 1503
1 1 1.00 45.00 90.00
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 1135 1482 21 21 1135 1482 1156 1482
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 2799 1502 21 21 2799 1502 2820 1502
2 3 0 2 0 7 50 0 -1 0.000 0 0 -1 0 0 5
599 1240 599 1960 1679 1960 1679 1241 599 1240
2 3 0 2 0 7 50 0 -1 0.000 0 0 -1 0 0 5
2172 1244 2172 1964 3252 1964 3252 1244 2172 1244
3 5 0 1 0 7 50 0 -1 0.000 0 0 0 9
1118 1416 1027 1630 834 1387 793 1769 1253 1925 1122 1646
1418 1778 1475 1551 1220 1617
1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000
1.000
3 5 0 1 0 7 50 0 -1 0.000 0 0 0 9
2759 1448 2787 1678 2499 1564 2654 1916 3131 1821 2877 1645
3199 1610 3135 1386 2948 1571
1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000
1.000
4 0 0 50 0 0 12 0.0000 4 135 90 1040 1420 p\001
4 0 0 50 0 0 12 0.0000 4 135 90 2815 1419 q\001
4 1 0 50 0 0 12 0.0000 4 135 105 1939 1359 T\001
#FIG 3.2 Produced by xfig version 3.2.5-alpha5
Landscape
Center
Metric
A4
100.00
Single
-2
1200 2
0 32 #404040
0 33 #808080
0 34 #c0c0c0
0 35 #e0e0e0
0 36 #808080
0 37 #c0c0c0
0 38 #e0e0e0
0 39 #444444
0 40 #8e8f8e
0 41 #c9c9c9
0 42 #dfd8df
0 43 #f7f3f7
0 44 #dd9d93
0 45 #f1ece0
0 46 #c3c3c3
0 47 #e2c8a8
0 48 #e1e1e1
0 49 #d2d2d2
0 50 #ededed
0 51 #da7a1a
0 52 #f1e41a
0 53 #887dc2
0 54 #d6d6d6
0 55 #8c8ca5
0 56 #4a4a4a
0 57 #8c6b6b
0 58 #5a5a5a
0 59 #636363
0 60 #8e8e8e
0 61 #b79b73
0 62 #4193ff
0 63 #bf703b
0 64 #db7700
0 65 #dab800
0 66 #006400
0 67 #5a6b3b
0 68 #d3d3d3
0 69 #aaaaaa
0 70 #8e8ea4
0 71 #f3b95d
0 72 #89996b
0 73 #646464
0 74 #b7e6ff
0 75 #86c0ec
0 76 #bdbdbd
0 77 #d39552
0 78 #98d2fe
0 79 #8c9c6b
0 80 #f76b00
0 81 #5a6b39
0 82 #8c9c6b
0 83 #8c9c7b
0 84 #184a18
0 85 #adadad
0 86 #f7bd5a
0 87 #636b9c
0 88 #f7f7f7
0 89 #de0000
0 90 #adadad
0 91 #f7bd5a
0 92 #adadad
0 93 #f7bd5a
0 94 #636b9c
0 95 #526b29
0 96 #949494
0 97 #006300
0 98 #00634a
0 99 #7b844a
0 100 #e7bd7b
0 101 #a5b5c6
0 102 #6b6b94
0 103 #846b6b
0 104 #529c4a
0 105 #d6e7e7
0 106 #dedede
0 107 #f3eed3
0 108 #f5ae5d
0 109 #95ce99
0 110 #b5157d
0 111 #eeeeee
0 112 #848484
0 113 #7b7b7b
0 114 #005a00
0 115 #e77373
0 116 #ffcb31
0 117 #29794a
0 118 #de2821
0 119 #2159c6
0 120 #f8f8f8
0 121 #e6e6e6
0 122 #63737b
0 123 #526363
0 124 #186b4a
0 125 #9ca5b5
0 126 #21845a
0 127 #c2c2c2
0 128 #6e6e6e
0 129 #717171
0 130 #aeaeae
0 131 #333333
0 132 #949395
0 133 #747075
0 134 #555555
0 135 #b3b3b3
0 136 #6d6d6d
0 137 #454545
0 138 #e2e2ee
0 139 #94949a
0 140 #dbdbdb
0 141 #a1a1b7
0 142 #9c0000
0 143 #86acff
0 144 #7070ff
0 145 #8c8c8c
0 146 #424242
0 147 #8c8c8c
0 148 #424242
0 149 #8c8c8c
0 150 #424242
0 151 #8c8c8c
0 152 #424242
0 153 #8c8c8c
0 154 #424242
0 155 #8c8c8c
0 156 #424242
6 450 585 2340 2430
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
630 2115 2160 2115
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
675 2160 675 630
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
630 1935 2025 1935
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
630 1755 2025 1755
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
630 1575 2025 1575
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
630 1395 2025 1395
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
630 1215 2025 1215
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
630 1035 2025 1035
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
630 855 2025 855
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
810 2160 810 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
990 2160 990 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
1170 2160 1170 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
1350 2160 1350 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
1530 2160 1530 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
1710 2160 1710 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
1890 2160 1890 675
4 1 0 50 -1 0 12 0.0000 0 180 1410 1350 2385 Fixed Image Grid\001
4 1 0 50 -1 0 12 0.0000 0 135 60 2295 2205 i\001
4 1 0 50 -1 0 12 0.0000 0 180 60 495 765 j\001
-6
6 3915 585 5805 2430
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
4095 2115 5625 2115
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
4140 2160 4140 630
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4095 1935 5490 1935
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4095 1755 5490 1755
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4095 1575 5490 1575
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4095 1395 5490 1395
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4095 1215 5490 1215
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4095 1035 5490 1035
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4095 855 5490 855
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4275 2160 4275 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4455 2160 4455 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4635 2160 4635 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4815 2160 4815 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
4995 2160 4995 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
5175 2160 5175 675
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
5355 2160 5355 675
4 1 0 50 -1 0 12 0.0000 0 180 1605 4815 2385 Moving Image Grid\001
4 1 0 50 -1 0 12 0.0000 0 135 60 5760 2205 i\001
4 1 0 50 -1 0 12 0.0000 0 180 60 3960 765 j\001
-6
6 2700 1305 3420 1530
2 3 0 1 0 7 100 0 20 0.000 0 0 7 0 0 8
2700 1374 2700 1461 3128 1461 3128 1530 3420 1417 3128 1305
3128 1374 2700 1374
-6
6 2700 3285 3420 3510
2 3 0 1 0 7 100 0 20 0.000 0 0 7 0 0 8
2700 3354 2700 3441 3128 3441 3128 3510 3420 3397 3128 3285
3128 3354 2700 3354
-6
6 405 2970 2385 4995
1 3 0 1 0 0 50 -1 20 0.000 1 0.0000 1620 3825 36 36 1620 3825 1656 3825
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
630 4500 2160 4500
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
675 4545 675 3015
4 1 0 50 -1 0 12 0.0000 0 90 105 2295 4590 x\001
4 1 0 50 -1 0 12 0.0000 0 135 105 495 3150 y\001
4 1 0 50 -1 0 12 0.0000 0 180 1005 1440 4770 Fixed Image\001
4 1 0 50 -1 0 12 0.0000 0 195 1725 1440 4950 Physical Coordinates\001
-6
6 4320 3465 5715 4365
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 1 0 2
0 0 1.00 33.65 67.31
4823 4246 5566 3817
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 1 0 2
0 0 1.00 33.65 67.31
4857 4256 4428 3512
4 1 0 50 -1 0 7 0.5236 0 60 75 5656 3824 x\001
4 1 0 50 -1 0 7 0.5236 0 90 60 4379 3628 y\001
4 1 0 50 -1 0 7 0.5236 0 105 630 5291 4150 Fixed Image\001
-6
6 2475 1080 3330 1755
2 1 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
2520 1125 3285 1710
2 1 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
3286 1127 2521 1712
-6
6 3870 2970 5850 4995
1 3 0 1 0 0 50 -1 20 0.000 1 0.0000 5220 3690 36 36 5220 3690 5256 3690
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
4095 4500 5625 4500
2 1 0 2 0 7 50 -1 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
4140 4545 4140 3015
4 1 0 50 -1 0 12 0.0000 0 90 105 5760 4590 x\001
4 1 0 50 -1 0 12 0.0000 0 135 105 3960 3150 y\001
4 1 0 50 -1 0 12 0.0000 0 180 1200 4905 4770 Moving Image\001
4 1 0 50 -1 0 12 0.0000 0 195 1725 4905 4950 Physical Coordinates\001
-6
1 3 0 1 0 0 50 -1 20 0.000 1 0.0000 990 1215 36 36 990 1215 1026 1215
1 3 0 1 0 0 50 -1 20 0.000 1 0.0000 5175 1035 36 36 5175 1035 5211 1035
3 2 0 1 0 7 50 -1 -1 0.000 0 1 0 4
1 1 1.00 60.00 120.00
990 1215 360 2250 1665 2925 1665 3780
0.000 -1.000 -1.000 0.000
3 2 0 1 0 7 50 -1 -1 0.000 0 1 0 4
1 1 1.00 60.00 120.00
5175 3600 5130 2925 5985 1980 5175 1035
0.000 -1.000 -1.000 0.000
3 2 0 1 0 7 50 -1 -1 0.000 0 1 0 4
0 0 1.00 60.00 120.00
1665 3870 2970 4455 4005 3870 5130 3690
0.000 -1.000 -1.000 0.000
4 1 0 50 -1 0 12 0.0000 0 195 1350 3060 3735 Space Transform\001
4 1 0 50 -1 0 12 0.0000 0 135 225 5400 2970 T2\001
4 1 0 50 -1 0 12 0.0000 0 150 225 1845 2880 T1\001
#FIG 3.2
Landscape
Center
Inches
Letter
100.00
Single
-2
1200 2
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 1950 1800 75 75 1950 1800 2025 1800
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 2820 1199 75 75 2820 1199 2895 1199
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 3931 1095 75 75 3931 1095 4006 1095
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 4889 1463 75 75 4889 1463 4964 1463
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 5514 2157 75 75 5514 2157 5589 2157
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 5820 3088 75 75 5820 3088 5895 3088
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 5653 4164 75 75 5653 4164 5728 4164
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 4979 5053 75 75 4979 5053 5054 5053
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 4021 5491 75 75 4021 5491 4096 5491
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 2813 5373 75 75 2813 5373 2888 5373
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 1931 4768 75 75 1931 4768 2006 4768
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 1438 3831 75 75 1438 3831 1513 3831
1 3 0 1 0 0 50 0 20 0.000 1 0.0000 1431 2755 75 75 1431 2755 1506 2755
1 3 1 1 0 7 50 0 -1 4.000 1 0.0000 3600 3300 2230 2230 3600 3300 5830 3300
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
3938 1088 4681 1220
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
4904 1460 5481 1946
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
5511 2166 5917 2824
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
5822 3092 5861 3893
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
5656 4160 5361 4900
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
4979 5046 4368 5505
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
4037 5491 3326 5748
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
2816 5371 2074 5239
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
1930 4775 1351 4289
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
2825 1194 3535 935
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
1954 1779 2440 1201
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
1424 2750 1556 2005
2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2
0 0 1.00 60.00 120.00
1421 3821 1208 3102
This diff is collapsed.
\chapter*{Foreword}
\noindent
Beside the Pleiades (PHR) and Cosmo-Skymed (CSK) systems developments
forming ORFEO, the dual and bilateral system (France - Italy) for
Earth Observation, the ORFEO Accompaniment Program was set up, to
prepare, accompany and promote the use and the exploitation of the
images derived from these sensors.
The creation of a preparatory
program\footnote{http://smsc.cnes.fr/PLEIADES/A\_prog\_accomp.htm} is
needed because of:
\begin{itemize}
\item the new capabilities and performances of the ORFEO systems
(optical and radar high resolution, access capability, data quality,
possibility to acquire simultaneously in optic and radar),
\item the implied need of new methodological developments : new
processing methods, or adaptation of existing methods,
\item the need to realise those new developments in very close
cooperation with the final users for better integration of new
products in their systems.
\end{itemize}
This program was initiated by CNES mid-2003 and will last until mid
2013. It consists in two parts, between which it is necessary to keep
a strong interaction:
\begin{itemize}
\item A Thematic part,
\item A Methodological part.
\end{itemize}
The Thematic part covers a large range of applications (civil and
defence), and aims at specifying and validating value added products
and services required by end users. This part includes consideration
about products integration in the operational systems or processing
chains. It also includes a careful thought on intermediary structures
to be developed to help non-autonomous users. Lastly, this part aims
at raising future users awareness, through practical demonstrations
and validations.
The Methodological part objective is the definition and the
development of tools for the operational exploitation of the
submetric optic and radar images (tridimensional aspects, changes
detection, texture analysis, pattern matching, optic radar
complementarities). It is mainly based on R\&D studies and doctorate
and post-doctorate researches.
In this context, CNES\footnote{http://www.cnes.fr} decided to develop
the \emph{ORFEO ToolBox} (OTB), a set of algorithms encapsulated in a
software library. The goals of the OTB is to capitalise a methological
\textit{savoir faire} in order to adopt an incremental development
approach aiming to efficiently exploit the results obtained in the
frame of methodological R\&D studies.
All the developments are based on FLOSS (Free/Libre Open Source Software) or
existing CNES developments. OTB is distributed under the permissive open
source license Apache v2.0 - aka Apache Software License (ASL) v2.0:\\
\url{http://www.apache.org/licenses/LICENSE-2.0}
OTB is implemented in C++ and is mainly based on
ITK\footnote{http://www.itk.org} (Insight Toolkit).
%
%
% This file in inserted in the Filtering.tex file.
%
%
The drawback of image denoising (smoothing) is that it tends to blur away the
sharp boundaries in the image that help to distinguish between the
larger-scale anatomical structures that one is trying to characterize (which
also limits the size of the smoothing kernels in most applications). Even in
cases where smoothing does not obliterate boundaries, it tends to distort the
fine structure of the image and thereby changes subtle aspects of the
anatomical shapes in question.
Perona and Malik \cite{Perona1990} introduced an alternative to
linear-filtering that they called \emph{anisotropic diffusion}. Anisotropic
diffusion is closely related to the earlier work of Grossberg
\cite{Grossberg1984}, who used similar nonlinear diffusion processes to model
human vision. The motivation for anisotropic diffusion (also called
\emph{nonuniform} or \emph{variable conductance} diffusion) is that a Gaussian
smoothed image is a single time slice of the solution to the heat equation,
that has the original image as its initial conditions. Thus, the solution to
\begin{equation} \frac{\partial g(x, y, t) }{\partial t} = \nabla \cdot \nabla
g(x, y, t), \end{equation} where $g(x, y, 0) = f(x, y)$ is the input image, is
$g(x, y, t) = G(\sqrt{2t}) \otimes f(x, y)$, where $G(\sigma)$ is a Gaussian
with standard deviation $\sigma$.
Anisotropic diffusion includes a variable conductance term that, in turn,
depends on the differential structure of the image. Thus, the variable
conductance can be formulated to limit the smoothing at ``edges'' in images, as
measured by high gradient magnitude, for example. \begin{equation} g_{t} = \nabla \cdot
c(\left| \nabla g \right|) \nabla g, \label{eq:aniso} \end{equation} where, for
notational convenience, we leave off the independent parameters of $g$ and use
the subscripts with respect to those parameters to indicate partial
derivatives. The function $c(|\nabla g|)$ is a fuzzy cutoff that reduces the
conductance at areas of large $|\nabla g|$, and can be any one of a number of
functions. The literature has shown \begin{equation} c(|\nabla g|) =
e^{-\frac{|\nabla g|^{2}}{2k^{2}}} \end{equation} to be quite effective.
Notice that conductance term introduces a free parameter $k$, the {\em
conductance parameter}, that controls the sensitivity of the process to edge
contrast. Thus, anisotropic diffusion entails two free parameters: the
conductance parameter, $k$, and the time parameter, $t$, that is analogous to
$\sigma$, the effective width of the filter when using Gaussian kernels.
Equation \ref{eq:aniso} is a nonlinear partial differential equation that can
be solved on a discrete grid using finite forward differences. Thus, the
smoothed image is obtained only by an iterative process, not a convolution or
non-stationary, linear filter. Typically, the number of iterations required
for practical results are small, and large 2D images can be processed in
several tens of seconds using carefully written code running on modern, general
purpose, single-processor computers. The technique applies readily and
effectively to 3D images, but requires more processing time.
In the early 1990's several research groups \cite{Gerig1991,Whitaker1993d}
demonstrated the effectiveness of anisotropic diffusion on medical images. In
a series of papers on the subject
\cite{Whitaker1993,Whitaker1993b,Whitaker1993c,Whitaker1993d,Whitaker-thesis,Whitaker1994},
Whitaker described a detailed analytical and empirical analysis, introduced a
smoothing term in the conductance that made the process more robust, invented a
numerical scheme that virtually eliminated directional artifacts in the
original algorithm, and generalized anisotropic diffusion to vector-valued
images, an image processing technique that can be used on vector-valued medical
data (such as the color cryosection data of the Visible Human Project).
For a vector-valued input $\vec{F}:U \mapsto \Re^{m}$ the process takes the
form \begin{equation} \vec{F}_{t} = \nabla \cdot c({\cal D}\vec{F}) \vec{F},
\label{eq:vector_diff} \end{equation} where ${\cal D}\vec{F}$ is a {\em
dissimilarity} measure of $\vec{F}$, a generalization of the gradient magnitude
to vector-valued images, that can incorporate linear and nonlinear coordinate
transformations on the range of $\vec{F}$. In this way, the smoothing of the
multiple images associated with vector-valued data is coupled through the
conductance term, that fuses the information in the different images. Thus
vector-valued, nonlinear diffusion can combine low-level image features (e.g.
edges) across all ``channels'' of a vector-valued image in order to preserve or
enhance those features in all of image ``channels''.
Vector-valued anisotropic diffusion is useful for denoising data from devices
that produce multiple values such as MRI or color photography. When performing
nonlinear diffusion on a color image, the color channels are diffused
separately, but linked through the conductance term. Vector-valued diffusion it
is also useful for processing registered data from different devices or for
denoising higher-order geometric or statistical features from scalar-valued
images \cite{Whitaker1994,Yoo1993}.
The output of anisotropic diffusion is an image or set of images that
demonstrates reduced noise and texture but preserves, and can also enhance,
edges. Such images are useful for a variety of processes including
statistical classification, visualization, and geometric feature extraction.
Previous work has shown \cite{Whitaker-thesis} that anisotropic diffusion, over
a wide range of conductance parameters, offers quantifiable advantages over
linear filtering for edge detection in medical images.
Since the effectiveness of nonlinear diffusion was first demonstrated, numerous
variations of this approach have surfaced in the literature \cite{Romeny1994}.
These include alternatives for constructing dissimilarity measures
\cite{Sapiro1996}, directional (i.e., tensor-valued) conductance terms
\cite{Weickert1996,Alvarez1994} and level set interpretations
\cite{Whitaker2001}.
......@@ -105,17 +105,12 @@ ${SoftwareGuide_BINARY_DIR}/SoftwareGuideConfiguration.tex
)
SET( Tex_SRCS
Abstract.tex
Applications.tex
AnisotropicDiffusionFiltering.tex
DataRepresentation.tex
Filtering.tex
GUI.tex
ImageMetrics.tex
ImageInterpolators.tex
ImageAdaptors.tex
Infrastructure.tex
Introduction.tex
IO.tex
Iterators.tex
Numerics.tex
......@@ -127,7 +122,6 @@ SET( Tex_SRCS
SpatialObjects.tex
Statistics.tex
SystemOverview.tex
Transforms.tex
Visualization.tex
Watersheds.tex
Fusion.tex
......
\chapter{Data Representation}
\label{sec:DataRepresentation}
This chapter introduces the basic classes responsible
for representing data in OTB. The most common classes are the
\doxygen{otb}{Image}, the \doxygen{itk}{Mesh} and the \doxygen{itk}{PointSet}.
\section{Image}
\label{sec:ImageSection}
......@@ -132,9 +127,6 @@ are available in the RGBPixel class.
The following example illustrates how RGB images can be represented in OTB.
\label{sec:DefiningRGBImages}
\input{RGBImage.tex}
\subsection{Vector Images}
\label{sec:DefiningVectorImages}
......@@ -151,131 +143,3 @@ The following example illustrates how RGB images can be represented in OTB.
\input{ImageListExample.tex}
\section{PointSet}
\label{sec:PointSetSection}
\subsection{Creating a PointSet}
\label{sec:CreatingAPointSet}
\input{PointSet1.tex}
\subsection{Getting Access to Points}
\label{sec:GettingAccessToPointsInThePointSet}
\input{PointSet2.tex}
\subsection{Getting Access to Data in Points}
\label{sec:GettingAccessToDataInThePointSet}
\input{PointSet3.tex}
%\subsection{RGB as Pixel Type}
%\label{sec:PointSetWithRGBAsPixelType}
%\input{RGBPointSet.tex}
\subsection{Vectors as Pixel Type}
\label{sec:PointSetWithVectorsAsPixelType}
\input{PointSetWithVectors.tex}
%\subsection{Normals as Pixel Type}
%\label{sec:PointSetWithCovariantVectorsAsPixelType}
%\input{PointSetWithCovariantVectors.tex}
\section{Mesh}\label{MeshSection}
\subsection{Creating a Mesh}
\label{sec:CreatingAMesh}
\input{Mesh1.tex}
\subsection{Inserting Cells}
\label{sec:InsertingCellsInMesh}
\input{Mesh2.tex}
\subsection{Managing Data in Cells}
\label{sec:ManagingCellDataInMesh}
\input{Mesh3.tex}
More details about the use of \doxygen{itk}{Mesh} can be found in the
ITK Software Guide.
%\subsection{Customizing the Mesh}
%\label{sec:CustomizingTheMesh}
%\input{MeshTraits.tex}
%\subsection{Topology and the K-Complex}
%\label{sec:MeshKComplex}
%\input{MeshKComplex.tex}
%\subsection{Representing a PolyLine}
%\label{sec:MeshPolyLine}
%\input{MeshPolyLine.tex}
%\subsection{Simplifying Mesh Creation}
%\label{sec:AutomaticMesh}
%\input{AutomaticMesh.tex}
%\subsection{Iterating Through Cells}
%\label{sec:MeshCellsIteration}
%\input{MeshCellsIteration.tex}
%\subsection{Visiting Cells}
%\label{sec:MeshCellVisitor}
%\input{MeshCellVisitor.tex}
%\subsection{More on Visiting Cells}
%\label{sec:MeshCellVisitorMultipleType}
%\input{MeshCellVisitor2.tex}
\section{Path}\label{PathSection}
\subsection{Creating a PolyLineParametricPath}
\label{sec:CreatingAPolyLineParametricPath}
\input{PolyLineParametricPath1.tex}
%\section{Containers}\label{ContainersSection}
%\label{sec:TreeContainer}
%\input{TreeContainer.tex}
......@@ -1001,38 +1001,3 @@ sharp peak, in order to have a good precision for the shift estimate.\\
\input{FineRegistrationImageFilterExample.tex}
%% \fi
\section{Irregular grid disparity map estimation}
\label{sec:SimpleDisparityMapEstimationSparse}
Taking figure \ref{zones} as a starting point, we can generalize the
approach by letting the user choose:
\begin{itemize}
\item the similarity measure;
\item the geometric transform to be estimated (see definition
\ref{defin-T});
\end{itemize}
In order to do this, we will use the ITK registration framework
locally on a set of nodes. Once the disparity is estimated on a set of
nodes, we will use it to generate a deformation field: the dense,
regular vector field which gives the translation to be applied to
a pixel of the secondary image to be positioned on its homologous
point of the master image.
%% \ifitkFullVersion
\input{SimpleDisparityMapEstimationExample.tex}
%% \fi
% These examples are commented since they do not show valuable results
%\section{Probability Density Estimation (PDE) based disparity map estimation}
%\label{sec:PDEEstimation}
%\input{NCCRegistrationFilterExample.tex}
%\section{Landmark-based Disparity Map Estimation}
%\label{sec:Landmark-basedDisparityMapEstimation}
%\input{SIFTDisparityMapEstimation.tex}
\chapter{Feature Extraction}
% \section{Introduction}
Under the term {\em Feature Extraction} we include several techniques
aiming to detect or extract information of low level of abstraction
from images. These {\em features} can be objects : points, lines,
etc. They can also be measures : moments, textures, etc.
\section{Textures}
\subsection{Haralick Descriptors}
This example illustrates the use of the \doxygen{otb}{ScalarImageToTexturesFilter},
which computes the standard Haralick's textural features~\cite{Haralick1973}.
The \doxygen{otb}{ScalarImageToTexturesFilter} class computes 8 local Haralick
textures features presented in table~\ref{tab:haralickStandardFeatures},
where :
\begin{itemize}
\item $\mu_t$ and $\sigma_t$ are the mean and standard deviation of the row
(or column, due to symmetry) sums
\item $ \mu = $ (weighted pixel average)
$ = \sum_{i,j}i \cdot g(i, j) =\sum_{i,j}j \cdot g(i, j) $ due to matrix
symmetry
\item $ \sigma = $ (weighted pixel variance) $ = \sum_{i,j}(i - \mu)^2 \cdot g(i, j) =\sum_{i,j}(j - \mu)^2 \cdot g(i, j) $
due to matrix symmetry
\end{itemize}
\begin{table}
\begin{center}
\begin{tabular}[h!]{|c|c|}
\hline
& \\
Energy & $ f_1 = \sum_{i,j}g(i, j)^2 $ \\
& \\
\hline
& \\
Entropy & $ f_2 = -\sum_{i,j}g(i, j) \log_2 g(i, j)$, or 0 if $g(i, j) = 0$ \\
& \\
\hline
& \\
Correlation & $ f_3 = \sum_{i,j}\frac{(i - \mu)(j - \mu)g(i, j)}{\sigma^2} $ \\
& \\
\hline
& \\
Difference Moment & $f_4 = \sum_{i,j}\frac{1}{1 + (i - j)^2}g(i, j) $ \\
& \\
\hline
& \\
Inertia (a.k.a. Contrast) & $ f_5 = \sum_{i,j}(i - j)^2g(i, j) $ \\
& \\
\hline
& \\
Cluster Shade & $ f_6 = \sum_{i,j}((i - \mu) + (j - \mu))^3 g(i, j) $ \\
& \\
\hline
Cluster Prominence & $ f_7 = \sum_{i,j}((i - \mu) + (j - \mu))^4 g(i, j) $ \\
& \\
\hline
& \\
Haralick's Correlation & $ f_8 = \frac{\sum_{i,j}(i, j) g(i, j) -\mu_t^2}{\sigma_t^2} $ \\
& \\
\hline
\end{tabular}
\itkcaption[Haralick features]{Haralick features~\cite{Haralick1973} available in \doxygen{otb}{ScalarImageToTexturesFilter}}
\end{center}
\label{tab:haralickStandardFeatures}
\end{table}
Note that more features are available in
\doxygen{otb}{ScalarImageToAdvancedTexturesFilter} and in
\doxygen{otb}{ScalarImageToHigherOrderTexturesFilter}.
\doxygen{otb}{ScalarImageToAdvancedTexturesFilter} computes 10 advanced
texture features presented presented in table~\ref{tab:haralickAdvancedFeatures},
where:
\begin{itemize}
\item $ \mu = $ (weighted pixel average) = $ \sum_{i, j}i \cdot g(i, j) =
\sum_{i,j}j \cdot g(i, j) $ (due to matrix symmetry)
\item $N_{g}$ : Number of distinct gray levels in the quantized image
\item $ g_{x+y}(k) = \sum_{i}\sum_{j}g(i) $ where $ i+j=k $ and $ k = 2, 3, .., 2N_{g} $ and $ g_{x-y}(k) = \sum_{i}\sum_{j}g(i) $ where $ i-j=k $ and $ k = 0, 1, ..,N_{g}-1 $
\end{itemize}
\begin{table}
\begin{center}
\begin{tabular}[h!]{|c|c|}
\hline
& \\
Mean & $ f_{mean} = \sum_{i, j}i g(i, j) $ \\
& \\
\hline
& \\
Sum of squares: Variance & $ f_4 = \sum_{i, j}(i - \mu)^2 g(i, j) $ \\
& \\
\hline
& \\
Dissimilarity & $ f_5 = \sum_{i, j}(i - j) g(i, j)^2 $ \\
& \\
\hline
& \\
Sum average & $ f_6 = -\sum_{i}i g_{x+y}(i) $ \\
& \\
\hline
& \\
Sum Variance & $ f_7 = \sum_{i}(i - f_8)^2 g_{x+y}(i) $ \\
& \\
\hline
& \\
Sum Entropy & $ f_8 = -\sum_{i}g_{x+y}(i) log (g_{x+y}(i)) $ \\
& \\
\hline
Difference variance & $ f_{10} = variance of g_{x-y}(i) $ \\
& \\
\hline
& \\
Difference entropy & $ f_{11} = -\sum_{i}g_{x-y}(i) log (g_{x-y}(i)) $ \\
& \\
\hline
& \\
Information Measures of Correlation IC1 & $ f_{12} = \frac{f_9 - HXY1}{H} $ \\
& \\
\hline
& \\
Information Measures of Correlation IC2 & $ f_{13} = \sqrt{1 - \exp{-2}|HXY2 - f_9|} $ \\
& \\
\hline
\end{tabular}
\itkcaption[Haralick features]{Haralick features~\cite{Haralick1973} available in \doxygen{otb}{ScalarImageToAdvancedTexturesFilter}}
\end{center}
\label{tab:haralickAdvancedFeatures}
\end{table}
\doxygen{otb}{ScalarImageToHigherOrderTexturesFilter} computes 10
other local higher order statistics textures coefficients also based on the grey
level run-length matrix. Formulas for these coefficients are presented in
table~\ref{tab:haralickHigherOrderFeatures},where:
\begin{itemize}
\item $p(i, j)$ is the element in cell i
\item j of a normalized Run Length Matrix
\item $n_r$ is the total number of runs
\item $n_p$ is the total number of pixels
\end{itemize}
\begin{table}
\begin{center}
\begin{tabular}[h!]{|c|c|}
\hline
& \\
Short Run Emphasis & $ SRE = \frac{1}{n_r} \sum_{i, j}\frac{p(i, j)}{j^2} $ \\
& \\
\hline
& \\
Long Run Emphasis & $ LRE = \frac{1}{n_r} \sum_{i, j}p(i, j) * j^2 $ \\
& \\
\hline
& \\
Grey-Level Nonuniformity & $ GLN = \frac{1}{n_r} \sum_{i} \left( \sum_{j}{p(i, j)} \right)^2 $ \\
& \\
\hline
& \\
Run Length Nonuniformity & $ RLN = \frac{1}{n_r} \sum_{j} \left( \sum_{i}{p(i, j)} \right)^2 $ \\
& \\
\hline
& \\
Low Grey-Level Run Emphasis & $ LGRE = \frac{1}{n_r} \sum_{i, j}\frac{p(i, j)}{i^2} $ \\
& \\
\hline
& \\
High Grey-Level Run Emphasis & $ HGRE = \frac{1}{n_r} \sum_{i, j}p(i, j) * i^2 $ \\
& \\
\hline
Short Run Low Grey-Level Emphasis & $ SRLGE = \frac{1}{n_r} \sum_{i, j}\frac{p(i, j)}{i^2 j^2} $ \\
& \\
\hline
& \\
Short Run High Grey-Level Emphasis & $ SRHGE = \frac{1}{n_r} \sum_{i, j}\frac{p(i, j) * i^2}{j^2} $ \\
& \\
\hline
& \\
Long Run Low Grey-Level Emphasis & $ LRLGE = \frac{1}{n_r} \sum_{i, j}\frac{p(i, j) * j^2}{i^2} $ \\
& \\
\hline
& \\
Long Run High Grey-Level Emphasis & $ LRHGE = \frac{1}{n_r} \sum_{i, j} p(i, j) i^2 j^2 $ \\
& \\
\hline
\end{tabular}
\itkcaption[Haralick higher order features]{Haralick features~\cite{Haralick1973} available in \doxygen{otb}{ScalarImageToHigherOrderTexturesFilter}}
\end{center}
\label{tab:haralickHigherOrderFeatures}
\end{table}
\relatedClasses
\begin{itemize}
\item \doxygen{otb}{ScalarImageToAdvancedTexturesFilter}
\item \doxygen{otb}{ScalarImageToPanTexTextureFilter}
\item \doxygen{otb}{GreyLevelCooccurrenceIndexedList}
\item \doxygen{otb}{ScalarImageToHigherOrderTexturesFilter}
\end{itemize}
\input{TextureExample}
\subsection{PanTex}
\input{PanTexExample}
\subsection{Structural Feature Set}
\input{SFSExample}
\section{Interest Points}
......@@ -216,17 +13,10 @@ Long Run High Grey-Level Emphasis & $ LRHGE = \frac{1}{n_r} \sum_{i, j} p(i, j)
\input{HarrisExample}
\subsection{SIFT detector}
\label{sec:SIFTDetector}
% \input{SIFTFastExample}
\InputIfFileExists{SIFTFastExample.tex}{}{}
\subsection{SURF detector}
\input{SURFExample}
\section{Alignments}
\label{sec:Alignments}
\input{AlignmentsExample}
\section{Lines}
\label{sec:LineDetectors}
\subsection{Line Detection}
\label{sec:LineDetection}
\input{RatioLineDetectorExample}
......@@ -237,12 +27,6 @@ Long Run High Grey-Level Emphasis & $ LRHGE = \frac{1}{n_r} \sum_{i, j} p(i, j)
\subsection{Segment Extraction}
\label{sec:SegmentExtraction}
\subsubsection{Local Hough Transform}
\input{LocalHoughExample}
%\input{ExtractSegmentsByStepsExample}
%\input{ExtractSegmentsExample}
\subsubsection{Line Segment Detector}
\label{sec:LSD}
\input{LineSegmentDetectorExample}
\subsection{Right Angle Detector}
......
% Configuration file #1 for DeformableRegistration1.cxx
%
% This example demonstrates the setup of a basic registration
% problem that does NOT use multi-resolution strategies. As a
% result, only one value for the parameters between
% (# of pixels per element) and (maximum iterations) is necessary.
% If you were using multi-resolution, you would have to specify
% values for those parameters at each level of the pyramid.
%
% Note: the paths in the parameters assume you have the traditional
% ITK file hierarchy as shown below:
%
% ITK/Insight/Examples/Registration/DeformableRegistration1.cxx
% ITK/Insight/Examples/Data/RatLungSlice*
% ITK/Insight-Bin/bin/DeformableRegistration1
%
% ---------------------------------------------------------
% Parameters for the single- or multi-resolution techniques
% ---------------------------------------------------------
1 % Number of levels in the multi-res pyramid (1 = single-res)
1 % Highest level to use in the pyramid
1 1 % Scaling at lowest level of pyramid
4 % Number of pixels per element
1.e4 % Elasticity (E)
1.e4 % Density x capacity (RhoC)
1 % Image energy scaling (gamma) - sets gradient step size
2 % NumberOfIntegrationPoints
1 % WidthOfMetricRegion
20 % MaximumIterations
% -------------------------------
% Parameters for the registration
% -------------------------------
0 0.99 % Similarity metric (0=mean sq, 1 = ncc, 2=pattern int, 3=MI, 5=demons)
1.0 % Alpha
0 % DescentDirection (1 = max, 0 = min)
0 % DoLineSearch (0=never, 1=always, 2=if needed)
1.e1 % TimeStep
0.5 % Landmark variance
0 % Employ regridding / enforce diffeomorphism ( >= 1 -> true)
% ----------------------------------
% Information about the image inputs
% ----------------------------------
128 % Nx (image x dimension)
128 % Ny (image y dimension)
0 % Nz (image z dimension - not used if 2D)
../../Insight/Examples/Data/RatLungSlice1.mha % ReferenceFileName
../../Insight/Examples/Data/RatLungSlice2.mha % TargetFileName
% -------------------------------------------------------------------
% The actions below depend on the values of the flags preceding them.
% For example, to write out the displacement fields, you have to set
% the value of WriteDisplacementField to 1.
% -------------------------------------------------------------------
0 % UseLandmarks? - read the file name below if this is true
- % LandmarkFileName